diff options
Diffstat (limited to 'lib/gcc/arm-linux-androideabi')
69 files changed, 21603 insertions, 0 deletions
diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/crtbegin.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/crtbegin.o Binary files differnew file mode 100644 index 0000000..3a122ac --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/crtbegin.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/crtbeginS.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/crtbeginS.o Binary files differnew file mode 100644 index 0000000..285a463 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/crtbeginS.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/crtbeginT.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/crtbeginT.o Binary files differnew file mode 100644 index 0000000..3a122ac --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/crtbeginT.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/crtend.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/crtend.o Binary files differnew file mode 100644 index 0000000..a106689 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/crtend.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/crtendS.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/crtendS.o Binary files differnew file mode 100644 index 0000000..a106689 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/crtendS.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/crtbegin.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/crtbegin.o Binary files differnew file mode 100644 index 0000000..0157718 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/crtbegin.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/crtbeginS.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/crtbeginS.o Binary files differnew file mode 100644 index 0000000..6bbdcfb --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/crtbeginS.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/crtbeginT.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/crtbeginT.o Binary files differnew file mode 100644 index 0000000..0157718 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/crtbeginT.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/crtend.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/crtend.o Binary files differnew file mode 100644 index 0000000..f0d9ebb --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/crtend.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/crtendS.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/crtendS.o Binary files differnew file mode 100644 index 0000000..f0d9ebb --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/crtendS.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/libgcc.a b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/libgcc.a Binary files differnew file mode 100644 index 0000000..c430f1e --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/libgcc.a diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/libgcov.a b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/libgcov.a Binary files differnew file mode 100644 index 0000000..3bf4e16 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/hard/libgcov.a diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/libgcc.a b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/libgcc.a Binary files differnew file mode 100644 index 0000000..9f5b644 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/libgcc.a diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/libgcov.a b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/libgcov.a Binary files differnew file mode 100644 index 0000000..9f08a52 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/libgcov.a diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/crtbegin.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/crtbegin.o Binary files differnew file mode 100644 index 0000000..7b721f3 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/crtbegin.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/crtbeginS.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/crtbeginS.o Binary files differnew file mode 100644 index 0000000..a2edda6 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/crtbeginS.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/crtbeginT.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/crtbeginT.o Binary files differnew file mode 100644 index 0000000..7b721f3 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/crtbeginT.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/crtend.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/crtend.o Binary files differnew file mode 100644 index 0000000..7b9d5b4 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/crtend.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/crtendS.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/crtendS.o Binary files differnew file mode 100644 index 0000000..7b9d5b4 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/crtendS.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/crtbegin.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/crtbegin.o Binary files differnew file mode 100644 index 0000000..85e43a2 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/crtbegin.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/crtbeginS.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/crtbeginS.o Binary files differnew file mode 100644 index 0000000..c7e3fba --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/crtbeginS.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/crtbeginT.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/crtbeginT.o Binary files differnew file mode 100644 index 0000000..85e43a2 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/crtbeginT.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/crtend.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/crtend.o Binary files differnew file mode 100644 index 0000000..92f272a --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/crtend.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/crtendS.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/crtendS.o Binary files differnew file mode 100644 index 0000000..92f272a --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/crtendS.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/libgcc.a b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/libgcc.a Binary files differnew file mode 100644 index 0000000..1200890 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/libgcc.a diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/libgcov.a b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/libgcov.a Binary files differnew file mode 100644 index 0000000..9353146 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/hard/libgcov.a diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/libgcc.a b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/libgcc.a Binary files differnew file mode 100644 index 0000000..c897efc --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/libgcc.a diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/libgcov.a b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/libgcov.a Binary files differnew file mode 100644 index 0000000..55e7cea --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/armv7-a/thumb/libgcov.a diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/crtbegin.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/crtbegin.o Binary files differnew file mode 100644 index 0000000..70e314f --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/crtbegin.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/crtbeginS.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/crtbeginS.o Binary files differnew file mode 100644 index 0000000..adceac9 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/crtbeginS.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/crtbeginT.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/crtbeginT.o Binary files differnew file mode 100644 index 0000000..70e314f --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/crtbeginT.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/crtend.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/crtend.o Binary files differnew file mode 100644 index 0000000..a63b41b --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/crtend.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/crtendS.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/crtendS.o Binary files differnew file mode 100644 index 0000000..a63b41b --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/crtendS.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/gcov-src/gcov-io.c b/lib/gcc/arm-linux-androideabi/4.9.x-google/gcov-src/gcov-io.c new file mode 100644 index 0000000..f226cbf --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/gcov-src/gcov-io.c @@ -0,0 +1,1088 @@ +/* File format for coverage information + Copyright (C) 1996-2014 Free Software Foundation, Inc. + Contributed by Bob Manson <manson@cygnus.com>. + Completely remangled by Nathan Sidwell <nathan@codesourcery.com>. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify it under +the terms of the GNU General Public License as published by the Free +Software Foundation; either version 3, or (at your option) any later +version. + +GCC is distributed in the hope that it will be useful, but WITHOUT ANY +WARRANTY; without even the implied warranty of MERCHANTABILITY or +FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + +/* Routines declared in gcov-io.h. This file should be #included by + another source file, after having #included gcov-io.h. */ + +#if !IN_GCOV +static void gcov_write_block (unsigned); +static gcov_unsigned_t *gcov_write_words (unsigned); +#endif +static const gcov_unsigned_t *gcov_read_words (unsigned); +#if !IN_LIBGCOV +static void gcov_allocate (unsigned); +#endif + +/* Optimum number of gcov_unsigned_t's read from or written to disk. */ +#define GCOV_BLOCK_SIZE (1 << 10) + +GCOV_LINKAGE struct gcov_var +{ + FILE *file; + gcov_position_t start; /* Position of first byte of block */ + unsigned offset; /* Read/write position within the block. */ + unsigned length; /* Read limit in the block. */ + unsigned overread; /* Number of words overread. */ + int error; /* < 0 overflow, > 0 disk error. */ + int mode; /* < 0 writing, > 0 reading */ +#if IN_LIBGCOV + /* Holds one block plus 4 bytes, thus all coverage reads & writes + fit within this buffer and we always can transfer GCOV_BLOCK_SIZE + to and from the disk. libgcov never backtracks and only writes 4 + or 8 byte objects. */ + gcov_unsigned_t buffer[GCOV_BLOCK_SIZE + 1]; +#else + int endian; /* Swap endianness. */ + /* Holds a variable length block, as the compiler can write + strings and needs to backtrack. */ + size_t alloc; + gcov_unsigned_t *buffer; +#endif +} gcov_var; + +/* Save the current position in the gcov file. */ +/* We need to expose this function when compiling for gcov-tool. */ +#ifndef IN_GCOV_TOOL +static inline +#endif +gcov_position_t +gcov_position (void) +{ + return gcov_var.start + gcov_var.offset; +} + +/* Return nonzero if the error flag is set. */ +/* We need to expose this function when compiling for gcov-tool. */ +#ifndef IN_GCOV_TOOL +static inline +#endif +int +gcov_is_error (void) +{ + return gcov_var.file ? gcov_var.error : 1; +} + +#if IN_LIBGCOV +/* Move to beginning of file and initialize for writing. */ +GCOV_LINKAGE inline void +gcov_rewrite (void) +{ + gcc_assert (gcov_var.mode > 0); + gcov_var.mode = -1; + gcov_var.start = 0; + gcov_var.offset = 0; + fseek (gcov_var.file, 0L, SEEK_SET); +} +#endif + +static inline gcov_unsigned_t from_file (gcov_unsigned_t value) +{ +#if !IN_LIBGCOV + if (gcov_var.endian) + { + value = (value >> 16) | (value << 16); + value = ((value & 0xff00ff) << 8) | ((value >> 8) & 0xff00ff); + } +#endif + return value; +} + +/* Open a gcov file. NAME is the name of the file to open and MODE + indicates whether a new file should be created, or an existing file + opened. If MODE is >= 0 an existing file will be opened, if + possible, and if MODE is <= 0, a new file will be created. Use + MODE=0 to attempt to reopen an existing file and then fall back on + creating a new one. If MODE < 0, the file will be opened in + read-only mode. Otherwise it will be opened for modification. + Return zero on failure, >0 on opening an existing file and <0 on + creating a new one. */ + +GCOV_LINKAGE int +#if IN_LIBGCOV +gcov_open (const char *name) +#else +gcov_open (const char *name, int mode) +#endif +{ +#if IN_LIBGCOV + const int mode = 0; +#endif +#if GCOV_LOCKED + struct flock s_flock; + int fd; + + s_flock.l_whence = SEEK_SET; + s_flock.l_start = 0; + s_flock.l_len = 0; /* Until EOF. */ + s_flock.l_pid = getpid (); +#endif + + gcc_assert (!gcov_var.file); + gcov_var.start = 0; + gcov_var.offset = gcov_var.length = 0; + gcov_var.overread = -1u; + gcov_var.error = 0; +#if !IN_LIBGCOV + gcov_var.endian = 0; +#endif +#if GCOV_LOCKED + if (mode > 0) + { + /* Read-only mode - acquire a read-lock. */ + s_flock.l_type = F_RDLCK; + /* pass mode (ignored) for compatibility */ + fd = open (name, O_RDONLY, S_IRUSR | S_IWUSR); + } + else if (mode < 0) + { + /* Write mode - acquire a write-lock. */ + s_flock.l_type = F_WRLCK; + fd = open (name, O_RDWR | O_CREAT | O_TRUNC, 0666); + } + else /* mode == 0 */ + { + /* Read-Write mode - acquire a write-lock. */ + s_flock.l_type = F_WRLCK; + fd = open (name, O_RDWR | O_CREAT, 0666); + } + if (fd < 0) + return 0; + + while (fcntl (fd, F_SETLKW, &s_flock) && errno == EINTR) + continue; + + gcov_var.file = fdopen (fd, (mode > 0) ? "rb" : "r+b"); + + if (!gcov_var.file) + { + close (fd); + return 0; + } + + if (mode > 0) + gcov_var.mode = 1; + else if (mode == 0) + { + struct stat st; + + if (fstat (fd, &st) < 0) + { + fclose (gcov_var.file); + gcov_var.file = 0; + return 0; + } + if (st.st_size != 0) + gcov_var.mode = 1; + else + gcov_var.mode = mode * 2 + 1; + } + else + gcov_var.mode = mode * 2 + 1; +#else + if (mode >= 0) + gcov_var.file = fopen (name, (mode > 0) ? "rb" : "r+b"); + + if (gcov_var.file) + gcov_var.mode = 1; + else if (mode <= 0) + { + gcov_var.file = fopen (name, "w+b"); + if (gcov_var.file) + gcov_var.mode = mode * 2 + 1; + } + if (!gcov_var.file) + return 0; +#endif + + setbuf (gcov_var.file, (char *)0); + + return 1; +} + +/* Close the current gcov file. Flushes data to disk. Returns nonzero + on failure or error flag set. */ + +GCOV_LINKAGE int +gcov_close (void) +{ + if (gcov_var.file) + { +#if !IN_GCOV + if (gcov_var.offset && gcov_var.mode < 0) + gcov_write_block (gcov_var.offset); +#endif + fclose (gcov_var.file); + gcov_var.file = 0; + gcov_var.length = 0; + } +#if !IN_LIBGCOV + free (gcov_var.buffer); + gcov_var.alloc = 0; + gcov_var.buffer = 0; +#endif + gcov_var.mode = 0; + return gcov_var.error; +} + +#if !IN_LIBGCOV +/* Check if MAGIC is EXPECTED. Use it to determine endianness of the + file. Returns +1 for same endian, -1 for other endian and zero for + not EXPECTED. */ + +GCOV_LINKAGE int +gcov_magic (gcov_unsigned_t magic, gcov_unsigned_t expected) +{ + if (magic == expected) + return 1; + magic = (magic >> 16) | (magic << 16); + magic = ((magic & 0xff00ff) << 8) | ((magic >> 8) & 0xff00ff); + if (magic == expected) + { + gcov_var.endian = 1; + return -1; + } + return 0; +} +#endif + +#if !IN_LIBGCOV +static void +gcov_allocate (unsigned length) +{ + size_t new_size = gcov_var.alloc; + + if (!new_size) + new_size = GCOV_BLOCK_SIZE; + new_size += length; + new_size *= 2; + + gcov_var.alloc = new_size; + gcov_var.buffer = XRESIZEVAR (gcov_unsigned_t, gcov_var.buffer, new_size << 2); +} +#endif + +#if !IN_GCOV +/* Write out the current block, if needs be. */ + +static void +gcov_write_block (unsigned size) +{ + if (fwrite (gcov_var.buffer, size << 2, 1, gcov_var.file) != 1) + gcov_var.error = 1; + gcov_var.start += size; + gcov_var.offset -= size; +} + +/* Allocate space to write BYTES bytes to the gcov file. Return a + pointer to those bytes, or NULL on failure. */ + +static gcov_unsigned_t * +gcov_write_words (unsigned words) +{ + gcov_unsigned_t *result; + + gcc_assert (gcov_var.mode < 0); +#if IN_LIBGCOV + if (gcov_var.offset >= GCOV_BLOCK_SIZE) + { + gcov_write_block (GCOV_BLOCK_SIZE); + if (gcov_var.offset) + { + gcc_assert (gcov_var.offset == 1); + memcpy (gcov_var.buffer, gcov_var.buffer + GCOV_BLOCK_SIZE, 4); + } + } +#else + if (gcov_var.offset + words > gcov_var.alloc) + gcov_allocate (gcov_var.offset + words); +#endif + result = &gcov_var.buffer[gcov_var.offset]; + gcov_var.offset += words; + + return result; +} + +/* Write unsigned VALUE to coverage file. Sets error flag + appropriately. */ + +GCOV_LINKAGE void +gcov_write_unsigned (gcov_unsigned_t value) +{ + gcov_unsigned_t *buffer = gcov_write_words (1); + + buffer[0] = value; +} + +/* Write counter VALUE to coverage file. Sets error flag + appropriately. */ + +#if IN_LIBGCOV +GCOV_LINKAGE void +gcov_write_counter (gcov_type value) +{ + gcov_unsigned_t *buffer = gcov_write_words (2); + + buffer[0] = (gcov_unsigned_t) value; + if (sizeof (value) > sizeof (gcov_unsigned_t)) + buffer[1] = (gcov_unsigned_t) (value >> 32); + else + buffer[1] = 0; +} +#endif /* IN_LIBGCOV */ + +#if !IN_LIBGCOV +/* Write STRING to coverage file. Sets error flag on file + error, overflow flag on overflow */ + +GCOV_LINKAGE void +gcov_write_string (const char *string) +{ + unsigned length = 0; + unsigned alloc = 0; + gcov_unsigned_t *buffer; + + if (string) + { + length = strlen (string); + alloc = (length + 4) >> 2; + } + + buffer = gcov_write_words (1 + alloc); + + buffer[0] = alloc; + buffer[alloc] = 0; + memcpy (&buffer[1], string, length); +} +#endif + +#if !IN_LIBGCOV +/* Write a tag TAG and reserve space for the record length. Return a + value to be used for gcov_write_length. */ + +GCOV_LINKAGE gcov_position_t +gcov_write_tag (gcov_unsigned_t tag) +{ + gcov_position_t result = gcov_var.start + gcov_var.offset; + gcov_unsigned_t *buffer = gcov_write_words (2); + + buffer[0] = tag; + buffer[1] = 0; + + return result; +} + +/* Write a record length using POSITION, which was returned by + gcov_write_tag. The current file position is the end of the + record, and is restored before returning. Returns nonzero on + overflow. */ + +GCOV_LINKAGE void +gcov_write_length (gcov_position_t position) +{ + unsigned offset; + gcov_unsigned_t length; + gcov_unsigned_t *buffer; + + gcc_assert (gcov_var.mode < 0); + gcc_assert (position + 2 <= gcov_var.start + gcov_var.offset); + gcc_assert (position >= gcov_var.start); + offset = position - gcov_var.start; + length = gcov_var.offset - offset - 2; + buffer = (gcov_unsigned_t *) &gcov_var.buffer[offset]; + buffer[1] = length; + if (gcov_var.offset >= GCOV_BLOCK_SIZE) + gcov_write_block (gcov_var.offset); +} + +#else /* IN_LIBGCOV */ + +/* Write a tag TAG and length LENGTH. */ + +GCOV_LINKAGE void +gcov_write_tag_length (gcov_unsigned_t tag, gcov_unsigned_t length) +{ + gcov_unsigned_t *buffer = gcov_write_words (2); + + buffer[0] = tag; + buffer[1] = length; +} + +/* Write a summary structure to the gcov file. Return nonzero on + overflow. */ + +GCOV_LINKAGE void +gcov_write_summary (gcov_unsigned_t tag, const struct gcov_summary *summary) +{ + unsigned ix, h_ix, bv_ix, h_cnt = 0; + const struct gcov_ctr_summary *csum; + unsigned histo_bitvector[GCOV_HISTOGRAM_BITVECTOR_SIZE]; + + /* Count number of non-zero histogram entries, and fill in a bit vector + of non-zero indices. The histogram is only currently computed for arc + counters. */ + for (bv_ix = 0; bv_ix < GCOV_HISTOGRAM_BITVECTOR_SIZE; bv_ix++) + histo_bitvector[bv_ix] = 0; + csum = &summary->ctrs[GCOV_COUNTER_ARCS]; + for (h_ix = 0; h_ix < GCOV_HISTOGRAM_SIZE; h_ix++) + { + if (csum->histogram[h_ix].num_counters > 0) + { + histo_bitvector[h_ix / 32] |= 1 << (h_ix % 32); + h_cnt++; + } + } + gcov_write_tag_length (tag, GCOV_TAG_SUMMARY_LENGTH (h_cnt)); + gcov_write_unsigned (summary->checksum); + for (csum = summary->ctrs, ix = GCOV_COUNTERS_SUMMABLE; ix--; csum++) + { + gcov_write_unsigned (csum->num); + gcov_write_unsigned (csum->runs); + gcov_write_counter (csum->sum_all); + gcov_write_counter (csum->run_max); + gcov_write_counter (csum->sum_max); + if (ix != GCOV_COUNTER_ARCS) + { + for (bv_ix = 0; bv_ix < GCOV_HISTOGRAM_BITVECTOR_SIZE; bv_ix++) + gcov_write_unsigned (0); + continue; + } + for (bv_ix = 0; bv_ix < GCOV_HISTOGRAM_BITVECTOR_SIZE; bv_ix++) + gcov_write_unsigned (histo_bitvector[bv_ix]); + for (h_ix = 0; h_ix < GCOV_HISTOGRAM_SIZE; h_ix++) + { + if (!csum->histogram[h_ix].num_counters) + continue; + gcov_write_unsigned (csum->histogram[h_ix].num_counters); + gcov_write_counter (csum->histogram[h_ix].min_value); + gcov_write_counter (csum->histogram[h_ix].cum_value); + } + } +} +#endif /* IN_LIBGCOV */ + +#endif /*!IN_GCOV */ + +/* Return a pointer to read BYTES bytes from the gcov file. Returns + NULL on failure (read past EOF). */ + +static const gcov_unsigned_t * +gcov_read_words (unsigned words) +{ + const gcov_unsigned_t *result; + unsigned excess = gcov_var.length - gcov_var.offset; + + gcc_assert (gcov_var.mode > 0); + if (excess < words) + { + gcov_var.start += gcov_var.offset; +#if IN_LIBGCOV + if (excess) + { + gcc_assert (excess == 1); + memcpy (gcov_var.buffer, gcov_var.buffer + gcov_var.offset, 4); + } +#else + memmove (gcov_var.buffer, gcov_var.buffer + gcov_var.offset, excess * 4); +#endif + gcov_var.offset = 0; + gcov_var.length = excess; +#if IN_LIBGCOV + gcc_assert (!gcov_var.length || gcov_var.length == 1); + excess = GCOV_BLOCK_SIZE; +#else + if (gcov_var.length + words > gcov_var.alloc) + gcov_allocate (gcov_var.length + words); + excess = gcov_var.alloc - gcov_var.length; +#endif + excess = fread (gcov_var.buffer + gcov_var.length, + 1, excess << 2, gcov_var.file) >> 2; + gcov_var.length += excess; + if (gcov_var.length < words) + { + gcov_var.overread += words - gcov_var.length; + gcov_var.length = 0; + return 0; + } + } + result = &gcov_var.buffer[gcov_var.offset]; + gcov_var.offset += words; + return result; +} + +/* Read unsigned value from a coverage file. Sets error flag on file + error, overflow flag on overflow */ + +GCOV_LINKAGE gcov_unsigned_t +gcov_read_unsigned (void) +{ + gcov_unsigned_t value; + const gcov_unsigned_t *buffer = gcov_read_words (1); + + if (!buffer) + return 0; + value = from_file (buffer[0]); + return value; +} + +/* Read counter value from a coverage file. Sets error flag on file + error, overflow flag on overflow */ + +GCOV_LINKAGE gcov_type +gcov_read_counter (void) +{ + gcov_type value; + const gcov_unsigned_t *buffer = gcov_read_words (2); + + if (!buffer) + return 0; + value = from_file (buffer[0]); + if (sizeof (value) > sizeof (gcov_unsigned_t)) + value |= ((gcov_type) from_file (buffer[1])) << 32; + else if (buffer[1]) + gcov_var.error = -1; + + return value; +} + +/* We need to expose the below function when compiling for gcov-tool. */ + +#if !IN_LIBGCOV || defined (IN_GCOV_TOOL) +/* Read string from coverage file. Returns a pointer to a static + buffer, or NULL on empty string. You must copy the string before + calling another gcov function. */ + +GCOV_LINKAGE const char * +gcov_read_string (void) +{ + unsigned length = gcov_read_unsigned (); + + if (!length) + return 0; + + return (const char *) gcov_read_words (length); +} +#endif + +GCOV_LINKAGE void +gcov_read_summary (struct gcov_summary *summary) +{ + unsigned ix, h_ix, bv_ix, h_cnt = 0; + struct gcov_ctr_summary *csum; + unsigned histo_bitvector[GCOV_HISTOGRAM_BITVECTOR_SIZE]; + unsigned cur_bitvector; + + summary->checksum = gcov_read_unsigned (); + for (csum = summary->ctrs, ix = GCOV_COUNTERS_SUMMABLE; ix--; csum++) + { + csum->num = gcov_read_unsigned (); + csum->runs = gcov_read_unsigned (); + csum->sum_all = gcov_read_counter (); + csum->run_max = gcov_read_counter (); + csum->sum_max = gcov_read_counter (); + memset (csum->histogram, 0, + sizeof (gcov_bucket_type) * GCOV_HISTOGRAM_SIZE); + for (bv_ix = 0; bv_ix < GCOV_HISTOGRAM_BITVECTOR_SIZE; bv_ix++) + { + histo_bitvector[bv_ix] = gcov_read_unsigned (); +#if IN_LIBGCOV + /* When building libgcov we don't include system.h, which includes + hwint.h (where popcount_hwi is declared). However, libgcov.a + is built by the bootstrapped compiler and therefore the builtins + are always available. */ + h_cnt += __builtin_popcount (histo_bitvector[bv_ix]); +#else + h_cnt += popcount_hwi (histo_bitvector[bv_ix]); +#endif + } + bv_ix = 0; + h_ix = 0; + cur_bitvector = 0; + while (h_cnt--) + { + /* Find the index corresponding to the next entry we will read in. + First find the next non-zero bitvector and re-initialize + the histogram index accordingly, then right shift and increment + the index until we find a set bit. */ + while (!cur_bitvector) + { + h_ix = bv_ix * 32; + gcc_assert (bv_ix < GCOV_HISTOGRAM_BITVECTOR_SIZE); + cur_bitvector = histo_bitvector[bv_ix++]; + } + while (!(cur_bitvector & 0x1)) + { + h_ix++; + cur_bitvector >>= 1; + } + gcc_assert (h_ix < GCOV_HISTOGRAM_SIZE); + + csum->histogram[h_ix].num_counters = gcov_read_unsigned (); + csum->histogram[h_ix].min_value = gcov_read_counter (); + csum->histogram[h_ix].cum_value = gcov_read_counter (); + /* Shift off the index we are done with and increment to the + corresponding next histogram entry. */ + cur_bitvector >>= 1; + h_ix++; + } + } +} + +#if (!IN_LIBGCOV && IN_GCOV != 1) || defined (IN_GCOV_TOOL) +/* Read LEN words (unsigned type) and construct MOD_INFO. */ + +GCOV_LINKAGE void +gcov_read_module_info (struct gcov_module_info *mod_info, + gcov_unsigned_t len) +{ + gcov_unsigned_t src_filename_len, filename_len, i, j, num_strings; + mod_info->ident = gcov_read_unsigned (); + mod_info->is_primary = gcov_read_unsigned (); + mod_info->flags = gcov_read_unsigned (); + mod_info->lang = gcov_read_unsigned (); + mod_info->ggc_memory = gcov_read_unsigned (); + mod_info->num_quote_paths = gcov_read_unsigned (); + mod_info->num_bracket_paths = gcov_read_unsigned (); + mod_info->num_system_paths = gcov_read_unsigned (); + mod_info->num_cpp_defines = gcov_read_unsigned (); + mod_info->num_cpp_includes = gcov_read_unsigned (); + mod_info->num_cl_args = gcov_read_unsigned (); + len -= 11; + + filename_len = gcov_read_unsigned (); + mod_info->da_filename = (char *) xmalloc (filename_len * + sizeof (gcov_unsigned_t)); + for (i = 0; i < filename_len; i++) + ((gcov_unsigned_t *) mod_info->da_filename)[i] = gcov_read_unsigned (); + len -= (filename_len + 1); + + src_filename_len = gcov_read_unsigned (); + mod_info->source_filename = (char *) xmalloc (src_filename_len * + sizeof (gcov_unsigned_t)); + for (i = 0; i < src_filename_len; i++) + ((gcov_unsigned_t *) mod_info->source_filename)[i] = gcov_read_unsigned (); + len -= (src_filename_len + 1); + + num_strings = mod_info->num_quote_paths + mod_info->num_bracket_paths + + mod_info->num_system_paths + + mod_info->num_cpp_defines + mod_info->num_cpp_includes + + mod_info->num_cl_args; + for (j = 0; j < num_strings; j++) + { + gcov_unsigned_t string_len = gcov_read_unsigned (); + mod_info->string_array[j] = + (char *) xmalloc (string_len * sizeof (gcov_unsigned_t)); + for (i = 0; i < string_len; i++) + ((gcov_unsigned_t *) mod_info->string_array[j])[i] = + gcov_read_unsigned (); + len -= (string_len + 1); + } + gcc_assert (!len); +} +#endif + +/* We need to expose the below function when compiling for gcov-tool. */ + +#if !IN_LIBGCOV || defined (IN_GCOV_TOOL) +/* Reset to a known position. BASE should have been obtained from + gcov_position, LENGTH should be a record length. */ + +GCOV_LINKAGE void +gcov_sync (gcov_position_t base, gcov_unsigned_t length) +{ + gcc_assert (gcov_var.mode > 0); + base += length; + if (base - gcov_var.start <= gcov_var.length) + gcov_var.offset = base - gcov_var.start; + else + { + gcov_var.offset = gcov_var.length = 0; + fseek (gcov_var.file, base << 2, SEEK_SET); + gcov_var.start = ftell (gcov_var.file) >> 2; + } +} +#endif + +#if IN_LIBGCOV +/* Move to a given position in a gcov file. */ + +GCOV_LINKAGE void +gcov_seek (gcov_position_t base) +{ + gcc_assert (gcov_var.mode < 0); + if (gcov_var.offset) + gcov_write_block (gcov_var.offset); + fseek (gcov_var.file, base << 2, SEEK_SET); + gcov_var.start = ftell (gcov_var.file) >> 2; +} + +/* Truncate the gcov file at the current position. */ + +GCOV_LINKAGE void +gcov_truncate (void) +{ + long offs; + int filenum; + gcc_assert (gcov_var.mode < 0); + if (gcov_var.offset) + gcov_write_block (gcov_var.offset); + offs = ftell (gcov_var.file); + filenum = fileno (gcov_var.file); + if (offs == -1 || filenum == -1 || ftruncate (filenum, offs)) + gcov_var.error = 1; +} +#endif + +#if IN_GCOV > 0 +/* Return the modification time of the current gcov file. */ + +GCOV_LINKAGE time_t +gcov_time (void) +{ + struct stat status; + + if (fstat (fileno (gcov_var.file), &status)) + return 0; + else + return status.st_mtime; +} +#endif /* IN_GCOV */ + +#if !IN_GCOV +/* Determine the index into histogram for VALUE. */ + +#if IN_LIBGCOV +static unsigned +#else +GCOV_LINKAGE unsigned +#endif +gcov_histo_index (gcov_type value) +{ + gcov_type_unsigned v = (gcov_type_unsigned)value; + unsigned r = 0; + unsigned prev2bits = 0; + + /* Find index into log2 scale histogram, where each of the log2 + sized buckets is divided into 4 linear sub-buckets for better + focus in the higher buckets. */ + + /* Find the place of the most-significant bit set. */ + if (v > 0) + { +#if IN_LIBGCOV + /* When building libgcov we don't include system.h, which includes + hwint.h (where floor_log2 is declared). However, libgcov.a + is built by the bootstrapped compiler and therefore the builtins + are always available. */ + r = sizeof (long long) * __CHAR_BIT__ - 1 - __builtin_clzll (v); +#else + /* We use floor_log2 from hwint.c, which takes a HOST_WIDE_INT + that is either 32 or 64 bits, and gcov_type_unsigned may be 64 bits. + Need to check for the case where gcov_type_unsigned is 64 bits + and HOST_WIDE_INT is 32 bits and handle it specially. */ +#if HOST_BITS_PER_WIDEST_INT == HOST_BITS_PER_WIDE_INT + r = floor_log2 (v); +#elif HOST_BITS_PER_WIDEST_INT == 2 * HOST_BITS_PER_WIDE_INT + HOST_WIDE_INT hwi_v = v >> HOST_BITS_PER_WIDE_INT; + if (hwi_v) + r = floor_log2 (hwi_v) + HOST_BITS_PER_WIDE_INT; + else + r = floor_log2 ((HOST_WIDE_INT)v); +#else + gcc_unreachable (); +#endif +#endif + } + + /* If at most the 2 least significant bits are set (value is + 0 - 3) then that value is our index into the lowest set of + four buckets. */ + if (r < 2) + return (unsigned)value; + + gcc_assert (r < 64); + + /* Find the two next most significant bits to determine which + of the four linear sub-buckets to select. */ + prev2bits = (v >> (r - 2)) & 0x3; + /* Finally, compose the final bucket index from the log2 index and + the next 2 bits. The minimum r value at this point is 2 since we + returned above if r was 2 or more, so the minimum bucket at this + point is 4. */ + return (r - 1) * 4 + prev2bits; +} + +/* Merge SRC_HISTO into TGT_HISTO. The counters are assumed to be in + the same relative order in both histograms, and are matched up + and merged in reverse order. Each counter is assigned an equal portion of + its entry's original cumulative counter value when computing the + new merged cum_value. */ + +static void gcov_histogram_merge (gcov_bucket_type *tgt_histo, + gcov_bucket_type *src_histo) +{ + int src_i, tgt_i, tmp_i = 0; + unsigned src_num, tgt_num, merge_num; + gcov_type src_cum, tgt_cum, merge_src_cum, merge_tgt_cum, merge_cum; + gcov_type merge_min; + gcov_bucket_type tmp_histo[GCOV_HISTOGRAM_SIZE]; + int src_done = 0; + + memset (tmp_histo, 0, sizeof (gcov_bucket_type) * GCOV_HISTOGRAM_SIZE); + + /* Assume that the counters are in the same relative order in both + histograms. Walk the histograms from largest to smallest entry, + matching up and combining counters in order. */ + src_num = 0; + src_cum = 0; + src_i = GCOV_HISTOGRAM_SIZE - 1; + for (tgt_i = GCOV_HISTOGRAM_SIZE - 1; tgt_i >= 0 && !src_done; tgt_i--) + { + tgt_num = tgt_histo[tgt_i].num_counters; + tgt_cum = tgt_histo[tgt_i].cum_value; + /* Keep going until all of the target histogram's counters at this + position have been matched and merged with counters from the + source histogram. */ + while (tgt_num > 0 && !src_done) + { + /* If this is either the first time through this loop or we just + exhausted the previous non-zero source histogram entry, look + for the next non-zero source histogram entry. */ + if (!src_num) + { + /* Locate the next non-zero entry. */ + while (src_i >= 0 && !src_histo[src_i].num_counters) + src_i--; + /* If source histogram has fewer counters, then just copy over the + remaining target counters and quit. */ + if (src_i < 0) + { + tmp_histo[tgt_i].num_counters += tgt_num; + tmp_histo[tgt_i].cum_value += tgt_cum; + if (!tmp_histo[tgt_i].min_value || + tgt_histo[tgt_i].min_value < tmp_histo[tgt_i].min_value) + tmp_histo[tgt_i].min_value = tgt_histo[tgt_i].min_value; + while (--tgt_i >= 0) + { + tmp_histo[tgt_i].num_counters + += tgt_histo[tgt_i].num_counters; + tmp_histo[tgt_i].cum_value += tgt_histo[tgt_i].cum_value; + if (!tmp_histo[tgt_i].min_value || + tgt_histo[tgt_i].min_value + < tmp_histo[tgt_i].min_value) + tmp_histo[tgt_i].min_value = tgt_histo[tgt_i].min_value; + } + + src_done = 1; + break; + } + + src_num = src_histo[src_i].num_counters; + src_cum = src_histo[src_i].cum_value; + } + + /* The number of counters to merge on this pass is the minimum + of the remaining counters from the current target and source + histogram entries. */ + merge_num = tgt_num; + if (src_num < merge_num) + merge_num = src_num; + + /* The merged min_value is the sum of the min_values from target + and source. */ + merge_min = tgt_histo[tgt_i].min_value + src_histo[src_i].min_value; + + /* Compute the portion of source and target entries' cum_value + that will be apportioned to the counters being merged. + The total remaining cum_value from each entry is divided + equally among the counters from that histogram entry if we + are not merging all of them. */ + merge_src_cum = src_cum; + if (merge_num < src_num) + merge_src_cum = merge_num * src_cum / src_num; + merge_tgt_cum = tgt_cum; + if (merge_num < tgt_num) + merge_tgt_cum = merge_num * tgt_cum / tgt_num; + /* The merged cum_value is the sum of the source and target + components. */ + merge_cum = merge_src_cum + merge_tgt_cum; + + /* Update the remaining number of counters and cum_value left + to be merged from this source and target entry. */ + src_cum -= merge_src_cum; + tgt_cum -= merge_tgt_cum; + src_num -= merge_num; + tgt_num -= merge_num; + + /* The merged counters get placed in the new merged histogram + at the entry for the merged min_value. */ + tmp_i = gcov_histo_index (merge_min); + gcc_assert (tmp_i < GCOV_HISTOGRAM_SIZE); + tmp_histo[tmp_i].num_counters += merge_num; + tmp_histo[tmp_i].cum_value += merge_cum; + if (!tmp_histo[tmp_i].min_value || + merge_min < tmp_histo[tmp_i].min_value) + tmp_histo[tmp_i].min_value = merge_min; + + /* Ensure the search for the next non-zero src_histo entry starts + at the next smallest histogram bucket. */ + if (!src_num) + src_i--; + } + } + + gcc_assert (tgt_i < 0); + + /* In the case where there were more counters in the source histogram, + accumulate the remaining unmerged cumulative counter values. Add + those to the smallest non-zero target histogram entry. Otherwise, + the total cumulative counter values in the histogram will be smaller + than the sum_all stored in the summary, which will complicate + computing the working set information from the histogram later on. */ + if (src_num) + src_i--; + while (src_i >= 0) + { + src_cum += src_histo[src_i].cum_value; + src_i--; + } + /* At this point, tmp_i should be the smallest non-zero entry in the + tmp_histo. */ + gcc_assert (tmp_i >= 0 && tmp_i < GCOV_HISTOGRAM_SIZE + && tmp_histo[tmp_i].num_counters > 0); + tmp_histo[tmp_i].cum_value += src_cum; + + /* Finally, copy the merged histogram into tgt_histo. */ + memcpy (tgt_histo, tmp_histo, + sizeof (gcov_bucket_type) * GCOV_HISTOGRAM_SIZE); +} +#endif /* !IN_GCOV */ + +/* This is used by gcov-dump (IN_GCOV == -1) and in the compiler + (!IN_GCOV && !IN_LIBGCOV). */ +#if IN_GCOV <= 0 && !IN_LIBGCOV +/* Compute the working set information from the counter histogram in + the profile summary. This is an array of information corresponding to a + range of percentages of the total execution count (sum_all), and includes + the number of counters required to cover that working set percentage and + the minimum counter value in that working set. */ + +GCOV_LINKAGE void +compute_working_sets (const struct gcov_ctr_summary *summary, + gcov_working_set_t *gcov_working_sets) +{ + gcov_type working_set_cum_values[NUM_GCOV_WORKING_SETS]; + gcov_type ws_cum_hotness_incr; + gcov_type cum, tmp_cum; + const gcov_bucket_type *histo_bucket; + unsigned ws_ix, c_num, count; + int h_ix; + + /* Compute the amount of sum_all that the cumulative hotness grows + by in each successive working set entry, which depends on the + number of working set entries. */ + ws_cum_hotness_incr = summary->sum_all / NUM_GCOV_WORKING_SETS; + + /* Next fill in an array of the cumulative hotness values corresponding + to each working set summary entry we are going to compute below. + Skip 0% statistics, which can be extrapolated from the + rest of the summary data. */ + cum = ws_cum_hotness_incr; + for (ws_ix = 0; ws_ix < NUM_GCOV_WORKING_SETS; + ws_ix++, cum += ws_cum_hotness_incr) + working_set_cum_values[ws_ix] = cum; + /* The last summary entry is reserved for (roughly) 99.9% of the + working set. Divide by 1024 so it becomes a shift, which gives + almost exactly 99.9%. */ + working_set_cum_values[NUM_GCOV_WORKING_SETS-1] + = summary->sum_all - summary->sum_all/1024; + + /* Next, walk through the histogram in decending order of hotness + and compute the statistics for the working set summary array. + As histogram entries are accumulated, we check to see which + working set entries have had their expected cum_value reached + and fill them in, walking the working set entries in increasing + size of cum_value. */ + ws_ix = 0; /* The current entry into the working set array. */ + cum = 0; /* The current accumulated counter sum. */ + count = 0; /* The current accumulated count of block counters. */ + for (h_ix = GCOV_HISTOGRAM_SIZE - 1; + h_ix >= 0 && ws_ix < NUM_GCOV_WORKING_SETS; h_ix--) + { + histo_bucket = &summary->histogram[h_ix]; + + /* If we haven't reached the required cumulative counter value for + the current working set percentage, simply accumulate this histogram + entry into the running sums and continue to the next histogram + entry. */ + if (cum + histo_bucket->cum_value < working_set_cum_values[ws_ix]) + { + cum += histo_bucket->cum_value; + count += histo_bucket->num_counters; + continue; + } + + /* If adding the current histogram entry's cumulative counter value + causes us to exceed the current working set size, then estimate + how many of this histogram entry's counter values are required to + reach the working set size, and fill in working set entries + as we reach their expected cumulative value. */ + for (c_num = 0, tmp_cum = cum; + c_num < histo_bucket->num_counters && ws_ix < NUM_GCOV_WORKING_SETS; + c_num++) + { + count++; + /* If we haven't reached the last histogram entry counter, add + in the minimum value again. This will underestimate the + cumulative sum so far, because many of the counter values in this + entry may have been larger than the minimum. We could add in the + average value every time, but that would require an expensive + divide operation. */ + if (c_num + 1 < histo_bucket->num_counters) + tmp_cum += histo_bucket->min_value; + /* If we have reached the last histogram entry counter, then add + in the entire cumulative value. */ + else + tmp_cum = cum + histo_bucket->cum_value; + + /* Next walk through successive working set entries and fill in + the statistics for any whose size we have reached by accumulating + this histogram counter. */ + while (ws_ix < NUM_GCOV_WORKING_SETS + && tmp_cum >= working_set_cum_values[ws_ix]) + { + gcov_working_sets[ws_ix].num_counters = count; + gcov_working_sets[ws_ix].min_counter + = histo_bucket->min_value; + ws_ix++; + } + } + /* Finally, update the running cumulative value since we were + using a temporary above. */ + cum += histo_bucket->cum_value; + } + gcc_assert (ws_ix == NUM_GCOV_WORKING_SETS); +} +#endif /* IN_GCOV <= 0 && !IN_LIBGCOV */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/gcov-src/gcov-io.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/gcov-src/gcov-io.h new file mode 100644 index 0000000..50ffa55 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/gcov-src/gcov-io.h @@ -0,0 +1,489 @@ +/* File format for coverage information + Copyright (C) 1996-2014 Free Software Foundation, Inc. + Contributed by Bob Manson <manson@cygnus.com>. + Completely remangled by Nathan Sidwell <nathan@codesourcery.com>. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify it under +the terms of the GNU General Public License as published by the Free +Software Foundation; either version 3, or (at your option) any later +version. + +GCC is distributed in the hope that it will be useful, but WITHOUT ANY +WARRANTY; without even the implied warranty of MERCHANTABILITY or +FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + + +/* Coverage information is held in two files. A notes file, which is + generated by the compiler, and a data file, which is generated by + the program under test. Both files use a similar structure. We do + not attempt to make these files backwards compatible with previous + versions, as you only need coverage information when developing a + program. We do hold version information, so that mismatches can be + detected, and we use a format that allows tools to skip information + they do not understand or are not interested in. + + Numbers are recorded in the 32 bit unsigned binary form of the + endianness of the machine generating the file. 64 bit numbers are + stored as two 32 bit numbers, the low part first. Strings are + padded with 1 to 4 NUL bytes, to bring the length up to a multiple + of 4. The number of 4 bytes is stored, followed by the padded + string. Zero length and NULL strings are simply stored as a length + of zero (they have no trailing NUL or padding). + + int32: byte3 byte2 byte1 byte0 | byte0 byte1 byte2 byte3 + int64: int32:low int32:high + string: int32:0 | int32:length char* char:0 padding + padding: | char:0 | char:0 char:0 | char:0 char:0 char:0 + item: int32 | int64 | string + + The basic format of the files is + + file : int32:magic int32:version int32:stamp record* + + The magic ident is different for the notes and the data files. The + magic ident is used to determine the endianness of the file, when + reading. The version is the same for both files and is derived + from gcc's version number. The stamp value is used to synchronize + note and data files and to synchronize merging within a data + file. It need not be an absolute time stamp, merely a ticker that + increments fast enough and cycles slow enough to distinguish + different compile/run/compile cycles. + + Although the ident and version are formally 32 bit numbers, they + are derived from 4 character ASCII strings. The version number + consists of the single character major version number, a two + character minor version number (leading zero for versions less than + 10), and a single character indicating the status of the release. + That will be 'e' experimental, 'p' prerelease and 'r' for release. + Because, by good fortune, these are in alphabetical order, string + collating can be used to compare version strings. Be aware that + the 'e' designation will (naturally) be unstable and might be + incompatible with itself. For gcc 3.4 experimental, it would be + '304e' (0x33303465). When the major version reaches 10, the + letters A-Z will be used. Assuming minor increments releases every + 6 months, we have to make a major increment every 50 years. + Assuming major increments releases every 5 years, we're ok for the + next 155 years -- good enough for me. + + A record has a tag, length and variable amount of data. + + record: header data + header: int32:tag int32:length + data: item* + + Records are not nested, but there is a record hierarchy. Tag + numbers reflect this hierarchy. Tags are unique across note and + data files. Some record types have a varying amount of data. The + LENGTH is the number of 4bytes that follow and is usually used to + determine how much data. The tag value is split into 4 8-bit + fields, one for each of four possible levels. The most significant + is allocated first. Unused levels are zero. Active levels are + odd-valued, so that the LSB of the level is one. A sub-level + incorporates the values of its superlevels. This formatting allows + you to determine the tag hierarchy, without understanding the tags + themselves, and is similar to the standard section numbering used + in technical documents. Level values [1..3f] are used for common + tags, values [41..9f] for the notes file and [a1..ff] for the data + file. + + The notes file contains the following records + note: unit function-graph* + unit: header int32:checksum string:source + function-graph: announce_function basic_blocks {arcs | lines}* + announce_function: header int32:ident + int32:lineno_checksum int32:cfg_checksum + string:name string:source int32:lineno + basic_block: header int32:flags* + arcs: header int32:block_no arc* + arc: int32:dest_block int32:flags + lines: header int32:block_no line* + int32:0 string:NULL + line: int32:line_no | int32:0 string:filename + + The BASIC_BLOCK record holds per-bb flags. The number of blocks + can be inferred from its data length. There is one ARCS record per + basic block. The number of arcs from a bb is implicit from the + data length. It enumerates the destination bb and per-arc flags. + There is one LINES record per basic block, it enumerates the source + lines which belong to that basic block. Source file names are + introduced by a line number of 0, following lines are from the new + source file. The initial source file for the function is NULL, but + the current source file should be remembered from one LINES record + to the next. The end of a block is indicated by an empty filename + - this does not reset the current source file. Note there is no + ordering of the ARCS and LINES records: they may be in any order, + interleaved in any manner. The current filename follows the order + the LINES records are stored in the file, *not* the ordering of the + blocks they are for. + + The data file contains the following records. + data: {unit summary:object summary:program* function-data*}* + unit: header int32:checksum + function-data: announce_function present counts + announce_function: header int32:ident + int32:lineno_checksum int32:cfg_checksum + present: header int32:present + counts: header int64:count* + summary: int32:checksum {count-summary}GCOV_COUNTERS_SUMMABLE + count-summary: int32:num int32:runs int64:sum + int64:max int64:sum_max histogram + histogram: {int32:bitvector}8 histogram-buckets* + histogram-buckets: int32:num int64:min int64:sum + + The ANNOUNCE_FUNCTION record is the same as that in the note file, + but without the source location. The COUNTS gives the + counter values for instrumented features. The about the whole + program. The checksum is used for whole program summaries, and + disambiguates different programs which include the same + instrumented object file. There may be several program summaries, + each with a unique checksum. The object summary's checksum is + zero. Note that the data file might contain information from + several runs concatenated, or the data might be merged. + + This file is included by both the compiler, gcov tools and the + runtime support library libgcov. IN_LIBGCOV and IN_GCOV are used to + distinguish which case is which. If IN_LIBGCOV is nonzero, + libgcov is being built. If IN_GCOV is nonzero, the gcov tools are + being built. Otherwise the compiler is being built. IN_GCOV may be + positive or negative. If positive, we are compiling a tool that + requires additional functions (see the code for knowledge of what + those functions are). */ + +#ifndef GCC_GCOV_IO_H +#define GCC_GCOV_IO_H + +#ifndef IN_LIBGCOV +/* About the host */ + +typedef unsigned gcov_unsigned_t; +typedef unsigned gcov_position_t; + +#if LONG_LONG_TYPE_SIZE > 32 +#define GCOV_TYPE_ATOMIC_FETCH_ADD_FN __atomic_fetch_add_8 +#define GCOV_TYPE_ATOMIC_FETCH_ADD BUILT_IN_ATOMIC_FETCH_ADD_8 +#else +#define GCOV_TYPE_ATOMIC_FETCH_ADD_FN __atomic_fetch_add_4 +#define GCOV_TYPE_ATOMIC_FETCH_ADD BUILT_IN_ATOMIC_FETCH_ADD_4 +#endif +#define PROFILE_GEN_EDGE_ATOMIC (flag_profile_gen_atomic == 1 || \ + flag_profile_gen_atomic == 3) +#define PROFILE_GEN_VALUE_ATOMIC (flag_profile_gen_atomic == 2 || \ + flag_profile_gen_atomic == 3) + +/* gcov_type is typedef'd elsewhere for the compiler */ +#if IN_GCOV +#define GCOV_LINKAGE static +typedef HOST_WIDEST_INT gcov_type; +typedef unsigned HOST_WIDEST_INT gcov_type_unsigned; +#if IN_GCOV > 0 +#include <sys/types.h> +#endif + +#define FUNC_ID_WIDTH HOST_BITS_PER_WIDE_INT/2 +#define FUNC_ID_MASK ((1L << FUNC_ID_WIDTH) - 1) +#define EXTRACT_MODULE_ID_FROM_GLOBAL_ID(gid) (unsigned)(((gid) >> FUNC_ID_WIDTH) & FUNC_ID_MASK) +#define EXTRACT_FUNC_ID_FROM_GLOBAL_ID(gid) (unsigned)((gid) & FUNC_ID_MASK) +#define FUNC_GLOBAL_ID(m,f) ((((HOST_WIDE_INT) (m)) << FUNC_ID_WIDTH) | (f) + +#else /*!IN_GCOV */ +#define GCOV_TYPE_SIZE (LONG_LONG_TYPE_SIZE > 32 ? 64 : 32) +#endif + +#if defined (HOST_HAS_F_SETLKW) +#define GCOV_LOCKED 1 +#else +#define GCOV_LOCKED 0 +#endif + +#define ATTRIBUTE_HIDDEN + +#endif /* !IN_LIBGOCV */ + +#ifndef GCOV_LINKAGE +#define GCOV_LINKAGE extern +#endif + +/* File suffixes. */ +#define GCOV_DATA_SUFFIX ".gcda" +#define GCOV_NOTE_SUFFIX ".gcno" + +/* File magic. Must not be palindromes. */ +#define GCOV_DATA_MAGIC ((gcov_unsigned_t)0x67636461) /* "gcda" */ +#define GCOV_NOTE_MAGIC ((gcov_unsigned_t)0x67636e6f) /* "gcno" */ + +/* gcov-iov.h is automatically generated by the makefile from + version.c, it looks like + #define GCOV_VERSION ((gcov_unsigned_t)0x89abcdef) +*/ +#include "gcov-iov.h" + +/* Convert a magic or version number to a 4 character string. */ +#define GCOV_UNSIGNED2STRING(ARRAY,VALUE) \ + ((ARRAY)[0] = (char)((VALUE) >> 24), \ + (ARRAY)[1] = (char)((VALUE) >> 16), \ + (ARRAY)[2] = (char)((VALUE) >> 8), \ + (ARRAY)[3] = (char)((VALUE) >> 0)) + +/* The record tags. Values [1..3f] are for tags which may be in either + file. Values [41..9f] for those in the note file and [a1..ff] for + the data file. The tag value zero is used as an explicit end of + file marker -- it is not required to be present. */ + +#define GCOV_TAG_FUNCTION ((gcov_unsigned_t)0x01000000) +#define GCOV_TAG_FUNCTION_LENGTH (3) +#define GCOV_TAG_BLOCKS ((gcov_unsigned_t)0x01410000) +#define GCOV_TAG_BLOCKS_LENGTH(NUM) (NUM) +#define GCOV_TAG_BLOCKS_NUM(LENGTH) (LENGTH) +#define GCOV_TAG_ARCS ((gcov_unsigned_t)0x01430000) +#define GCOV_TAG_ARCS_LENGTH(NUM) (1 + (NUM) * 2) +#define GCOV_TAG_ARCS_NUM(LENGTH) (((LENGTH) - 1) / 2) +#define GCOV_TAG_LINES ((gcov_unsigned_t)0x01450000) +#define GCOV_TAG_COUNTER_BASE ((gcov_unsigned_t)0x01a10000) +#define GCOV_TAG_COUNTER_LENGTH(NUM) ((NUM) * 2) +#define GCOV_TAG_COUNTER_NUM(LENGTH) ((LENGTH) / 2) +#define GCOV_TAG_OBJECT_SUMMARY ((gcov_unsigned_t)0xa1000000) /* Obsolete */ +#define GCOV_TAG_PROGRAM_SUMMARY ((gcov_unsigned_t)0xa3000000) +#define GCOV_TAG_SUMMARY_LENGTH(NUM) \ + (1 + GCOV_COUNTERS_SUMMABLE * (10 + 3 * 2) + (NUM) * 5) +#define GCOV_TAG_MODULE_INFO ((gcov_unsigned_t)0xab000000) +#define GCOV_TAG_AFDO_FILE_NAMES ((gcov_unsigned_t)0xaa000000) +#define GCOV_TAG_AFDO_FUNCTION ((gcov_unsigned_t)0xac000000) +#define GCOV_TAG_AFDO_MODULE_GROUPING ((gcov_unsigned_t)0xae000000) +#define GCOV_TAG_AFDO_WORKING_SET ((gcov_unsigned_t)0xaf000000) + +/* Counters that are collected. */ +#define DEF_GCOV_COUNTER(COUNTER, NAME, MERGE_FN) COUNTER, +enum { +#include "gcov-counter.def" +GCOV_COUNTERS +}; +#undef DEF_GCOV_COUNTER + +/* Counters which can be summaried. */ +#define GCOV_COUNTERS_SUMMABLE (GCOV_COUNTER_ARCS + 1) + +/* The first of counters used for value profiling. They must form a + consecutive interval and their order must match the order of + HIST_TYPEs in value-prof.h. */ +#define GCOV_FIRST_VALUE_COUNTER GCOV_COUNTERS_SUMMABLE + +/* The last of counters used for value profiling. */ +#define GCOV_LAST_VALUE_COUNTER (GCOV_COUNTERS - 2) + +/* Number of counters used for value profiling. */ +#define GCOV_N_VALUE_COUNTERS \ + (GCOV_LAST_VALUE_COUNTER - GCOV_FIRST_VALUE_COUNTER + 1) + +#define GCOV_ICALL_TOPN_VAL 2 /* Track two hottest callees */ +#define GCOV_ICALL_TOPN_NCOUNTS 9 /* The number of counter entries per icall callsite */ + +/* Convert a counter index to a tag. */ +#define GCOV_TAG_FOR_COUNTER(COUNT) \ + (GCOV_TAG_COUNTER_BASE + ((gcov_unsigned_t)(COUNT) << 17)) +/* Convert a tag to a counter. */ +#define GCOV_COUNTER_FOR_TAG(TAG) \ + ((unsigned)(((TAG) - GCOV_TAG_COUNTER_BASE) >> 17)) +/* Check whether a tag is a counter tag. */ +#define GCOV_TAG_IS_COUNTER(TAG) \ + (!((TAG) & 0xFFFF) && GCOV_COUNTER_FOR_TAG (TAG) < GCOV_COUNTERS) + +/* The tag level mask has 1's in the position of the inner levels, & + the lsb of the current level, and zero on the current and outer + levels. */ +#define GCOV_TAG_MASK(TAG) (((TAG) - 1) ^ (TAG)) + +/* Return nonzero if SUB is an immediate subtag of TAG. */ +#define GCOV_TAG_IS_SUBTAG(TAG,SUB) \ + (GCOV_TAG_MASK (TAG) >> 8 == GCOV_TAG_MASK (SUB) \ + && !(((SUB) ^ (TAG)) & ~GCOV_TAG_MASK (TAG))) + +/* Return nonzero if SUB is at a sublevel to TAG. */ +#define GCOV_TAG_IS_SUBLEVEL(TAG,SUB) \ + (GCOV_TAG_MASK (TAG) > GCOV_TAG_MASK (SUB)) + +/* Basic block flags. */ +#define GCOV_BLOCK_UNEXPECTED (1 << 1) + +/* Arc flags. */ +#define GCOV_ARC_ON_TREE (1 << 0) +#define GCOV_ARC_FAKE (1 << 1) +#define GCOV_ARC_FALLTHROUGH (1 << 2) + +/* Structured records. */ + +/* Structure used for each bucket of the log2 histogram of counter values. */ +typedef struct +{ + /* Number of counters whose profile count falls within the bucket. */ + gcov_unsigned_t num_counters; + /* Smallest profile count included in this bucket. */ + gcov_type min_value; + /* Cumulative value of the profile counts in this bucket. */ + gcov_type cum_value; +} gcov_bucket_type; + +/* For a log2 scale histogram with each range split into 4 + linear sub-ranges, there will be at most 64 (max gcov_type bit size) - 1 log2 + ranges since the lowest 2 log2 values share the lowest 4 linear + sub-range (values 0 - 3). This is 252 total entries (63*4). */ + +#define GCOV_HISTOGRAM_SIZE 252 + +/* How many unsigned ints are required to hold a bit vector of non-zero + histogram entries when the histogram is written to the gcov file. + This is essentially a ceiling divide by 32 bits. */ +#define GCOV_HISTOGRAM_BITVECTOR_SIZE (GCOV_HISTOGRAM_SIZE + 31) / 32 + +/* Cumulative counter data. */ +struct gcov_ctr_summary +{ + gcov_unsigned_t num; /* number of counters. */ + gcov_unsigned_t runs; /* number of program runs */ + gcov_type sum_all; /* sum of all counters accumulated. */ + gcov_type run_max; /* maximum value on a single run. */ + gcov_type sum_max; /* sum of individual run max values. */ + gcov_bucket_type histogram[GCOV_HISTOGRAM_SIZE]; /* histogram of + counter values. */ +}; + +/* Object & program summary record. */ +struct gcov_summary +{ + gcov_unsigned_t checksum; /* checksum of program */ + struct gcov_ctr_summary ctrs[GCOV_COUNTERS_SUMMABLE]; +}; + +#define GCOV_MODULE_UNKNOWN_LANG 0 +#define GCOV_MODULE_C_LANG 1 +#define GCOV_MODULE_CPP_LANG 2 +#define GCOV_MODULE_FORT_LANG 3 + +#define GCOV_MODULE_ASM_STMTS (1 << 16) +#define GCOV_MODULE_LANG_MASK 0xffff + +/* Source module info. The data structure is used in + both runtime and profile-use phase. Make sure to allocate + enough space for the variable length member. */ +struct gcov_module_info +{ + gcov_unsigned_t ident; + gcov_unsigned_t is_primary; /* this is overloaded to mean two things: + (1) means FDO/LIPO in instrumented binary. + (2) means IS_PRIMARY in persistent file or + memory copy used in profile-use. */ + gcov_unsigned_t flags; /* bit 0: is_exported, + bit 1: need to include all the auxiliary + modules in use compilation. */ + gcov_unsigned_t lang; /* lower 16 bits encode the language, and the upper + 16 bits enocde other attributes, such as whether + any assembler is present in the source, etc. */ + gcov_unsigned_t ggc_memory; /* memory needed for parsing in kb */ + char *da_filename; + char *source_filename; + gcov_unsigned_t num_quote_paths; + gcov_unsigned_t num_bracket_paths; + gcov_unsigned_t num_system_paths; + gcov_unsigned_t num_cpp_defines; + gcov_unsigned_t num_cpp_includes; + gcov_unsigned_t num_cl_args; + char *string_array[1]; +}; + +extern struct gcov_module_info **module_infos; +extern unsigned primary_module_id; +#define SET_MODULE_INCLUDE_ALL_AUX(modu) ((modu->flags |= 0x2)) +#define MODULE_INCLUDE_ALL_AUX_FLAG(modu) ((modu->flags & 0x2)) +#define SET_MODULE_EXPORTED(modu) ((modu->flags |= 0x1)) +#define MODULE_EXPORTED_FLAG(modu) ((modu->flags & 0x1)) +#define PRIMARY_MODULE_EXPORTED \ + (MODULE_EXPORTED_FLAG (module_infos[0]) \ + && !((module_infos[0]->lang & GCOV_MODULE_ASM_STMTS) \ + && flag_ripa_disallow_asm_modules)) + +#if !defined(inhibit_libc) + +/* Functions for reading and writing gcov files. In libgcov you can + open the file for reading then writing. Elsewhere you can open the + file either for reading or for writing. When reading a file you may + use the gcov_read_* functions, gcov_sync, gcov_position, & + gcov_error. When writing a file you may use the gcov_write + functions, gcov_seek & gcov_error. When a file is to be rewritten + you use the functions for reading, then gcov_rewrite then the + functions for writing. Your file may become corrupted if you break + these invariants. */ + +#if !IN_LIBGCOV +GCOV_LINKAGE int gcov_open (const char */*name*/, int /*direction*/); +GCOV_LINKAGE int gcov_magic (gcov_unsigned_t, gcov_unsigned_t); +#endif + +/* Available everywhere. */ +GCOV_LINKAGE int gcov_close (void) ATTRIBUTE_HIDDEN; +GCOV_LINKAGE gcov_unsigned_t gcov_read_unsigned (void) ATTRIBUTE_HIDDEN; +GCOV_LINKAGE gcov_type gcov_read_counter (void) ATTRIBUTE_HIDDEN; +GCOV_LINKAGE void gcov_read_summary (struct gcov_summary *) ATTRIBUTE_HIDDEN; +GCOV_LINKAGE const char *gcov_read_string (void); +GCOV_LINKAGE void gcov_sync (gcov_position_t /*base*/, + gcov_unsigned_t /*length */); + + +#if !IN_LIBGCOV && IN_GCOV != 1 +GCOV_LINKAGE void gcov_read_module_info (struct gcov_module_info *mod_info, + gcov_unsigned_t len) ATTRIBUTE_HIDDEN; +#endif + +#if !IN_GCOV +/* Available outside gcov */ +GCOV_LINKAGE void gcov_write_unsigned (gcov_unsigned_t) ATTRIBUTE_HIDDEN; +#endif + +#if !IN_GCOV && !IN_LIBGCOV +/* Available only in compiler */ +GCOV_LINKAGE unsigned gcov_histo_index (gcov_type value); +GCOV_LINKAGE void gcov_write_string (const char *); +GCOV_LINKAGE gcov_position_t gcov_write_tag (gcov_unsigned_t); +GCOV_LINKAGE void gcov_write_length (gcov_position_t /*position*/); +#endif + +#if IN_GCOV <= 0 && !IN_LIBGCOV +/* Available in gcov-dump and the compiler. */ + +/* Number of data points in the working set summary array. Using 128 + provides information for at least every 1% increment of the total + profile size. The last entry is hardwired to 99.9% of the total. */ +#define NUM_GCOV_WORKING_SETS 128 + +/* Working set size statistics for a given percentage of the entire + profile (sum_all from the counter summary). */ +typedef struct gcov_working_set_info +{ + /* Number of hot counters included in this working set. */ + unsigned num_counters; + /* Smallest counter included in this working set. */ + gcov_type min_counter; +} gcov_working_set_t; + +GCOV_LINKAGE void compute_working_sets (const struct gcov_ctr_summary *summary, + gcov_working_set_t *gcov_working_sets); +#endif + +#if IN_GCOV > 0 +/* Available in gcov */ +GCOV_LINKAGE time_t gcov_time (void); +#endif + +#endif /* !inhibit_libc */ + +#endif /* GCC_GCOV_IO_H */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/gcov-src/gcov-iov.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/gcov-src/gcov-iov.h new file mode 100644 index 0000000..ec6b717 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/gcov-src/gcov-iov.h @@ -0,0 +1,4 @@ +/* Generated automatically by the program `build/gcov-iov' + from `4.9.x-google (4 9) and prerelease (*)'. */ + +#define GCOV_VERSION ((gcov_unsigned_t)0x3430392a) /* 409* */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/gcov-src/libgcov-driver.c b/lib/gcc/arm-linux-androideabi/4.9.x-google/gcov-src/libgcov-driver.c new file mode 100644 index 0000000..dc8cf36 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/gcov-src/libgcov-driver.c @@ -0,0 +1,1193 @@ +/* Routines required for instrumenting a program. */ +/* Compile this one with gcc. */ +/* Copyright (C) 1989-2014 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify it under +the terms of the GNU General Public License as published by the Free +Software Foundation; either version 3, or (at your option) any later +version. + +GCC is distributed in the hope that it will be useful, but WITHOUT ANY +WARRANTY; without even the implied warranty of MERCHANTABILITY or +FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + +#include "libgcov.h" + +#if defined(inhibit_libc) +/* If libc and its header files are not available, provide dummy functions. */ + +#if defined(L_gcov) +void __gcov_init (struct gcov_info *p __attribute__ ((unused))) {} +#endif + +#else /* inhibit_libc */ + +#include <string.h> +#if GCOV_LOCKED +#include <fcntl.h> +#include <errno.h> +#include <sys/stat.h> +#endif + +#ifdef L_gcov +#include "gcov-io.c" + +#ifndef IN_GCOV_TOOL +extern gcov_unsigned_t __gcov_sampling_period; +extern gcov_unsigned_t __gcov_has_sampling; +static int gcov_sampling_period_initialized = 0; +#endif + +/* Unique identifier assigned to each module (object file). */ +static gcov_unsigned_t gcov_cur_module_id = 0; + + +/* Dynamic call graph build and form module groups. */ +int __gcov_compute_module_groups (void) ATTRIBUTE_HIDDEN; +void __gcov_finalize_dyn_callgraph (void) ATTRIBUTE_HIDDEN; + +/* The following functions can be called from outside of this file. */ +extern void gcov_clear (void) ATTRIBUTE_HIDDEN; +extern void gcov_exit (void) ATTRIBUTE_HIDDEN; +extern void set_gcov_dump_complete (void) ATTRIBUTE_HIDDEN; +extern void reset_gcov_dump_complete (void) ATTRIBUTE_HIDDEN; +extern int get_gcov_dump_complete (void) ATTRIBUTE_HIDDEN; +extern void set_gcov_list (struct gcov_info *) ATTRIBUTE_HIDDEN; +__attribute__((weak)) void __coverage_callback (gcov_type, int); + +#ifndef IN_GCOV_TOOL +/* Create a strong reference to these symbols so that they are + unconditionally pulled into the instrumented binary, even when + the only reference is a weak reference. This is necessary because + we are using weak references to enable references from code that + may not be linked with libgcov. These are the only symbols that + should be accessed via link references from application code! + + A subtlety of the linker is that it will only resolve weak references + defined within archive libraries when there is a strong reference to + something else defined within the same object file. Since these functions + are defined within their own object files, they would not automatically + get resolved. Since there are symbols within the main L_gcov + section that are strongly referenced during -fprofile-generate and + -ftest-coverage builds, these dummy symbols will always need to be + resolved. */ +void (*__gcov_dummy_ref1)(void) = &__gcov_reset; +void (*__gcov_dummy_ref2)(void) = &__gcov_dump; +extern char *__gcov_get_profile_prefix (void); +char *(*__gcov_dummy_ref3)(void) = &__gcov_get_profile_prefix; +extern void __gcov_set_sampling_period (unsigned int period); +char *(*__gcov_dummy_ref4)(void) = &__gcov_set_sampling_period; +extern unsigned int __gcov_sampling_enabled (void); +char *(*__gcov_dummy_ref5)(void) = &__gcov_sampling_enabled; +extern void __gcov_flush (void); +char *(*__gcov_dummy_ref6)(void) = &__gcov_flush; +extern unsigned int __gcov_profiling_for_test_coverage (void); +char *(*__gcov_dummy_ref7)(void) = &__gcov_profiling_for_test_coverage; +#endif + +/* Default callback function for profile instrumentation callback. */ +__attribute__((weak)) void +__coverage_callback (gcov_type funcdef_no __attribute__ ((unused)), + int edge_no __attribute__ ((unused))) +{ + /* nothing */ +} + +struct gcov_fn_buffer +{ + struct gcov_fn_buffer *next; + unsigned fn_ix; + struct gcov_fn_info info; + /* note gcov_fn_info ends in a trailing array. */ +}; + +struct gcov_summary_buffer +{ + struct gcov_summary_buffer *next; + struct gcov_summary summary; +}; + +/* Chain of per-object gcov structures. */ +extern struct gcov_info *__gcov_list; + +/* Set the head of gcov_list. */ +void +set_gcov_list (struct gcov_info *head) +{ + __gcov_list = head; +} + +/* Size of the longest file name. */ +/* We need to expose this static variable when compiling for gcov-tool. */ +#ifndef IN_GCOV_TOOL +static +#endif +size_t gcov_max_filename = 0; + +/* Flag when the profile has already been dumped via __gcov_dump(). */ +static int gcov_dump_complete; + +/* A global function that get the vaule of gcov_dump_complete. */ + +int +get_gcov_dump_complete (void) +{ + return gcov_dump_complete; +} + +/* A global functino that set the vaule of gcov_dump_complete. Will + be used in __gcov_dump() in libgcov-interface.c. */ + +void +set_gcov_dump_complete (void) +{ + gcov_dump_complete = 1; +} + +/* A global functino that set the vaule of gcov_dump_complete. Will + be used in __gcov_reset() in libgcov-interface.c. */ + +void +reset_gcov_dump_complete (void) +{ + gcov_dump_complete = 0; +} + +/* A utility function for outputing errors. */ +static int gcov_error (const char *, ...); + +static struct gcov_fn_buffer * +free_fn_data (const struct gcov_info *gi_ptr, struct gcov_fn_buffer *buffer, + unsigned limit) +{ + struct gcov_fn_buffer *next; + unsigned ix, n_ctr = 0; + + if (!buffer) + return 0; + next = buffer->next; + + for (ix = 0; ix != limit; ix++) + if (gi_ptr->merge[ix]) + free (buffer->info.ctrs[n_ctr++].values); + free (buffer); + return next; +} + +static struct gcov_fn_buffer ** +buffer_fn_data (const char *filename, const struct gcov_info *gi_ptr, + struct gcov_fn_buffer **end_ptr, unsigned fn_ix) +{ + unsigned n_ctrs = 0, ix = 0; + struct gcov_fn_buffer *fn_buffer; + unsigned len; + + for (ix = GCOV_COUNTERS; ix--;) + if (gi_ptr->merge[ix]) + n_ctrs++; + + len = sizeof (*fn_buffer) + sizeof (fn_buffer->info.ctrs[0]) * n_ctrs; + fn_buffer = (struct gcov_fn_buffer *) xmalloc (len); + + if (!fn_buffer) + goto fail; + + fn_buffer->next = 0; + fn_buffer->fn_ix = fn_ix; + fn_buffer->info.ident = gcov_read_unsigned (); + fn_buffer->info.lineno_checksum = gcov_read_unsigned (); + fn_buffer->info.cfg_checksum = gcov_read_unsigned (); + + for (n_ctrs = ix = 0; ix != GCOV_COUNTERS; ix++) + { + gcov_unsigned_t length; + gcov_type *values; + + if (!gi_ptr->merge[ix]) + continue; + + if (gcov_read_unsigned () != GCOV_TAG_FOR_COUNTER (ix)) + { + len = 0; + goto fail; + } + + length = GCOV_TAG_COUNTER_NUM (gcov_read_unsigned ()); + len = length * sizeof (gcov_type); + values = (gcov_type *) xmalloc (len); + if (!values) + goto fail; + + fn_buffer->info.ctrs[n_ctrs].num = length; + fn_buffer->info.ctrs[n_ctrs].values = values; + + while (length--) + *values++ = gcov_read_counter (); + n_ctrs++; + } + + *end_ptr = fn_buffer; + return &fn_buffer->next; + +fail: + gcov_error ("profiling:%s:Function %u %s %u \n", filename, fn_ix, + len ? "cannot allocate" : "counter mismatch", len ? len : ix); + + return (struct gcov_fn_buffer **)free_fn_data (gi_ptr, fn_buffer, ix); +} + +/* Determine whether a counter is active. */ + +static inline int +gcov_counter_active (const struct gcov_info *info, unsigned int type) +{ + return (info->merge[type] != 0); +} + +/* Add an unsigned value to the current crc */ + +static gcov_unsigned_t +crc32_unsigned (gcov_unsigned_t crc32, gcov_unsigned_t value) +{ + unsigned ix; + + for (ix = 32; ix--; value <<= 1) + { + unsigned feedback; + + feedback = (value ^ crc32) & 0x80000000 ? 0x04c11db7 : 0; + crc32 <<= 1; + crc32 ^= feedback; + } + + return crc32; +} + +/* Check if VERSION of the info block PTR matches libgcov one. + Return 1 on success, or zero in case of versions mismatch. + If FILENAME is not NULL, its value used for reporting purposes + instead of value from the info block. */ + +static int +gcov_version (struct gcov_info *ptr, gcov_unsigned_t version, + const char *filename) +{ + if (version != GCOV_VERSION) + { + char v[4], e[4]; + + GCOV_UNSIGNED2STRING (v, version); + GCOV_UNSIGNED2STRING (e, GCOV_VERSION); + + if (filename) + gcov_error ("profiling:%s:Version mismatch - expected %.4s got %.4s\n", + filename? filename : ptr->filename, e, v); + else + gcov_error ("profiling:Version mismatch - expected %.4s got %.4s\n", e, v); + + return 0; + } + return 1; +} + +/* Insert counter VALUE into HISTOGRAM. */ + +static void +gcov_histogram_insert(gcov_bucket_type *histogram, gcov_type value) +{ + unsigned i; + + i = gcov_histo_index(value); + histogram[i].num_counters++; + histogram[i].cum_value += value; + if (value < histogram[i].min_value) + histogram[i].min_value = value; +} + +/* Computes a histogram of the arc counters to place in the summary SUM. */ + +static void +gcov_compute_histogram (struct gcov_summary *sum) +{ + struct gcov_info *gi_ptr; + const struct gcov_fn_info *gfi_ptr; + const struct gcov_ctr_info *ci_ptr; + struct gcov_ctr_summary *cs_ptr; + unsigned t_ix, f_ix, ctr_info_ix, ix; + int h_ix; + + /* This currently only applies to arc counters. */ + t_ix = GCOV_COUNTER_ARCS; + + /* First check if there are any counts recorded for this counter. */ + cs_ptr = &(sum->ctrs[t_ix]); + if (!cs_ptr->num) + return; + + for (h_ix = 0; h_ix < GCOV_HISTOGRAM_SIZE; h_ix++) + { + cs_ptr->histogram[h_ix].num_counters = 0; + cs_ptr->histogram[h_ix].min_value = cs_ptr->run_max; + cs_ptr->histogram[h_ix].cum_value = 0; + } + + /* Walk through all the per-object structures and record each of + the count values in histogram. */ + for (gi_ptr = __gcov_list; gi_ptr; gi_ptr = gi_ptr->next) + { + if (!gi_ptr->merge[t_ix]) + continue; + + /* Find the appropriate index into the gcov_ctr_info array + for the counter we are currently working on based on the + existence of the merge function pointer for this object. */ + for (ix = 0, ctr_info_ix = 0; ix < t_ix; ix++) + { + if (gi_ptr->merge[ix]) + ctr_info_ix++; + } + for (f_ix = 0; f_ix != gi_ptr->n_functions; f_ix++) + { + gfi_ptr = gi_ptr->functions[f_ix]; + + if (!gfi_ptr || gfi_ptr->key != gi_ptr) + continue; + + ci_ptr = &gfi_ptr->ctrs[ctr_info_ix]; + for (ix = 0; ix < ci_ptr->num; ix++) + gcov_histogram_insert (cs_ptr->histogram, ci_ptr->values[ix]); + } + } +} + +/* gcda filename. */ +static char *gi_filename; +/* buffer for the fn_data from another program. */ +static struct gcov_fn_buffer *fn_buffer; +/* buffer for summary from other programs to be written out. */ +static struct gcov_summary_buffer *sum_buffer; +/* If application calls fork or exec multiple times, we end up storing + profile repeadely. We should not account this as multiple runs or + functions executed once may mistakely become cold. */ +static int run_accounted = 0; + +/* This funtions computes the program level summary and the histo-gram. + It computes and returns CRC32 and stored summary in THIS_PRG. */ + +static gcov_unsigned_t +gcov_exit_compute_summary (struct gcov_summary *this_prg) +{ + struct gcov_info *gi_ptr; + const struct gcov_fn_info *gfi_ptr; + struct gcov_ctr_summary *cs_ptr; + const struct gcov_ctr_info *ci_ptr; + int f_ix; + unsigned t_ix; + gcov_unsigned_t c_num; + gcov_unsigned_t crc32 = 0; + + /* Find the totals for this execution. */ + memset (this_prg, 0, sizeof (*this_prg)); + for (gi_ptr = __gcov_list; gi_ptr; gi_ptr = gi_ptr->next) + { + crc32 = crc32_unsigned (crc32, gi_ptr->stamp); + crc32 = crc32_unsigned (crc32, gi_ptr->n_functions); + + for (f_ix = 0; (unsigned)f_ix != gi_ptr->n_functions; f_ix++) + { + gfi_ptr = gi_ptr->functions[f_ix]; + + if (gfi_ptr && gfi_ptr->key != gi_ptr) + gfi_ptr = 0; + + crc32 = crc32_unsigned (crc32, gfi_ptr ? gfi_ptr->cfg_checksum : 0); + crc32 = crc32_unsigned (crc32, + gfi_ptr ? gfi_ptr->lineno_checksum : 0); + if (!gfi_ptr) + continue; + + ci_ptr = gfi_ptr->ctrs; + for (t_ix = 0; t_ix != GCOV_COUNTERS_SUMMABLE; t_ix++) + { + if (!gi_ptr->merge[t_ix]) + continue; + + cs_ptr = &(this_prg->ctrs[t_ix]); + cs_ptr->num += ci_ptr->num; + crc32 = crc32_unsigned (crc32, ci_ptr->num); + + for (c_num = 0; c_num < ci_ptr->num; c_num++) + { + cs_ptr->sum_all += ci_ptr->values[c_num]; + if (cs_ptr->run_max < ci_ptr->values[c_num]) + cs_ptr->run_max = ci_ptr->values[c_num]; + } + ci_ptr++; + } + } + } + gcov_compute_histogram (this_prg); + return crc32; +} + +/* A struct that bundles all the related information about the + gcda filename. */ +struct gcov_filename_aux{ + char *gi_filename_up; + int gcov_prefix_strip; + size_t prefix_length; +}; + +/* Including system dependent components. */ +#include "libgcov-driver-system.c" + +/* Scan through the current open gcda file corresponding to GI_PTR + to locate the end position of the last summary, returned in + SUMMARY_END_POS_P. Return 0 on success, -1 on error. */ +static int +gcov_scan_summary_end (struct gcov_info *gi_ptr, + gcov_position_t *summary_end_pos_p) +{ + gcov_unsigned_t tag, version, stamp; + tag = gcov_read_unsigned (); + if (tag != GCOV_DATA_MAGIC) + { + gcov_error ("profiling:%s:Not a gcov data file\n", gi_filename); + return -1; + } + + version = gcov_read_unsigned (); + if (!gcov_version (gi_ptr, version, gi_filename)) + return -1; + + stamp = gcov_read_unsigned (); + if (stamp != gi_ptr->stamp) + /* Read from a different compilation. Overwrite the file. */ + return -1; + + /* Look for program summary. */ + while (1) + { + struct gcov_summary tmp; + + *summary_end_pos_p = gcov_position (); + tag = gcov_read_unsigned (); + if (tag != GCOV_TAG_PROGRAM_SUMMARY) + break; + + gcov_read_unsigned (); + gcov_read_summary (&tmp); + if (gcov_is_error ()) + return -1; + } + + return 0; +} + +/* This function merges counters in GI_PTR to an existing gcda file. + Return 0 on success. + Return -1 on error. In this case, caller will goto read_fatal. */ + +static int +gcov_exit_merge_gcda (struct gcov_info *gi_ptr, + struct gcov_summary *prg_p, + struct gcov_summary *this_prg, + gcov_position_t *summary_pos_p, + gcov_position_t *eof_pos_p, + gcov_unsigned_t crc32) +{ + gcov_unsigned_t tag, length; + unsigned t_ix; + int f_ix; + int error = 0; + struct gcov_fn_buffer **fn_tail = &fn_buffer; + struct gcov_summary_buffer **sum_tail = &sum_buffer; + + length = gcov_read_unsigned (); + if (!gcov_version (gi_ptr, length, gi_filename)) + return -1; + + length = gcov_read_unsigned (); + if (length != gi_ptr->stamp) + /* Read from a different compilation. Overwrite the file. */ + return 0; + + /* Look for program summary. */ + for (f_ix = 0;;) + { + struct gcov_summary tmp; + + *eof_pos_p = gcov_position (); + tag = gcov_read_unsigned (); + if (tag != GCOV_TAG_PROGRAM_SUMMARY) + break; + + f_ix--; + length = gcov_read_unsigned (); + gcov_read_summary (&tmp); + if ((error = gcov_is_error ())) + goto read_error; + if (*summary_pos_p) + { + /* Save all summaries after the one that will be + merged into below. These will need to be rewritten + as histogram merging may change the number of non-zero + histogram entries that will be emitted, and thus the + size of the merged summary. */ + (*sum_tail) = (struct gcov_summary_buffer *) + xmalloc (sizeof(struct gcov_summary_buffer)); + (*sum_tail)->summary = tmp; + (*sum_tail)->next = 0; + sum_tail = &((*sum_tail)->next); + goto next_summary; + } + if (tmp.checksum != crc32) + goto next_summary; + + for (t_ix = 0; t_ix != GCOV_COUNTERS_SUMMABLE; t_ix++) + if (tmp.ctrs[t_ix].num != this_prg->ctrs[t_ix].num) + goto next_summary; + *prg_p = tmp; + *summary_pos_p = *eof_pos_p; + + next_summary:; + } + + /* Merge execution counts for each function. */ + for (f_ix = 0; (unsigned)f_ix != gi_ptr->n_functions; + f_ix++, tag = gcov_read_unsigned ()) + { + const struct gcov_ctr_info *ci_ptr; + const struct gcov_fn_info *gfi_ptr = gi_ptr->functions[f_ix]; + + if (tag != GCOV_TAG_FUNCTION) + goto read_mismatch; + + length = gcov_read_unsigned (); + if (!length) + /* This function did not appear in the other program. + We have nothing to merge. */ + continue; + + if (length != GCOV_TAG_FUNCTION_LENGTH) + goto read_mismatch; + + if (!gfi_ptr || gfi_ptr->key != gi_ptr) + { + /* This function appears in the other program. We + need to buffer the information in order to write + it back out -- we'll be inserting data before + this point, so cannot simply keep the data in the + file. */ + fn_tail = buffer_fn_data (gi_filename, + gi_ptr, fn_tail, f_ix); + if (!fn_tail) + goto read_mismatch; + continue; + } + + length = gcov_read_unsigned (); + if (length != gfi_ptr->ident) + goto read_mismatch; + + length = gcov_read_unsigned (); + if (length != gfi_ptr->lineno_checksum) + goto read_mismatch; + + length = gcov_read_unsigned (); + if (length != gfi_ptr->cfg_checksum) + goto read_mismatch; + + ci_ptr = gfi_ptr->ctrs; + for (t_ix = 0; t_ix < GCOV_COUNTERS; t_ix++) + { + gcov_merge_fn merge = gi_ptr->merge[t_ix]; + + if (!merge) + continue; + + tag = gcov_read_unsigned (); + length = gcov_read_unsigned (); + if (tag != GCOV_TAG_FOR_COUNTER (t_ix) + || length != GCOV_TAG_COUNTER_LENGTH (ci_ptr->num)) + goto read_mismatch; + (*merge) (ci_ptr->values, ci_ptr->num); + ci_ptr++; + } + if ((error = gcov_is_error ())) + goto read_error; + } + + if (tag && tag != GCOV_TAG_MODULE_INFO) + { + read_mismatch:; + gcov_error ("profiling:%s:Merge mismatch for %s %u\n", + gi_filename, f_ix >= 0 ? "function" : "summary", + f_ix < 0 ? -1 - f_ix : f_ix); + return -1; + } + return 0; + +read_error: + gcov_error ("profiling:%s:%s merging\n", gi_filename, + error < 0 ? "Overflow": "Error"); + return -1; +} + +/* Write counters in GI_PTR to a gcda file starting from its current + location. */ + +static void +gcov_write_func_counters (struct gcov_info *gi_ptr) +{ + unsigned f_ix; + + /* Write execution counts for each function. */ + for (f_ix = 0; f_ix != gi_ptr->n_functions; f_ix++) + { + unsigned buffered = 0; + const struct gcov_fn_info *gfi_ptr; + const struct gcov_ctr_info *ci_ptr; + gcov_unsigned_t length; + unsigned t_ix; + + if (fn_buffer && fn_buffer->fn_ix == f_ix) + { + /* Buffered data from another program. */ + buffered = 1; + gfi_ptr = &fn_buffer->info; + length = GCOV_TAG_FUNCTION_LENGTH; + } + else + { + gfi_ptr = gi_ptr->functions[f_ix]; + if (gfi_ptr && gfi_ptr->key == gi_ptr) + length = GCOV_TAG_FUNCTION_LENGTH; + else + length = 0; + } + + gcov_write_tag_length (GCOV_TAG_FUNCTION, length); + if (!length) + continue; + + gcov_write_unsigned (gfi_ptr->ident); + gcov_write_unsigned (gfi_ptr->lineno_checksum); + gcov_write_unsigned (gfi_ptr->cfg_checksum); + + ci_ptr = gfi_ptr->ctrs; + for (t_ix = 0; t_ix < GCOV_COUNTERS; t_ix++) + { + gcov_unsigned_t n_counts; + gcov_type *c_ptr; + + if (!gi_ptr->merge[t_ix]) + continue; + + n_counts = ci_ptr->num; + gcov_write_tag_length (GCOV_TAG_FOR_COUNTER (t_ix), + GCOV_TAG_COUNTER_LENGTH (n_counts)); + c_ptr = ci_ptr->values; + while (n_counts--) + gcov_write_counter (*c_ptr++); + ci_ptr++; + } + if (buffered) + fn_buffer = free_fn_data (gi_ptr, fn_buffer, GCOV_COUNTERS); + } + + gi_ptr->eof_pos = gcov_position (); + gcov_write_unsigned (0); +} + +/* Write counters in GI_PTR and the summary in PRG to a gcda file. In + the case of appending to an existing file, SUMMARY_POS will be non-zero. + We will write the file starting from SUMMAY_POS. */ + +static void +gcov_exit_write_gcda (struct gcov_info *gi_ptr, + const struct gcov_summary *prg_p, + const gcov_position_t eof_pos, + const gcov_position_t summary_pos) + +{ + struct gcov_summary_buffer *next_sum_buffer; + + /* Write out the data. */ + if (!eof_pos) + { + gcov_write_tag_length (GCOV_DATA_MAGIC, GCOV_VERSION); + gcov_write_unsigned (gi_ptr->stamp); + } + + if (summary_pos) + gcov_seek (summary_pos); + gcc_assert (!summary_pos || summary_pos == gcov_position ()); + + /* Generate whole program statistics. */ + gcov_write_summary (GCOV_TAG_PROGRAM_SUMMARY, prg_p); + + /* Rewrite all the summaries that were after the summary we merged + into. This is necessary as the merged summary may have a different + size due to the number of non-zero histogram entries changing after + merging. */ + + while (sum_buffer) + { + gcov_write_summary (GCOV_TAG_PROGRAM_SUMMARY, &sum_buffer->summary); + next_sum_buffer = sum_buffer->next; + free (sum_buffer); + sum_buffer = next_sum_buffer; + } + + /* Write the counters. */ + gcov_write_func_counters (gi_ptr); +} + +/* Helper function for merging summary. + Return -1 on error. Return 0 on success. */ + +static int +gcov_exit_merge_summary (const struct gcov_info *gi_ptr, struct gcov_summary *prg, + struct gcov_summary *this_prg, gcov_unsigned_t crc32, + struct gcov_summary *all_prg __attribute__ ((unused))) +{ + struct gcov_ctr_summary *cs_prg, *cs_tprg; + unsigned t_ix; +#if !GCOV_LOCKED + /* summary for all instances of program. */ + struct gcov_ctr_summary *cs_all; +#endif + + /* Merge the summaries. */ + for (t_ix = 0; t_ix < GCOV_COUNTERS_SUMMABLE; t_ix++) + { + cs_prg = &(prg->ctrs[t_ix]); + cs_tprg = &(this_prg->ctrs[t_ix]); + + if (gi_ptr->merge[t_ix]) + { + int first = !cs_prg->runs; + + if (!run_accounted) + cs_prg->runs++; + if (first) + cs_prg->num = cs_tprg->num; + cs_prg->sum_all += cs_tprg->sum_all; + if (cs_prg->run_max < cs_tprg->run_max) + cs_prg->run_max = cs_tprg->run_max; + cs_prg->sum_max += cs_tprg->run_max; + if (first) + memcpy (cs_prg->histogram, cs_tprg->histogram, + sizeof (gcov_bucket_type) * GCOV_HISTOGRAM_SIZE); + else + gcov_histogram_merge (cs_prg->histogram, cs_tprg->histogram); + } + else if (cs_prg->runs) + { + gcov_error ("profiling:%s:Merge mismatch for summary.\n", + gi_filename); + return -1; + } +#if !GCOV_LOCKED + cs_all = &all_prg->ctrs[t_ix]; + if (!cs_all->runs && cs_prg->runs) + { + cs_all->num = cs_prg->num; + cs_all->runs = cs_prg->runs; + cs_all->sum_all = cs_prg->sum_all; + cs_all->run_max = cs_prg->run_max; + cs_all->sum_max = cs_prg->sum_max; + } + else if (!all_prg->checksum + /* Don't compare the histograms, which may have slight + variations depending on the order they were updated + due to the truncating integer divides used in the + merge. */ + && (cs_all->num != cs_prg->num + || cs_all->runs != cs_prg->runs + || cs_all->sum_all != cs_prg->sum_all + || cs_all->run_max != cs_prg->run_max + || cs_all->sum_max != cs_prg->sum_max)) + { + gcov_error ("profiling:%s:Data file mismatch - some " + "data files may have been concurrently " + "updated without locking support\n", gi_filename); + all_prg->checksum = ~0u; + } +#endif + } + + prg->checksum = crc32; + + return 0; +} + +/* Sort N entries in VALUE_ARRAY in descending order. + Each entry in VALUE_ARRAY has two values. The sorting + is based on the second value. */ + +GCOV_LINKAGE void +gcov_sort_n_vals (gcov_type *value_array, int n) +{ + int j, k; + for (j = 2; j < n; j += 2) + { + gcov_type cur_ent[2]; + cur_ent[0] = value_array[j]; + cur_ent[1] = value_array[j + 1]; + k = j - 2; + while (k >= 0 && value_array[k + 1] < cur_ent[1]) + { + value_array[k + 2] = value_array[k]; + value_array[k + 3] = value_array[k+1]; + k -= 2; + } + value_array[k + 2] = cur_ent[0]; + value_array[k + 3] = cur_ent[1]; + } +} + +/* Sort the profile counters for all indirect call sites. Counters + for each call site are allocated in array COUNTERS. */ + +static void +gcov_sort_icall_topn_counter (const struct gcov_ctr_info *counters) +{ + int i; + gcov_type *values; + int n = counters->num; + gcc_assert (!(n % GCOV_ICALL_TOPN_NCOUNTS)); + + values = counters->values; + + for (i = 0; i < n; i += GCOV_ICALL_TOPN_NCOUNTS) + { + gcov_type *value_array = &values[i + 1]; + gcov_sort_n_vals (value_array, GCOV_ICALL_TOPN_NCOUNTS - 1); + } +} + +static void +gcov_sort_topn_counter_arrays (const struct gcov_info *gi_ptr) +{ + unsigned int i; + int f_ix; + const struct gcov_fn_info *gfi_ptr; + const struct gcov_ctr_info *ci_ptr; + + for (f_ix = 0; (unsigned)f_ix != gi_ptr->n_functions; f_ix++) + { + gfi_ptr = gi_ptr->functions[f_ix]; + ci_ptr = gfi_ptr->ctrs; + for (i = 0; i < GCOV_COUNTERS; i++) + { + if (!gcov_counter_active (gi_ptr, i)) + continue; + if (i == GCOV_COUNTER_ICALL_TOPNV) + { + gcov_sort_icall_topn_counter (ci_ptr); + break; + } + ci_ptr++; + } + } +} + +/* Dump the coverage counts for one gcov_info object. We merge with existing + counts when possible, to avoid growing the .da files ad infinitum. We use + this program's checksum to make sure we only accumulate whole program + statistics to the correct summary. An object file might be embedded + in two separate programs, and we must keep the two program + summaries separate. */ + +static void +gcov_exit_dump_gcov (struct gcov_info *gi_ptr, struct gcov_filename_aux *gf, + gcov_unsigned_t crc32, struct gcov_summary *all_prg, + struct gcov_summary *this_prg) +{ + struct gcov_summary prg; /* summary for this object over all program. */ + int error; + gcov_unsigned_t tag; + gcov_position_t summary_pos = 0; + gcov_position_t eof_pos = 0; + + fn_buffer = 0; + sum_buffer = 0; + + gcov_sort_topn_counter_arrays (gi_ptr); + + error = gcov_exit_open_gcda_file (gi_ptr, gf); + if (error == -1) + return; + + tag = gcov_read_unsigned (); + if (tag) + { + /* Merge data from file. */ + if (tag != GCOV_DATA_MAGIC) + { + gcov_error ("profiling:%s:Not a gcov data file\n", gi_filename); + goto read_fatal; + } + error = gcov_exit_merge_gcda (gi_ptr, &prg, this_prg, &summary_pos, &eof_pos, + crc32); + if (error == -1) + goto read_fatal; + } + + gcov_rewrite (); + + if (!summary_pos) + { + memset (&prg, 0, sizeof (prg)); + summary_pos = eof_pos; + } + + error = gcov_exit_merge_summary (gi_ptr, &prg, this_prg, crc32, all_prg); + if (error == -1) + goto read_fatal; + + gcov_exit_write_gcda (gi_ptr, &prg, eof_pos, summary_pos); + /* fall through */ + +read_fatal:; + while (fn_buffer) + fn_buffer = free_fn_data (gi_ptr, fn_buffer, GCOV_COUNTERS); + + if ((error = gcov_close ())) + gcov_error (error < 0 ? + "profiling:%s:Overflow writing\n" : + "profiling:%s:Error writing\n", + gi_filename); +} + +/* Write imported files (auxiliary modules) for primary module GI_PTR + into file GI_FILENAME. */ + +static void +gcov_write_import_file (char *gi_filename, struct gcov_info *gi_ptr) +{ + char *gi_imports_filename; + const char *gcov_suffix; + FILE *imports_file; + size_t prefix_length, suffix_length; + + gcov_suffix = getenv ("GCOV_IMPORTS_SUFFIX"); + if (!gcov_suffix || !strlen (gcov_suffix)) + gcov_suffix = ".imports"; + suffix_length = strlen (gcov_suffix); + prefix_length = strlen (gi_filename); + gi_imports_filename = (char *) alloca (prefix_length + suffix_length + 1); + memset (gi_imports_filename, 0, prefix_length + suffix_length + 1); + memcpy (gi_imports_filename, gi_filename, prefix_length); + memcpy (gi_imports_filename + prefix_length, gcov_suffix, suffix_length); + imports_file = fopen (gi_imports_filename, "w"); + if (imports_file) + { + const struct dyn_imp_mod **imp_mods; + unsigned i, imp_len; + imp_mods = gcov_get_sorted_import_module_array (gi_ptr, &imp_len); + if (imp_mods) + { + for (i = 0; i < imp_len; i++) + { + fprintf (imports_file, "%s\n", + imp_mods[i]->imp_mod->mod_info->source_filename); + fprintf (imports_file, "%s%s\n", + imp_mods[i]->imp_mod->mod_info->da_filename, GCOV_DATA_SUFFIX); + } + free (imp_mods); + } + fclose (imports_file); + } +} + +static void +gcov_dump_module_info (struct gcov_filename_aux *gf) +{ + struct gcov_info *gi_ptr; + + /* Compute the module groups and record whether there were any + counter fixups applied that require rewriting the counters. */ + int changed = __gcov_compute_module_groups (); + + /* Now write out module group info. */ + for (gi_ptr = __gcov_list; gi_ptr; gi_ptr = gi_ptr->next) + { + int error; + + if (gcov_exit_open_gcda_file (gi_ptr, gf) == -1) + continue; + + if (changed) + { + /* Scan file to find the end of the summary section, which is + where we will start re-writing the counters. */ + gcov_position_t summary_end_pos; + if (gcov_scan_summary_end (gi_ptr, &summary_end_pos) == -1) + gcov_error ("profiling:%s:Error scanning summaries\n", + gi_filename); + else + { + gcov_position_t eof_pos = gi_ptr->eof_pos; + gcov_rewrite (); + gcov_seek (summary_end_pos); + gcov_write_func_counters (gi_ptr); + gcc_assert (eof_pos == gi_ptr->eof_pos); + } + } + else + gcov_rewrite (); + + /* Overwrite the zero word at the of the file. */ + gcov_seek (gi_ptr->eof_pos); + + gcov_write_module_infos (gi_ptr); + /* Write the end marker */ + gcov_write_unsigned (0); + gcov_truncate (); + + if ((error = gcov_close ())) + gcov_error (error < 0 ? "profiling:%s:Overflow writing\n" : + "profiling:%s:Error writing\n", + gi_filename); + gcov_write_import_file (gi_filename, gi_ptr); + } + __gcov_finalize_dyn_callgraph (); +} + +/* Dump all the coverage counts for the program. It first computes program + summary and then traverses gcov_list list and dumps the gcov_info + objects one by one. */ + +void +gcov_exit (void) +{ + struct gcov_info *gi_ptr; + struct gcov_filename_aux gf; + gcov_unsigned_t crc32; + int dump_module_info = 0; + struct gcov_summary all_prg; + struct gcov_summary this_prg; + + /* Prevent the counters from being dumped a second time on exit when the + application already wrote out the profile using __gcov_dump(). */ + if (gcov_dump_complete) + return; + + crc32 = gcov_exit_compute_summary (&this_prg); + + allocate_filename_struct (&gf); +#if !GCOV_LOCKED + memset (&all_prg, 0, sizeof (all_prg)); +#endif + + /* Now merge each file. */ + for (gi_ptr = __gcov_list; gi_ptr; gi_ptr = gi_ptr->next) + { + gcov_exit_dump_gcov (gi_ptr, &gf, crc32, &all_prg, &this_prg); + + /* The IS_PRIMARY field is overloaded to indicate if this module + is FDO/LIPO. */ + dump_module_info |= gi_ptr->mod_info->is_primary; + } + run_accounted = 1; + + if (dump_module_info) + gcov_dump_module_info (&gf); + + if (gi_filename) + free (gi_filename); +} + +/* Reset all counters to zero. */ + +void +gcov_clear (void) +{ + const struct gcov_info *gi_ptr; + + for (gi_ptr = __gcov_list; gi_ptr; gi_ptr = gi_ptr->next) + { + unsigned f_ix; + + for (f_ix = 0; f_ix < gi_ptr->n_functions; f_ix++) + { + unsigned t_ix; + const struct gcov_fn_info *gfi_ptr = gi_ptr->functions[f_ix]; + + if (!gfi_ptr || gfi_ptr->key != gi_ptr) + continue; + const struct gcov_ctr_info *ci_ptr = gfi_ptr->ctrs; + for (t_ix = 0; t_ix != GCOV_COUNTERS; t_ix++) + { + if (!gi_ptr->merge[t_ix]) + continue; + + memset (ci_ptr->values, 0, sizeof (gcov_type) * ci_ptr->num); + ci_ptr++; + } + } + } +} + +/* Add a new object file onto the bb chain. Invoked automatically + when running an object file's global ctors. */ + +void +__gcov_init (struct gcov_info *info) +{ +#ifndef IN_GCOV_TOOL + if (!gcov_sampling_period_initialized) + { + const char* env_value_str = getenv ("GCOV_SAMPLING_PERIOD"); + if (env_value_str) + { + int env_value_int = atoi(env_value_str); + if (env_value_int >= 1) + __gcov_sampling_period = env_value_int; + } + gcov_sampling_period_initialized = 1; + } +#endif + + if (!info->version || !info->n_functions) + return; + if (gcov_version (info, info->version, 0)) + { + size_t filename_length = strlen(info->filename); + + /* Refresh the longest file name information */ + if (filename_length > gcov_max_filename) + gcov_max_filename = filename_length; + + /* Assign the module ID (starting at 1). */ + info->mod_info->ident = (++gcov_cur_module_id); + gcc_assert (EXTRACT_MODULE_ID_FROM_GLOBAL_ID (GEN_FUNC_GLOBAL_ID ( + info->mod_info->ident, 0)) + == info->mod_info->ident); + + if (!__gcov_list) + atexit (gcov_exit); + + info->next = __gcov_list; + __gcov_list = info; + } + info->version = 0; +} + +#endif /* L_gcov */ +#endif /* inhibit_libc */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include-fixed/README b/lib/gcc/arm-linux-androideabi/4.9.x-google/include-fixed/README new file mode 100644 index 0000000..7086a77 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include-fixed/README @@ -0,0 +1,14 @@ +This README file is copied into the directory for GCC-only header files +when fixincludes is run by the makefile for GCC. + +Many of the files in this directory were automatically edited from the +standard system header files by the fixincludes process. They are +system-specific, and will not work on any other kind of system. They +are also not part of GCC. The reason we have to do this is because +GCC requires ANSI C headers and many vendors supply ANSI-incompatible +headers. + +Because this is an automated process, sometimes headers get "fixed" +that do not, strictly speaking, need a fix. As long as nothing is broken +by the process, it is just an unfortunate collateral inconvenience. +We would like to rectify it, if it is not "too inconvenient". diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include-fixed/limits.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include-fixed/limits.h new file mode 100644 index 0000000..8c6a4d3 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include-fixed/limits.h @@ -0,0 +1,171 @@ +/* Copyright (C) 1992-2014 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify it under +the terms of the GNU General Public License as published by the Free +Software Foundation; either version 3, or (at your option) any later +version. + +GCC is distributed in the hope that it will be useful, but WITHOUT ANY +WARRANTY; without even the implied warranty of MERCHANTABILITY or +FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + +/* This administrivia gets added to the beginning of limits.h + if the system has its own version of limits.h. */ + +/* We use _GCC_LIMITS_H_ because we want this not to match + any macros that the system's limits.h uses for its own purposes. */ +#ifndef _GCC_LIMITS_H_ /* Terminated in limity.h. */ +#define _GCC_LIMITS_H_ + +#ifndef _LIBC_LIMITS_H_ +/* Use "..." so that we find syslimits.h only in this same directory. */ +#include "syslimits.h" +#endif +/* Copyright (C) 1991-2014 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify it under +the terms of the GNU General Public License as published by the Free +Software Foundation; either version 3, or (at your option) any later +version. + +GCC is distributed in the hope that it will be useful, but WITHOUT ANY +WARRANTY; without even the implied warranty of MERCHANTABILITY or +FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + +#ifndef _LIMITS_H___ +#define _LIMITS_H___ + +/* Number of bits in a `char'. */ +#undef CHAR_BIT +#define CHAR_BIT __CHAR_BIT__ + +/* Maximum length of a multibyte character. */ +#ifndef MB_LEN_MAX +#define MB_LEN_MAX 1 +#endif + +/* Minimum and maximum values a `signed char' can hold. */ +#undef SCHAR_MIN +#define SCHAR_MIN (-SCHAR_MAX - 1) +#undef SCHAR_MAX +#define SCHAR_MAX __SCHAR_MAX__ + +/* Maximum value an `unsigned char' can hold. (Minimum is 0). */ +#undef UCHAR_MAX +#if __SCHAR_MAX__ == __INT_MAX__ +# define UCHAR_MAX (SCHAR_MAX * 2U + 1U) +#else +# define UCHAR_MAX (SCHAR_MAX * 2 + 1) +#endif + +/* Minimum and maximum values a `char' can hold. */ +#ifdef __CHAR_UNSIGNED__ +# undef CHAR_MIN +# if __SCHAR_MAX__ == __INT_MAX__ +# define CHAR_MIN 0U +# else +# define CHAR_MIN 0 +# endif +# undef CHAR_MAX +# define CHAR_MAX UCHAR_MAX +#else +# undef CHAR_MIN +# define CHAR_MIN SCHAR_MIN +# undef CHAR_MAX +# define CHAR_MAX SCHAR_MAX +#endif + +/* Minimum and maximum values a `signed short int' can hold. */ +#undef SHRT_MIN +#define SHRT_MIN (-SHRT_MAX - 1) +#undef SHRT_MAX +#define SHRT_MAX __SHRT_MAX__ + +/* Maximum value an `unsigned short int' can hold. (Minimum is 0). */ +#undef USHRT_MAX +#if __SHRT_MAX__ == __INT_MAX__ +# define USHRT_MAX (SHRT_MAX * 2U + 1U) +#else +# define USHRT_MAX (SHRT_MAX * 2 + 1) +#endif + +/* Minimum and maximum values a `signed int' can hold. */ +#undef INT_MIN +#define INT_MIN (-INT_MAX - 1) +#undef INT_MAX +#define INT_MAX __INT_MAX__ + +/* Maximum value an `unsigned int' can hold. (Minimum is 0). */ +#undef UINT_MAX +#define UINT_MAX (INT_MAX * 2U + 1U) + +/* Minimum and maximum values a `signed long int' can hold. + (Same as `int'). */ +#undef LONG_MIN +#define LONG_MIN (-LONG_MAX - 1L) +#undef LONG_MAX +#define LONG_MAX __LONG_MAX__ + +/* Maximum value an `unsigned long int' can hold. (Minimum is 0). */ +#undef ULONG_MAX +#define ULONG_MAX (LONG_MAX * 2UL + 1UL) + +#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L +/* Minimum and maximum values a `signed long long int' can hold. */ +# undef LLONG_MIN +# define LLONG_MIN (-LLONG_MAX - 1LL) +# undef LLONG_MAX +# define LLONG_MAX __LONG_LONG_MAX__ + +/* Maximum value an `unsigned long long int' can hold. (Minimum is 0). */ +# undef ULLONG_MAX +# define ULLONG_MAX (LLONG_MAX * 2ULL + 1ULL) +#endif + +#if defined (__GNU_LIBRARY__) ? defined (__USE_GNU) : !defined (__STRICT_ANSI__) +/* Minimum and maximum values a `signed long long int' can hold. */ +# undef LONG_LONG_MIN +# define LONG_LONG_MIN (-LONG_LONG_MAX - 1LL) +# undef LONG_LONG_MAX +# define LONG_LONG_MAX __LONG_LONG_MAX__ + +/* Maximum value an `unsigned long long int' can hold. (Minimum is 0). */ +# undef ULONG_LONG_MAX +# define ULONG_LONG_MAX (LONG_LONG_MAX * 2ULL + 1ULL) +#endif + +#endif /* _LIMITS_H___ */ +/* This administrivia gets added to the end of limits.h + if the system has its own version of limits.h. */ + +#else /* not _GCC_LIMITS_H_ */ + +#ifdef _GCC_NEXT_LIMITS_H +#include_next <limits.h> /* recurse down to the real one */ +#endif + +#endif /* not _GCC_LIMITS_H_ */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include-fixed/linux/a.out.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include-fixed/linux/a.out.h new file mode 100644 index 0000000..0c0972b --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include-fixed/linux/a.out.h @@ -0,0 +1,229 @@ +/* DO NOT EDIT THIS FILE. + + It has been auto-edited by fixincludes from: + + "/tmp/ndk-xur/build/toolchain/prefix/sysroot/usr/include/linux/a.out.h" + + This had to be done to correct non-standard usages in the + original, manufacturer supplied header file. */ + +/**************************************************************************** + **************************************************************************** + *** + *** This header was automatically generated from a Linux kernel header + *** of the same name, to make information necessary for userspace to + *** call into the kernel available to libc. It contains only constants, + *** structures, and macros generated from the original header, and thus, + *** contains no copyrightable information. + *** + **************************************************************************** + ****************************************************************************/ +#ifndef __A_OUT_GNU_H__ +#define __A_OUT_GNU_H__ + +#define __GNU_EXEC_MACROS__ + +#ifndef __STRUCT_EXEC_OVERRIDE__ + +#include <asm/a.out.h> + +#endif + +enum machine_type { +#ifdef M_OLDSUN2 + M__OLDSUN2 = M_OLDSUN2, +#else + M_OLDSUN2 = 0, +#endif +#ifdef M_68010 + M__68010 = M_68010, +#else + M_68010 = 1, +#endif +#ifdef M_68020 + M__68020 = M_68020, +#else + M_68020 = 2, +#endif +#ifdef M_SPARC + M__SPARC = M_SPARC, +#else + M_SPARC = 3, +#endif + + M_386 = 100, + M_MIPS1 = 151, + M_MIPS2 = 152 +}; + +#ifndef N_MAGIC +#define N_MAGIC(exec) ((exec).a_info & 0xffff) +#endif +#define N_MACHTYPE(exec) ((enum machine_type)(((exec).a_info >> 16) & 0xff)) +#define N_FLAGS(exec) (((exec).a_info >> 24) & 0xff) +#define N_SET_INFO(exec, magic, type, flags) ((exec).a_info = ((magic) & 0xffff) | (((int)(type) & 0xff) << 16) | (((flags) & 0xff) << 24)) +#define N_SET_MAGIC(exec, magic) ((exec).a_info = (((exec).a_info & 0xffff0000) | ((magic) & 0xffff))) + +#define N_SET_MACHTYPE(exec, machtype) ((exec).a_info = ((exec).a_info&0xff00ffff) | ((((int)(machtype))&0xff) << 16)) + +#define N_SET_FLAGS(exec, flags) ((exec).a_info = ((exec).a_info&0x00ffffff) | (((flags) & 0xff) << 24)) + +#define OMAGIC 0407 + +#define NMAGIC 0410 + +#define ZMAGIC 0413 + +#define QMAGIC 0314 + +#define CMAGIC 0421 + +#ifndef N_BADMAG +#define N_BADMAG(x) (N_MAGIC(x) != OMAGIC && N_MAGIC(x) != NMAGIC && N_MAGIC(x) != ZMAGIC && N_MAGIC(x) != QMAGIC) +#endif + +#define _N_HDROFF(x) (1024 - sizeof (struct exec)) + +#ifndef N_TXTOFF +#define N_TXTOFF(x) (N_MAGIC(x) == ZMAGIC ? _N_HDROFF((x)) + sizeof (struct exec) : (N_MAGIC(x) == QMAGIC ? 0 : sizeof (struct exec))) +#endif + +#ifndef N_DATOFF +#define N_DATOFF(x) (N_TXTOFF(x) + (x).a_text) +#endif + +#ifndef N_TRELOFF +#define N_TRELOFF(x) (N_DATOFF(x) + (x).a_data) +#endif + +#ifndef N_DRELOFF +#define N_DRELOFF(x) (N_TRELOFF(x) + N_TRSIZE(x)) +#endif + +#ifndef N_SYMOFF +#define N_SYMOFF(x) (N_DRELOFF(x) + N_DRSIZE(x)) +#endif + +#ifndef N_STROFF +#define N_STROFF(x) (N_SYMOFF(x) + N_SYMSIZE(x)) +#endif + +#ifndef N_TXTADDR +#define N_TXTADDR(x) (N_MAGIC(x) == QMAGIC ? PAGE_SIZE : 0) +#endif + +#if defined(vax) || defined(hp300) || defined(pyr) +#define SEGMENT_SIZE page_size +#endif +#ifdef sony +#define SEGMENT_SIZE 0x2000 +#endif +#ifdef is68k +#define SEGMENT_SIZE 0x20000 +#endif +#if defined(m68k) && defined(PORTAR) +#define PAGE_SIZE 0x400 +#define SEGMENT_SIZE PAGE_SIZE +#endif + +#ifdef __linux__ +#include <asm/page.h> +#if defined(__i386__) || defined(__mc68000__) +#define SEGMENT_SIZE 1024 +#else +#ifndef SEGMENT_SIZE +#define SEGMENT_SIZE PAGE_SIZE +#endif +#endif +#endif + +#define _N_SEGMENT_ROUND(x) ALIGN(x, SEGMENT_SIZE) + +#define _N_TXTENDADDR(x) (N_TXTADDR(x)+(x).a_text) + +#ifndef N_DATADDR +#define N_DATADDR(x) (N_MAGIC(x)==OMAGIC? (_N_TXTENDADDR(x)) : (_N_SEGMENT_ROUND (_N_TXTENDADDR(x)))) +#endif + +#ifndef N_BSSADDR +#define N_BSSADDR(x) (N_DATADDR(x) + (x).a_data) +#endif + +#ifndef N_NLIST_DECLARED +struct nlist { + union { + char *n_name; + struct nlist *n_next; + long n_strx; + } n_un; + unsigned char n_type; + char n_other; + short n_desc; + unsigned long n_value; +}; +#endif + +#ifndef N_UNDF +#define N_UNDF 0 +#endif +#ifndef N_ABS +#define N_ABS 2 +#endif +#ifndef N_TEXT +#define N_TEXT 4 +#endif +#ifndef N_DATA +#define N_DATA 6 +#endif +#ifndef N_BSS +#define N_BSS 8 +#endif +#ifndef N_FN +#define N_FN 15 +#endif + +#ifndef N_EXT +#define N_EXT 1 +#endif +#ifndef N_TYPE +#define N_TYPE 036 +#endif +#ifndef N_STAB +#define N_STAB 0340 +#endif + +#define N_INDR 0xa + +#define N_SETA 0x14 +#define N_SETT 0x16 +#define N_SETD 0x18 +#define N_SETB 0x1A + +#define N_SETV 0x1C + +#ifndef N_RELOCATION_INFO_DECLARED + +struct relocation_info +{ + + int r_address; + + unsigned int r_symbolnum:24; + + unsigned int r_pcrel:1; + + unsigned int r_length:2; + + unsigned int r_extern:1; + +#ifdef NS32K + unsigned r_bsr:1; + unsigned r_disp:1; + unsigned r_pad:2; +#else + unsigned int r_pad:4; +#endif +}; +#endif + +#endif diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include-fixed/stdio.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include-fixed/stdio.h new file mode 100644 index 0000000..c73f7b2 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include-fixed/stdio.h @@ -0,0 +1,441 @@ +/* DO NOT EDIT THIS FILE. + + It has been auto-edited by fixincludes from: + + "/tmp/ndk-xur/build/toolchain/prefix/sysroot/usr/include/stdio.h" + + This had to be done to correct non-standard usages in the + original, manufacturer supplied header file. */ + +/* $OpenBSD: stdio.h,v 1.35 2006/01/13 18:10:09 miod Exp $ */ +/* $NetBSD: stdio.h,v 1.18 1996/04/25 18:29:21 jtc Exp $ */ + +/*- + * Copyright (c) 1990 The Regents of the University of California. + * All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Chris Torek. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)stdio.h 5.17 (Berkeley) 6/3/91 + */ + +#ifndef _STDIO_H_ +#define _STDIO_H_ + +#include <sys/cdefs.h> +#include <sys/types.h> + +/* __gnuc_va_list and size_t must be defined by stdio.h according to Posix */ +#define __need___va_list +#include <stdarg.h> + +/* note that this forces stddef.h to *only* define size_t */ +#define __need_size_t +#include <stddef.h> + +#define __need_NULL +#include <stddef.h> + +#define _FSTDIO /* Define for new stdio with functions. */ + +typedef off_t fpos_t; /* stdio file position type */ + +/* + * NB: to fit things in six character monocase externals, the stdio + * code uses the prefix `__s' for stdio objects, typically followed + * by a three-character attempt at a mnemonic. + */ + +/* stdio buffers */ +struct __sbuf { + unsigned char *_base; + int _size; +}; + +/* + * stdio state variables. + * + * The following always hold: + * + * if (_flags&(__SLBF|__SWR)) == (__SLBF|__SWR), + * _lbfsize is -_bf._size, else _lbfsize is 0 + * if _flags&__SRD, _w is 0 + * if _flags&__SWR, _r is 0 + * + * This ensures that the getc and putc macros (or inline functions) never + * try to write or read from a file that is in `read' or `write' mode. + * (Moreover, they can, and do, automatically switch from read mode to + * write mode, and back, on "r+" and "w+" files.) + * + * _lbfsize is used only to make the inline line-buffered output stream + * code as compact as possible. + * + * _ub, _up, and _ur are used when ungetc() pushes back more characters + * than fit in the current _bf, or when ungetc() pushes back a character + * that does not match the previous one in _bf. When this happens, + * _ub._base becomes non-nil (i.e., a stream has ungetc() data iff + * _ub._base!=NULL) and _up and _ur save the current values of _p and _r. + * + * NOTE: if you change this structure, you also need to update the + * std() initializer in findfp.c. + */ +typedef struct __sFILE { + unsigned char *_p; /* current position in (some) buffer */ + int _r; /* read space left for getc() */ + int _w; /* write space left for putc() */ + short _flags; /* flags, below; this FILE is free if 0 */ + short _file; /* fileno, if Unix descriptor, else -1 */ + struct __sbuf _bf; /* the buffer (at least 1 byte, if !NULL) */ + int _lbfsize; /* 0 or -_bf._size, for inline putc */ + + /* operations */ + void *_cookie; /* cookie passed to io functions */ + int (*_close)(void *); + int (*_read)(void *, char *, int); + fpos_t (*_seek)(void *, fpos_t, int); + int (*_write)(void *, const char *, int); + + /* extension data, to avoid further ABI breakage */ + struct __sbuf _ext; + /* data for long sequences of ungetc() */ + unsigned char *_up; /* saved _p when _p is doing ungetc data */ + int _ur; /* saved _r when _r is counting ungetc data */ + + /* tricks to meet minimum requirements even when malloc() fails */ + unsigned char _ubuf[3]; /* guarantee an ungetc() buffer */ + unsigned char _nbuf[1]; /* guarantee a getc() buffer */ + + /* separate buffer for fgetln() when line crosses buffer boundary */ + struct __sbuf _lb; /* buffer for fgetln() */ + + /* Unix stdio files get aligned to block boundaries on fseek() */ + int _blksize; /* stat.st_blksize (may be != _bf._size) */ + fpos_t _offset; /* current lseek offset */ +} FILE; + +__BEGIN_DECLS +extern FILE __sF[]; +__END_DECLS + +#define __SLBF 0x0001 /* line buffered */ +#define __SNBF 0x0002 /* unbuffered */ +#define __SRD 0x0004 /* OK to read */ +#define __SWR 0x0008 /* OK to write */ + /* RD and WR are never simultaneously asserted */ +#define __SRW 0x0010 /* open for reading & writing */ +#define __SEOF 0x0020 /* found EOF */ +#define __SERR 0x0040 /* found error */ +#define __SMBF 0x0080 /* _buf is from malloc */ +#define __SAPP 0x0100 /* fdopen()ed in append mode */ +#define __SSTR 0x0200 /* this is an sprintf/snprintf string */ +#define __SOPT 0x0400 /* do fseek() optimisation */ +#define __SNPT 0x0800 /* do not do fseek() optimisation */ +#define __SOFF 0x1000 /* set iff _offset is in fact correct */ +#define __SMOD 0x2000 /* true => fgetln modified _p text */ +#define __SALC 0x4000 /* allocate string space dynamically */ + +/* + * The following three definitions are for ANSI C, which took them + * from System V, which brilliantly took internal interface macros and + * made them official arguments to setvbuf(), without renaming them. + * Hence, these ugly _IOxxx names are *supposed* to appear in user code. + * + * Although numbered as their counterparts above, the implementation + * does not rely on this. + */ +#define _IOFBF 0 /* setvbuf should set fully buffered */ +#define _IOLBF 1 /* setvbuf should set line buffered */ +#define _IONBF 2 /* setvbuf should set unbuffered */ + +#define BUFSIZ 1024 /* size of buffer used by setbuf */ + +#define EOF (-1) + +/* + * FOPEN_MAX is a minimum maximum, and should be the number of descriptors + * that the kernel can provide without allocation of a resource that can + * fail without the process sleeping. Do not use this for anything. + */ +#define FOPEN_MAX 20 /* must be <= OPEN_MAX <sys/syslimits.h> */ +#define FILENAME_MAX 1024 /* must be <= PATH_MAX <sys/syslimits.h> */ + +/* System V/ANSI C; this is the wrong way to do this, do *not* use these. */ +#if __BSD_VISIBLE || __XPG_VISIBLE +#define P_tmpdir "/tmp/" +#endif +#define L_tmpnam 1024 /* XXX must be == PATH_MAX */ +#define TMP_MAX 308915776 + +#ifndef SEEK_SET +#define SEEK_SET 0 /* set file offset to offset */ +#endif +#ifndef SEEK_CUR +#define SEEK_CUR 1 /* set file offset to current plus offset */ +#endif +#ifndef SEEK_END +#define SEEK_END 2 /* set file offset to EOF plus offset */ +#endif + +#define stdin (&__sF[0]) +#define stdout (&__sF[1]) +#define stderr (&__sF[2]) + +/* + * Functions defined in ANSI C standard. + */ +__BEGIN_DECLS +void clearerr(FILE *); +int fclose(FILE *); +int feof(FILE *); +int ferror(FILE *); +int fflush(FILE *); +int fgetc(FILE *); +int fgetpos(FILE *, fpos_t *); +char *fgets(char *, int, FILE *); +FILE *fopen(const char *, const char *); +int fprintf(FILE *, const char *, ...); +int fputc(int, FILE *); +int fputs(const char *, FILE *); +size_t fread(void *, size_t, size_t, FILE *); +FILE *freopen(const char *, const char *, FILE *); +int fscanf(FILE *, const char *, ...); +int fseek(FILE *, long, int); +int fseeko(FILE *, off_t, int); +int fsetpos(FILE *, const fpos_t *); +long ftell(FILE *); +off_t ftello(FILE *); +size_t fwrite(const void *, size_t, size_t, FILE *); +int getc(FILE *); +int getchar(void); +char *gets(char *); +#if __BSD_VISIBLE && !defined(__SYS_ERRLIST) +#define __SYS_ERRLIST + +extern int sys_nerr; /* perror(3) external variables */ +extern char *sys_errlist[]; +#endif +void perror(const char *); +int printf(const char *, ...); +int putc(int, FILE *); +int putchar(int); +int puts(const char *); +int remove(const char *); +int rename(const char *, const char *); +void rewind(FILE *); +int scanf(const char *, ...); +void setbuf(FILE *, char *); +int setvbuf(FILE *, char *, int, size_t); +int sprintf(char *, const char *, ...); +int sscanf(const char *, const char *, ...); +FILE *tmpfile(void); +char *tmpnam(char *); +int ungetc(int, FILE *); +int vfprintf(FILE *, const char *, __gnuc_va_list); +int vprintf(const char *, __gnuc_va_list); +int vsprintf(char *, const char *, __gnuc_va_list); + +#if __ISO_C_VISIBLE >= 1999 || __BSD_VISIBLE +int snprintf(char *, size_t, const char *, ...) + __attribute__((__format__ (printf, 3, 4))) + __attribute__((__nonnull__ (3))); +int vfscanf(FILE *, const char *, __gnuc_va_list) + __attribute__((__format__ (scanf, 2, 0))) + __attribute__((__nonnull__ (2))); +int vscanf(const char *, __gnuc_va_list) + __attribute__((__format__ (scanf, 1, 0))) + __attribute__((__nonnull__ (1))); +int vsnprintf(char *, size_t, const char *, __gnuc_va_list) + __attribute__((__format__ (printf, 3, 0))) + __attribute__((__nonnull__ (3))); +int vsscanf(const char *, const char *, __gnuc_va_list) + __attribute__((__format__ (scanf, 2, 0))) + __attribute__((__nonnull__ (2))); +#endif /* __ISO_C_VISIBLE >= 1999 || __BSD_VISIBLE */ + +__END_DECLS + + +/* + * Functions defined in POSIX 1003.1. + */ +#if __BSD_VISIBLE || __POSIX_VISIBLE || __XPG_VISIBLE +#define L_ctermid 1024 /* size for ctermid(); PATH_MAX */ +#define L_cuserid 9 /* size for cuserid(); UT_NAMESIZE + 1 */ + +__BEGIN_DECLS +#if 0 /* MISSING FROM BIONIC */ +char *ctermid(char *); +char *cuserid(char *); +#endif /* MISSING */ +FILE *fdopen(int, const char *); +int fileno(FILE *); + +#if (__POSIX_VISIBLE >= 199209) +int pclose(FILE *); +FILE *popen(const char *, const char *); +#endif + +#if __POSIX_VISIBLE >= 199506 +void flockfile(FILE *); +int ftrylockfile(FILE *); +void funlockfile(FILE *); + +/* + * These are normally used through macros as defined below, but POSIX + * requires functions as well. + */ +int getc_unlocked(FILE *); +int getchar_unlocked(void); +int putc_unlocked(int, FILE *); +int putchar_unlocked(int); +#endif /* __POSIX_VISIBLE >= 199506 */ + +#if __XPG_VISIBLE +char *tempnam(const char *, const char *); +#endif +__END_DECLS + +#endif /* __BSD_VISIBLE || __POSIX_VISIBLE || __XPG_VISIBLE */ + +/* + * Routines that are purely local. + */ +#if __BSD_VISIBLE +__BEGIN_DECLS +int asprintf(char **, const char *, ...) + __attribute__((__format__ (printf, 2, 3))) + __attribute__((__nonnull__ (2))); +char *fgetln(FILE *, size_t *); +int fpurge(FILE *); +int getw(FILE *); +int putw(int, FILE *); +void setbuffer(FILE *, char *, int); +int setlinebuf(FILE *); +int vasprintf(char **, const char *, __gnuc_va_list) + __attribute__((__format__ (printf, 2, 0))) + __attribute__((__nonnull__ (2))); +__END_DECLS + +/* + * Stdio function-access interface. + */ +__BEGIN_DECLS +FILE *funopen(const void *, + int (*)(void *, char *, int), + int (*)(void *, const char *, int), + fpos_t (*)(void *, fpos_t, int), + int (*)(void *)); +__END_DECLS +#define fropen(cookie, fn) funopen(cookie, fn, 0, 0, 0) +#define fwopen(cookie, fn) funopen(cookie, 0, fn, 0, 0) +#endif /* __BSD_VISIBLE */ + +/* + * Functions internal to the implementation. + */ +__BEGIN_DECLS +int __srget(FILE *); +int __swbuf(int, FILE *); +__END_DECLS + +/* + * The __sfoo macros are here so that we can + * define function versions in the C library. + */ +#define __sgetc(p) (--(p)->_r < 0 ? __srget(p) : (int)(*(p)->_p++)) +#if defined(__GNUC__) +static __inline int __sputc(int _c, FILE *_p) { + if (--_p->_w >= 0 || (_p->_w >= _p->_lbfsize && (char)_c != '\n')) + return (*_p->_p++ = _c); + else + return (__swbuf(_c, _p)); +} +#else +/* + * This has been tuned to generate reasonable code on the vax using pcc. + */ +#define __sputc(c, p) \ + (--(p)->_w < 0 ? \ + (p)->_w >= (p)->_lbfsize ? \ + (*(p)->_p = (c)), *(p)->_p != '\n' ? \ + (int)*(p)->_p++ : \ + __swbuf('\n', p) : \ + __swbuf((int)(c), p) : \ + (*(p)->_p = (c), (int)*(p)->_p++)) +#endif + +#define __sfeof(p) (((p)->_flags & __SEOF) != 0) +#define __sferror(p) (((p)->_flags & __SERR) != 0) +#define __sclearerr(p) ((void)((p)->_flags &= ~(__SERR|__SEOF))) +#define __sfileno(p) ((p)->_file) + +#define feof(p) __sfeof(p) +#define ferror(p) __sferror(p) + +#ifndef _POSIX_THREADS +#define clearerr(p) __sclearerr(p) +#endif + +#if __POSIX_VISIBLE +#define fileno(p) __sfileno(p) +#endif + +#ifndef lint +#ifndef _POSIX_THREADS +#define getc(fp) __sgetc(fp) +#endif /* _POSIX_THREADS */ +#define getc_unlocked(fp) __sgetc(fp) +/* + * The macro implementations of putc and putc_unlocked are not + * fully POSIX compliant; they do not set errno on failure + */ +#if __BSD_VISIBLE +#ifndef _POSIX_THREADS +#define putc(x, fp) __sputc(x, fp) +#endif /* _POSIX_THREADS */ +#define putc_unlocked(x, fp) __sputc(x, fp) +#endif /* __BSD_VISIBLE */ +#endif /* lint */ + +#define getchar() getc(stdin) +#define putchar(x) putc(x, stdout) +#define getchar_unlocked() getc_unlocked(stdin) +#define putchar_unlocked(c) putc_unlocked(c, stdout) + +#ifdef _GNU_SOURCE +/* + * glibc defines dprintf(int, const char*, ...), which is poorly named + * and likely to conflict with locally defined debugging printfs + * fdprintf is a better name, and some programs that use fdprintf use a + * #define fdprintf dprintf for compatibility + */ +int fdprintf(int, const char*, ...); +int vfdprintf(int, const char*, __gnuc_va_list); +#endif /* _GNU_SOURCE */ + +#endif /* _STDIO_H_ */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include-fixed/syslimits.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include-fixed/syslimits.h new file mode 100644 index 0000000..a362802 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include-fixed/syslimits.h @@ -0,0 +1,8 @@ +/* syslimits.h stands for the system's own limits.h file. + If we can use it ok unmodified, then we install this text. + If fixincludes fixes it, then the fixed version is installed + instead of this text. */ + +#define _GCC_NEXT_LIMITS_H /* tell gcc's limits.h to recurse */ +#include_next <limits.h> +#undef _GCC_NEXT_LIMITS_H diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/arm_acle.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/arm_acle.h new file mode 100644 index 0000000..aaa7aff --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/arm_acle.h @@ -0,0 +1,100 @@ +/* ARM Non-NEON ACLE intrinsics include file. + + Copyright (C) 2013-2014 Free Software Foundation, Inc. + Contributed by ARM Ltd. + + This file is part of GCC. + + GCC is free software; you can redistribute it and/or modify it + under the terms of the GNU General Public License as published + by the Free Software Foundation; either version 3, or (at your + option) any later version. + + GCC is distributed in the hope that it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY + or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public + License for more details. + + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see + <http://www.gnu.org/licenses/>. */ + +#ifndef _GCC_ARM_ACLE_H +#define _GCC_ARM_ACLE_H + +#include <stdint.h> +#ifdef __cplusplus +extern "C" { +#endif + +#ifdef __ARM_FEATURE_CRC32 +__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) +__crc32b (uint32_t __a, uint8_t __b) +{ + return __builtin_arm_crc32b (__a, __b); +} + +__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) +__crc32h (uint32_t __a, uint16_t __b) +{ + return __builtin_arm_crc32h (__a, __b); +} + +__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) +__crc32w (uint32_t __a, uint32_t __b) +{ + return __builtin_arm_crc32w (__a, __b); +} + +#ifdef __ARM_32BIT_STATE +__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) +__crc32d (uint32_t __a, uint64_t __b) +{ + uint32_t __d; + + __d = __crc32w (__crc32w (__a, __b & 0xffffffffULL), __b >> 32); + return __d; +} +#endif + +__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) +__crc32cb (uint32_t __a, uint8_t __b) +{ + return __builtin_arm_crc32cb (__a, __b); +} + +__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) +__crc32ch (uint32_t __a, uint16_t __b) +{ + return __builtin_arm_crc32ch (__a, __b); +} + +__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) +__crc32cw (uint32_t __a, uint32_t __b) +{ + return __builtin_arm_crc32cw (__a, __b); +} + +#ifdef __ARM_32BIT_STATE +__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) +__crc32cd (uint32_t __a, uint64_t __b) +{ + uint32_t __d; + + __d = __crc32cw (__crc32cw (__a, __b & 0xffffffffULL), __b >> 32); + return __d; +} +#endif + +#endif + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/arm_neon.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/arm_neon.h new file mode 100644 index 0000000..9573543 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/arm_neon.h @@ -0,0 +1,13817 @@ +/* ARM NEON intrinsics include file. + + Copyright (C) 2006-2014 Free Software Foundation, Inc. + Contributed by CodeSourcery. + + This file is part of GCC. + + GCC is free software; you can redistribute it and/or modify it + under the terms of the GNU General Public License as published + by the Free Software Foundation; either version 3, or (at your + option) any later version. + + GCC is distributed in the hope that it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY + or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public + License for more details. + + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see + <http://www.gnu.org/licenses/>. */ + +#ifndef _GCC_ARM_NEON_H +#define _GCC_ARM_NEON_H 1 + +#ifndef __ARM_NEON__ +#error You must enable NEON instructions (e.g. -mfloat-abi=softfp -mfpu=neon) to use arm_neon.h +#else + +#ifdef __cplusplus +extern "C" { +#endif + +#include <stdint.h> + +typedef __builtin_neon_qi int8x8_t __attribute__ ((__vector_size__ (8))); +typedef __builtin_neon_hi int16x4_t __attribute__ ((__vector_size__ (8))); +typedef __builtin_neon_si int32x2_t __attribute__ ((__vector_size__ (8))); +typedef __builtin_neon_di int64x1_t; +typedef __builtin_neon_hf float16x4_t __attribute__ ((__vector_size__ (8))); +typedef __builtin_neon_sf float32x2_t __attribute__ ((__vector_size__ (8))); +typedef __builtin_neon_poly8 poly8x8_t __attribute__ ((__vector_size__ (8))); +typedef __builtin_neon_poly16 poly16x4_t __attribute__ ((__vector_size__ (8))); +#ifdef __ARM_FEATURE_CRYPTO +typedef __builtin_neon_poly64 poly64x1_t; +#endif +typedef __builtin_neon_uqi uint8x8_t __attribute__ ((__vector_size__ (8))); +typedef __builtin_neon_uhi uint16x4_t __attribute__ ((__vector_size__ (8))); +typedef __builtin_neon_usi uint32x2_t __attribute__ ((__vector_size__ (8))); +typedef __builtin_neon_udi uint64x1_t; +typedef __builtin_neon_qi int8x16_t __attribute__ ((__vector_size__ (16))); +typedef __builtin_neon_hi int16x8_t __attribute__ ((__vector_size__ (16))); +typedef __builtin_neon_si int32x4_t __attribute__ ((__vector_size__ (16))); +typedef __builtin_neon_di int64x2_t __attribute__ ((__vector_size__ (16))); +typedef __builtin_neon_sf float32x4_t __attribute__ ((__vector_size__ (16))); +typedef __builtin_neon_poly8 poly8x16_t __attribute__ ((__vector_size__ (16))); +typedef __builtin_neon_poly16 poly16x8_t __attribute__ ((__vector_size__ (16))); +#ifdef __ARM_FEATURE_CRYPTO +typedef __builtin_neon_poly64 poly64x2_t __attribute__ ((__vector_size__ (16))); +#endif +typedef __builtin_neon_uqi uint8x16_t __attribute__ ((__vector_size__ (16))); +typedef __builtin_neon_uhi uint16x8_t __attribute__ ((__vector_size__ (16))); +typedef __builtin_neon_usi uint32x4_t __attribute__ ((__vector_size__ (16))); +typedef __builtin_neon_udi uint64x2_t __attribute__ ((__vector_size__ (16))); + +typedef float float32_t; +typedef __builtin_neon_poly8 poly8_t; +typedef __builtin_neon_poly16 poly16_t; +#ifdef __ARM_FEATURE_CRYPTO +typedef __builtin_neon_poly64 poly64_t; +typedef __builtin_neon_poly128 poly128_t; +#endif + +typedef struct int8x8x2_t +{ + int8x8_t val[2]; +} int8x8x2_t; + +typedef struct int8x16x2_t +{ + int8x16_t val[2]; +} int8x16x2_t; + +typedef struct int16x4x2_t +{ + int16x4_t val[2]; +} int16x4x2_t; + +typedef struct int16x8x2_t +{ + int16x8_t val[2]; +} int16x8x2_t; + +typedef struct int32x2x2_t +{ + int32x2_t val[2]; +} int32x2x2_t; + +typedef struct int32x4x2_t +{ + int32x4_t val[2]; +} int32x4x2_t; + +typedef struct int64x1x2_t +{ + int64x1_t val[2]; +} int64x1x2_t; + +typedef struct int64x2x2_t +{ + int64x2_t val[2]; +} int64x2x2_t; + +typedef struct uint8x8x2_t +{ + uint8x8_t val[2]; +} uint8x8x2_t; + +typedef struct uint8x16x2_t +{ + uint8x16_t val[2]; +} uint8x16x2_t; + +typedef struct uint16x4x2_t +{ + uint16x4_t val[2]; +} uint16x4x2_t; + +typedef struct uint16x8x2_t +{ + uint16x8_t val[2]; +} uint16x8x2_t; + +typedef struct uint32x2x2_t +{ + uint32x2_t val[2]; +} uint32x2x2_t; + +typedef struct uint32x4x2_t +{ + uint32x4_t val[2]; +} uint32x4x2_t; + +typedef struct uint64x1x2_t +{ + uint64x1_t val[2]; +} uint64x1x2_t; + +typedef struct uint64x2x2_t +{ + uint64x2_t val[2]; +} uint64x2x2_t; + +typedef struct float32x2x2_t +{ + float32x2_t val[2]; +} float32x2x2_t; + +typedef struct float32x4x2_t +{ + float32x4_t val[2]; +} float32x4x2_t; + +typedef struct poly8x8x2_t +{ + poly8x8_t val[2]; +} poly8x8x2_t; + +typedef struct poly8x16x2_t +{ + poly8x16_t val[2]; +} poly8x16x2_t; + +typedef struct poly16x4x2_t +{ + poly16x4_t val[2]; +} poly16x4x2_t; + +typedef struct poly16x8x2_t +{ + poly16x8_t val[2]; +} poly16x8x2_t; + +#ifdef __ARM_FEATURE_CRYPTO +typedef struct poly64x1x2_t +{ + poly64x1_t val[2]; +} poly64x1x2_t; +#endif + + +#ifdef __ARM_FEATURE_CRYPTO +typedef struct poly64x2x2_t +{ + poly64x2_t val[2]; +} poly64x2x2_t; +#endif + + +typedef struct int8x8x3_t +{ + int8x8_t val[3]; +} int8x8x3_t; + +typedef struct int8x16x3_t +{ + int8x16_t val[3]; +} int8x16x3_t; + +typedef struct int16x4x3_t +{ + int16x4_t val[3]; +} int16x4x3_t; + +typedef struct int16x8x3_t +{ + int16x8_t val[3]; +} int16x8x3_t; + +typedef struct int32x2x3_t +{ + int32x2_t val[3]; +} int32x2x3_t; + +typedef struct int32x4x3_t +{ + int32x4_t val[3]; +} int32x4x3_t; + +typedef struct int64x1x3_t +{ + int64x1_t val[3]; +} int64x1x3_t; + +typedef struct int64x2x3_t +{ + int64x2_t val[3]; +} int64x2x3_t; + +typedef struct uint8x8x3_t +{ + uint8x8_t val[3]; +} uint8x8x3_t; + +typedef struct uint8x16x3_t +{ + uint8x16_t val[3]; +} uint8x16x3_t; + +typedef struct uint16x4x3_t +{ + uint16x4_t val[3]; +} uint16x4x3_t; + +typedef struct uint16x8x3_t +{ + uint16x8_t val[3]; +} uint16x8x3_t; + +typedef struct uint32x2x3_t +{ + uint32x2_t val[3]; +} uint32x2x3_t; + +typedef struct uint32x4x3_t +{ + uint32x4_t val[3]; +} uint32x4x3_t; + +typedef struct uint64x1x3_t +{ + uint64x1_t val[3]; +} uint64x1x3_t; + +typedef struct uint64x2x3_t +{ + uint64x2_t val[3]; +} uint64x2x3_t; + +typedef struct float32x2x3_t +{ + float32x2_t val[3]; +} float32x2x3_t; + +typedef struct float32x4x3_t +{ + float32x4_t val[3]; +} float32x4x3_t; + +typedef struct poly8x8x3_t +{ + poly8x8_t val[3]; +} poly8x8x3_t; + +typedef struct poly8x16x3_t +{ + poly8x16_t val[3]; +} poly8x16x3_t; + +typedef struct poly16x4x3_t +{ + poly16x4_t val[3]; +} poly16x4x3_t; + +typedef struct poly16x8x3_t +{ + poly16x8_t val[3]; +} poly16x8x3_t; + +#ifdef __ARM_FEATURE_CRYPTO +typedef struct poly64x1x3_t +{ + poly64x1_t val[3]; +} poly64x1x3_t; +#endif + + +#ifdef __ARM_FEATURE_CRYPTO +typedef struct poly64x2x3_t +{ + poly64x2_t val[3]; +} poly64x2x3_t; +#endif + + +typedef struct int8x8x4_t +{ + int8x8_t val[4]; +} int8x8x4_t; + +typedef struct int8x16x4_t +{ + int8x16_t val[4]; +} int8x16x4_t; + +typedef struct int16x4x4_t +{ + int16x4_t val[4]; +} int16x4x4_t; + +typedef struct int16x8x4_t +{ + int16x8_t val[4]; +} int16x8x4_t; + +typedef struct int32x2x4_t +{ + int32x2_t val[4]; +} int32x2x4_t; + +typedef struct int32x4x4_t +{ + int32x4_t val[4]; +} int32x4x4_t; + +typedef struct int64x1x4_t +{ + int64x1_t val[4]; +} int64x1x4_t; + +typedef struct int64x2x4_t +{ + int64x2_t val[4]; +} int64x2x4_t; + +typedef struct uint8x8x4_t +{ + uint8x8_t val[4]; +} uint8x8x4_t; + +typedef struct uint8x16x4_t +{ + uint8x16_t val[4]; +} uint8x16x4_t; + +typedef struct uint16x4x4_t +{ + uint16x4_t val[4]; +} uint16x4x4_t; + +typedef struct uint16x8x4_t +{ + uint16x8_t val[4]; +} uint16x8x4_t; + +typedef struct uint32x2x4_t +{ + uint32x2_t val[4]; +} uint32x2x4_t; + +typedef struct uint32x4x4_t +{ + uint32x4_t val[4]; +} uint32x4x4_t; + +typedef struct uint64x1x4_t +{ + uint64x1_t val[4]; +} uint64x1x4_t; + +typedef struct uint64x2x4_t +{ + uint64x2_t val[4]; +} uint64x2x4_t; + +typedef struct float32x2x4_t +{ + float32x2_t val[4]; +} float32x2x4_t; + +typedef struct float32x4x4_t +{ + float32x4_t val[4]; +} float32x4x4_t; + +typedef struct poly8x8x4_t +{ + poly8x8_t val[4]; +} poly8x8x4_t; + +typedef struct poly8x16x4_t +{ + poly8x16_t val[4]; +} poly8x16x4_t; + +typedef struct poly16x4x4_t +{ + poly16x4_t val[4]; +} poly16x4x4_t; + +typedef struct poly16x8x4_t +{ + poly16x8_t val[4]; +} poly16x8x4_t; + +#ifdef __ARM_FEATURE_CRYPTO +typedef struct poly64x1x4_t +{ + poly64x1_t val[4]; +} poly64x1x4_t; +#endif + + +#ifdef __ARM_FEATURE_CRYPTO +typedef struct poly64x2x4_t +{ + poly64x2_t val[4]; +} poly64x2x4_t; +#endif + + + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vadd_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vaddv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vadd_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vaddv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vadd_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vaddv2si (__a, __b, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vadd_f32 (float32x2_t __a, float32x2_t __b) +{ + return (float32x2_t)__builtin_neon_vaddv2sf (__a, __b, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vadd_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vaddv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vadd_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vaddv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vadd_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vaddv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vadd_s64 (int64x1_t __a, int64x1_t __b) +{ + return (int64x1_t)__builtin_neon_vadddi (__a, __b, 1); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vadd_u64 (uint64x1_t __a, uint64x1_t __b) +{ + return (uint64x1_t)__builtin_neon_vadddi ((int64x1_t) __a, (int64x1_t) __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vaddq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vaddv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vaddq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vaddv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vaddq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vaddv4si (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vaddq_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int64x2_t)__builtin_neon_vaddv2di (__a, __b, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vaddq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (float32x4_t)__builtin_neon_vaddv4sf (__a, __b, 3); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vaddq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vaddv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vaddq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vaddv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vaddq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vaddv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vaddq_u64 (uint64x2_t __a, uint64x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vaddv2di ((int64x2_t) __a, (int64x2_t) __b, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vaddl_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int16x8_t)__builtin_neon_vaddlv8qi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vaddl_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int32x4_t)__builtin_neon_vaddlv4hi (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vaddl_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int64x2_t)__builtin_neon_vaddlv2si (__a, __b, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vaddl_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vaddlv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vaddl_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vaddlv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vaddl_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vaddlv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vaddw_s8 (int16x8_t __a, int8x8_t __b) +{ + return (int16x8_t)__builtin_neon_vaddwv8qi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vaddw_s16 (int32x4_t __a, int16x4_t __b) +{ + return (int32x4_t)__builtin_neon_vaddwv4hi (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vaddw_s32 (int64x2_t __a, int32x2_t __b) +{ + return (int64x2_t)__builtin_neon_vaddwv2si (__a, __b, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vaddw_u8 (uint16x8_t __a, uint8x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vaddwv8qi ((int16x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vaddw_u16 (uint32x4_t __a, uint16x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vaddwv4hi ((int32x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vaddw_u32 (uint64x2_t __a, uint32x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vaddwv2si ((int64x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vhadd_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vhaddv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vhadd_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vhaddv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vhadd_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vhaddv2si (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vhadd_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vhaddv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vhadd_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vhaddv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vhadd_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vhaddv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vhaddq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vhaddv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vhaddq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vhaddv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vhaddq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vhaddv4si (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vhaddq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vhaddv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vhaddq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vhaddv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vhaddq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vhaddv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vrhadd_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vhaddv8qi (__a, __b, 5); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vrhadd_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vhaddv4hi (__a, __b, 5); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vrhadd_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vhaddv2si (__a, __b, 5); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vrhadd_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vhaddv8qi ((int8x8_t) __a, (int8x8_t) __b, 4); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vrhadd_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vhaddv4hi ((int16x4_t) __a, (int16x4_t) __b, 4); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vrhadd_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vhaddv2si ((int32x2_t) __a, (int32x2_t) __b, 4); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vrhaddq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vhaddv16qi (__a, __b, 5); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vrhaddq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vhaddv8hi (__a, __b, 5); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vrhaddq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vhaddv4si (__a, __b, 5); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vrhaddq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vhaddv16qi ((int8x16_t) __a, (int8x16_t) __b, 4); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vrhaddq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vhaddv8hi ((int16x8_t) __a, (int16x8_t) __b, 4); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vrhaddq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vhaddv4si ((int32x4_t) __a, (int32x4_t) __b, 4); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vqadd_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vqaddv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqadd_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vqaddv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqadd_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vqaddv2si (__a, __b, 1); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vqadd_s64 (int64x1_t __a, int64x1_t __b) +{ + return (int64x1_t)__builtin_neon_vqadddi (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vqadd_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vqaddv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vqadd_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vqaddv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vqadd_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vqaddv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vqadd_u64 (uint64x1_t __a, uint64x1_t __b) +{ + return (uint64x1_t)__builtin_neon_vqadddi ((int64x1_t) __a, (int64x1_t) __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vqaddq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vqaddv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vqaddq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vqaddv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqaddq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vqaddv4si (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vqaddq_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int64x2_t)__builtin_neon_vqaddv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vqaddq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vqaddv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vqaddq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vqaddv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vqaddq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vqaddv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vqaddq_u64 (uint64x2_t __a, uint64x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vqaddv2di ((int64x2_t) __a, (int64x2_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vaddhn_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int8x8_t)__builtin_neon_vaddhnv8hi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vaddhn_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int16x4_t)__builtin_neon_vaddhnv4si (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vaddhn_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int32x2_t)__builtin_neon_vaddhnv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vaddhn_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vaddhnv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vaddhn_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vaddhnv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vaddhn_u64 (uint64x2_t __a, uint64x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vaddhnv2di ((int64x2_t) __a, (int64x2_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vraddhn_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int8x8_t)__builtin_neon_vaddhnv8hi (__a, __b, 5); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vraddhn_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int16x4_t)__builtin_neon_vaddhnv4si (__a, __b, 5); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vraddhn_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int32x2_t)__builtin_neon_vaddhnv2di (__a, __b, 5); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vraddhn_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vaddhnv8hi ((int16x8_t) __a, (int16x8_t) __b, 4); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vraddhn_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vaddhnv4si ((int32x4_t) __a, (int32x4_t) __b, 4); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vraddhn_u64 (uint64x2_t __a, uint64x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vaddhnv2di ((int64x2_t) __a, (int64x2_t) __b, 4); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vmul_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vmulv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vmul_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vmulv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vmul_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vmulv2si (__a, __b, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vmul_f32 (float32x2_t __a, float32x2_t __b) +{ + return (float32x2_t)__builtin_neon_vmulv2sf (__a, __b, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vmul_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vmulv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vmul_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vmulv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vmul_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vmulv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vmul_p8 (poly8x8_t __a, poly8x8_t __b) +{ + return (poly8x8_t)__builtin_neon_vmulv8qi ((int8x8_t) __a, (int8x8_t) __b, 2); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vmulq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vmulv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmulq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vmulv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmulq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vmulv4si (__a, __b, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vmulq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (float32x4_t)__builtin_neon_vmulv4sf (__a, __b, 3); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vmulq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vmulv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmulq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vmulv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmulq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vmulv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vmulq_p8 (poly8x16_t __a, poly8x16_t __b) +{ + return (poly8x16_t)__builtin_neon_vmulv16qi ((int8x16_t) __a, (int8x16_t) __b, 2); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqdmulh_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vqdmulhv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqdmulh_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vqdmulhv2si (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vqdmulhq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vqdmulhv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqdmulhq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vqdmulhv4si (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqrdmulh_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vqdmulhv4hi (__a, __b, 5); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqrdmulh_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vqdmulhv2si (__a, __b, 5); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vqrdmulhq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vqdmulhv8hi (__a, __b, 5); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqrdmulhq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vqdmulhv4si (__a, __b, 5); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmull_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int16x8_t)__builtin_neon_vmullv8qi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmull_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int32x4_t)__builtin_neon_vmullv4hi (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vmull_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int64x2_t)__builtin_neon_vmullv2si (__a, __b, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmull_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vmullv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmull_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vmullv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vmull_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vmullv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vmull_p8 (poly8x8_t __a, poly8x8_t __b) +{ + return (poly16x8_t)__builtin_neon_vmullv8qi ((int8x8_t) __a, (int8x8_t) __b, 2); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqdmull_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int32x4_t)__builtin_neon_vqdmullv4hi (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vqdmull_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int64x2_t)__builtin_neon_vqdmullv2si (__a, __b, 1); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vmla_s8 (int8x8_t __a, int8x8_t __b, int8x8_t __c) +{ + return (int8x8_t)__builtin_neon_vmlav8qi (__a, __b, __c, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vmla_s16 (int16x4_t __a, int16x4_t __b, int16x4_t __c) +{ + return (int16x4_t)__builtin_neon_vmlav4hi (__a, __b, __c, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vmla_s32 (int32x2_t __a, int32x2_t __b, int32x2_t __c) +{ + return (int32x2_t)__builtin_neon_vmlav2si (__a, __b, __c, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vmla_f32 (float32x2_t __a, float32x2_t __b, float32x2_t __c) +{ + return (float32x2_t)__builtin_neon_vmlav2sf (__a, __b, __c, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vmla_u8 (uint8x8_t __a, uint8x8_t __b, uint8x8_t __c) +{ + return (uint8x8_t)__builtin_neon_vmlav8qi ((int8x8_t) __a, (int8x8_t) __b, (int8x8_t) __c, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vmla_u16 (uint16x4_t __a, uint16x4_t __b, uint16x4_t __c) +{ + return (uint16x4_t)__builtin_neon_vmlav4hi ((int16x4_t) __a, (int16x4_t) __b, (int16x4_t) __c, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vmla_u32 (uint32x2_t __a, uint32x2_t __b, uint32x2_t __c) +{ + return (uint32x2_t)__builtin_neon_vmlav2si ((int32x2_t) __a, (int32x2_t) __b, (int32x2_t) __c, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vmlaq_s8 (int8x16_t __a, int8x16_t __b, int8x16_t __c) +{ + return (int8x16_t)__builtin_neon_vmlav16qi (__a, __b, __c, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmlaq_s16 (int16x8_t __a, int16x8_t __b, int16x8_t __c) +{ + return (int16x8_t)__builtin_neon_vmlav8hi (__a, __b, __c, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmlaq_s32 (int32x4_t __a, int32x4_t __b, int32x4_t __c) +{ + return (int32x4_t)__builtin_neon_vmlav4si (__a, __b, __c, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vmlaq_f32 (float32x4_t __a, float32x4_t __b, float32x4_t __c) +{ + return (float32x4_t)__builtin_neon_vmlav4sf (__a, __b, __c, 3); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vmlaq_u8 (uint8x16_t __a, uint8x16_t __b, uint8x16_t __c) +{ + return (uint8x16_t)__builtin_neon_vmlav16qi ((int8x16_t) __a, (int8x16_t) __b, (int8x16_t) __c, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmlaq_u16 (uint16x8_t __a, uint16x8_t __b, uint16x8_t __c) +{ + return (uint16x8_t)__builtin_neon_vmlav8hi ((int16x8_t) __a, (int16x8_t) __b, (int16x8_t) __c, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmlaq_u32 (uint32x4_t __a, uint32x4_t __b, uint32x4_t __c) +{ + return (uint32x4_t)__builtin_neon_vmlav4si ((int32x4_t) __a, (int32x4_t) __b, (int32x4_t) __c, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmlal_s8 (int16x8_t __a, int8x8_t __b, int8x8_t __c) +{ + return (int16x8_t)__builtin_neon_vmlalv8qi (__a, __b, __c, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmlal_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c) +{ + return (int32x4_t)__builtin_neon_vmlalv4hi (__a, __b, __c, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vmlal_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c) +{ + return (int64x2_t)__builtin_neon_vmlalv2si (__a, __b, __c, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmlal_u8 (uint16x8_t __a, uint8x8_t __b, uint8x8_t __c) +{ + return (uint16x8_t)__builtin_neon_vmlalv8qi ((int16x8_t) __a, (int8x8_t) __b, (int8x8_t) __c, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmlal_u16 (uint32x4_t __a, uint16x4_t __b, uint16x4_t __c) +{ + return (uint32x4_t)__builtin_neon_vmlalv4hi ((int32x4_t) __a, (int16x4_t) __b, (int16x4_t) __c, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vmlal_u32 (uint64x2_t __a, uint32x2_t __b, uint32x2_t __c) +{ + return (uint64x2_t)__builtin_neon_vmlalv2si ((int64x2_t) __a, (int32x2_t) __b, (int32x2_t) __c, 0); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqdmlal_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c) +{ + return (int32x4_t)__builtin_neon_vqdmlalv4hi (__a, __b, __c, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vqdmlal_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c) +{ + return (int64x2_t)__builtin_neon_vqdmlalv2si (__a, __b, __c, 1); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vmls_s8 (int8x8_t __a, int8x8_t __b, int8x8_t __c) +{ + return (int8x8_t)__builtin_neon_vmlsv8qi (__a, __b, __c, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vmls_s16 (int16x4_t __a, int16x4_t __b, int16x4_t __c) +{ + return (int16x4_t)__builtin_neon_vmlsv4hi (__a, __b, __c, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vmls_s32 (int32x2_t __a, int32x2_t __b, int32x2_t __c) +{ + return (int32x2_t)__builtin_neon_vmlsv2si (__a, __b, __c, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vmls_f32 (float32x2_t __a, float32x2_t __b, float32x2_t __c) +{ + return (float32x2_t)__builtin_neon_vmlsv2sf (__a, __b, __c, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vmls_u8 (uint8x8_t __a, uint8x8_t __b, uint8x8_t __c) +{ + return (uint8x8_t)__builtin_neon_vmlsv8qi ((int8x8_t) __a, (int8x8_t) __b, (int8x8_t) __c, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vmls_u16 (uint16x4_t __a, uint16x4_t __b, uint16x4_t __c) +{ + return (uint16x4_t)__builtin_neon_vmlsv4hi ((int16x4_t) __a, (int16x4_t) __b, (int16x4_t) __c, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vmls_u32 (uint32x2_t __a, uint32x2_t __b, uint32x2_t __c) +{ + return (uint32x2_t)__builtin_neon_vmlsv2si ((int32x2_t) __a, (int32x2_t) __b, (int32x2_t) __c, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vmlsq_s8 (int8x16_t __a, int8x16_t __b, int8x16_t __c) +{ + return (int8x16_t)__builtin_neon_vmlsv16qi (__a, __b, __c, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmlsq_s16 (int16x8_t __a, int16x8_t __b, int16x8_t __c) +{ + return (int16x8_t)__builtin_neon_vmlsv8hi (__a, __b, __c, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmlsq_s32 (int32x4_t __a, int32x4_t __b, int32x4_t __c) +{ + return (int32x4_t)__builtin_neon_vmlsv4si (__a, __b, __c, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vmlsq_f32 (float32x4_t __a, float32x4_t __b, float32x4_t __c) +{ + return (float32x4_t)__builtin_neon_vmlsv4sf (__a, __b, __c, 3); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vmlsq_u8 (uint8x16_t __a, uint8x16_t __b, uint8x16_t __c) +{ + return (uint8x16_t)__builtin_neon_vmlsv16qi ((int8x16_t) __a, (int8x16_t) __b, (int8x16_t) __c, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmlsq_u16 (uint16x8_t __a, uint16x8_t __b, uint16x8_t __c) +{ + return (uint16x8_t)__builtin_neon_vmlsv8hi ((int16x8_t) __a, (int16x8_t) __b, (int16x8_t) __c, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmlsq_u32 (uint32x4_t __a, uint32x4_t __b, uint32x4_t __c) +{ + return (uint32x4_t)__builtin_neon_vmlsv4si ((int32x4_t) __a, (int32x4_t) __b, (int32x4_t) __c, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmlsl_s8 (int16x8_t __a, int8x8_t __b, int8x8_t __c) +{ + return (int16x8_t)__builtin_neon_vmlslv8qi (__a, __b, __c, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmlsl_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c) +{ + return (int32x4_t)__builtin_neon_vmlslv4hi (__a, __b, __c, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vmlsl_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c) +{ + return (int64x2_t)__builtin_neon_vmlslv2si (__a, __b, __c, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmlsl_u8 (uint16x8_t __a, uint8x8_t __b, uint8x8_t __c) +{ + return (uint16x8_t)__builtin_neon_vmlslv8qi ((int16x8_t) __a, (int8x8_t) __b, (int8x8_t) __c, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmlsl_u16 (uint32x4_t __a, uint16x4_t __b, uint16x4_t __c) +{ + return (uint32x4_t)__builtin_neon_vmlslv4hi ((int32x4_t) __a, (int16x4_t) __b, (int16x4_t) __c, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vmlsl_u32 (uint64x2_t __a, uint32x2_t __b, uint32x2_t __c) +{ + return (uint64x2_t)__builtin_neon_vmlslv2si ((int64x2_t) __a, (int32x2_t) __b, (int32x2_t) __c, 0); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqdmlsl_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c) +{ + return (int32x4_t)__builtin_neon_vqdmlslv4hi (__a, __b, __c, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vqdmlsl_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c) +{ + return (int64x2_t)__builtin_neon_vqdmlslv2si (__a, __b, __c, 1); +} + +#ifdef __ARM_FEATURE_FMA +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vfma_f32 (float32x2_t __a, float32x2_t __b, float32x2_t __c) +{ + return (float32x2_t)__builtin_neon_vfmav2sf (__a, __b, __c, 3); +} + +#endif +#ifdef __ARM_FEATURE_FMA +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vfmaq_f32 (float32x4_t __a, float32x4_t __b, float32x4_t __c) +{ + return (float32x4_t)__builtin_neon_vfmav4sf (__a, __b, __c, 3); +} + +#endif +#ifdef __ARM_FEATURE_FMA +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vfms_f32 (float32x2_t __a, float32x2_t __b, float32x2_t __c) +{ + return (float32x2_t)__builtin_neon_vfmsv2sf (__a, __b, __c, 3); +} + +#endif +#ifdef __ARM_FEATURE_FMA +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vfmsq_f32 (float32x4_t __a, float32x4_t __b, float32x4_t __c) +{ + return (float32x4_t)__builtin_neon_vfmsv4sf (__a, __b, __c, 3); +} + +#endif +#if __ARM_ARCH >= 8 +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vrndn_f32 (float32x2_t __a) +{ + return (float32x2_t)__builtin_neon_vrintnv2sf (__a); +} + +#endif +#if __ARM_ARCH >= 8 +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vrndqn_f32 (float32x4_t __a) +{ + return (float32x4_t)__builtin_neon_vrintnv4sf (__a); +} + +#endif +#if __ARM_ARCH >= 8 +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vrnda_f32 (float32x2_t __a) +{ + return (float32x2_t)__builtin_neon_vrintav2sf (__a); +} + +#endif +#if __ARM_ARCH >= 8 +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vrndqa_f32 (float32x4_t __a) +{ + return (float32x4_t)__builtin_neon_vrintav4sf (__a); +} + +#endif +#if __ARM_ARCH >= 8 +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vrndp_f32 (float32x2_t __a) +{ + return (float32x2_t)__builtin_neon_vrintpv2sf (__a); +} + +#endif +#if __ARM_ARCH >= 8 +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vrndqp_f32 (float32x4_t __a) +{ + return (float32x4_t)__builtin_neon_vrintpv4sf (__a); +} + +#endif +#if __ARM_ARCH >= 8 +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vrndm_f32 (float32x2_t __a) +{ + return (float32x2_t)__builtin_neon_vrintmv2sf (__a); +} + +#endif +#if __ARM_ARCH >= 8 +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vrndqm_f32 (float32x4_t __a) +{ + return (float32x4_t)__builtin_neon_vrintmv4sf (__a); +} + +#endif +#if __ARM_ARCH >= 8 +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vrnd_f32 (float32x2_t __a) +{ + return (float32x2_t)__builtin_neon_vrintzv2sf (__a); +} + +#endif +#if __ARM_ARCH >= 8 +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vrndq_f32 (float32x4_t __a) +{ + return (float32x4_t)__builtin_neon_vrintzv4sf (__a); +} + +#endif +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vsub_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vsubv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vsub_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vsubv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vsub_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vsubv2si (__a, __b, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vsub_f32 (float32x2_t __a, float32x2_t __b) +{ + return (float32x2_t)__builtin_neon_vsubv2sf (__a, __b, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vsub_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vsubv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vsub_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vsubv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vsub_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vsubv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vsub_s64 (int64x1_t __a, int64x1_t __b) +{ + return (int64x1_t)__builtin_neon_vsubdi (__a, __b, 1); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vsub_u64 (uint64x1_t __a, uint64x1_t __b) +{ + return (uint64x1_t)__builtin_neon_vsubdi ((int64x1_t) __a, (int64x1_t) __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vsubq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vsubv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vsubq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vsubv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vsubq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vsubv4si (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vsubq_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int64x2_t)__builtin_neon_vsubv2di (__a, __b, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vsubq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (float32x4_t)__builtin_neon_vsubv4sf (__a, __b, 3); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vsubq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vsubv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vsubq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vsubv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsubq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vsubv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vsubq_u64 (uint64x2_t __a, uint64x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vsubv2di ((int64x2_t) __a, (int64x2_t) __b, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vsubl_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int16x8_t)__builtin_neon_vsublv8qi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vsubl_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int32x4_t)__builtin_neon_vsublv4hi (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vsubl_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int64x2_t)__builtin_neon_vsublv2si (__a, __b, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vsubl_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vsublv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsubl_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vsublv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vsubl_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vsublv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vsubw_s8 (int16x8_t __a, int8x8_t __b) +{ + return (int16x8_t)__builtin_neon_vsubwv8qi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vsubw_s16 (int32x4_t __a, int16x4_t __b) +{ + return (int32x4_t)__builtin_neon_vsubwv4hi (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vsubw_s32 (int64x2_t __a, int32x2_t __b) +{ + return (int64x2_t)__builtin_neon_vsubwv2si (__a, __b, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vsubw_u8 (uint16x8_t __a, uint8x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vsubwv8qi ((int16x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsubw_u16 (uint32x4_t __a, uint16x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vsubwv4hi ((int32x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vsubw_u32 (uint64x2_t __a, uint32x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vsubwv2si ((int64x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vhsub_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vhsubv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vhsub_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vhsubv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vhsub_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vhsubv2si (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vhsub_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vhsubv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vhsub_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vhsubv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vhsub_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vhsubv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vhsubq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vhsubv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vhsubq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vhsubv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vhsubq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vhsubv4si (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vhsubq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vhsubv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vhsubq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vhsubv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vhsubq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vhsubv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vqsub_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vqsubv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqsub_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vqsubv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqsub_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vqsubv2si (__a, __b, 1); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vqsub_s64 (int64x1_t __a, int64x1_t __b) +{ + return (int64x1_t)__builtin_neon_vqsubdi (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vqsub_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vqsubv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vqsub_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vqsubv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vqsub_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vqsubv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vqsub_u64 (uint64x1_t __a, uint64x1_t __b) +{ + return (uint64x1_t)__builtin_neon_vqsubdi ((int64x1_t) __a, (int64x1_t) __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vqsubq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vqsubv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vqsubq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vqsubv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqsubq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vqsubv4si (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vqsubq_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int64x2_t)__builtin_neon_vqsubv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vqsubq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vqsubv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vqsubq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vqsubv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vqsubq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vqsubv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vqsubq_u64 (uint64x2_t __a, uint64x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vqsubv2di ((int64x2_t) __a, (int64x2_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vsubhn_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int8x8_t)__builtin_neon_vsubhnv8hi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vsubhn_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int16x4_t)__builtin_neon_vsubhnv4si (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vsubhn_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int32x2_t)__builtin_neon_vsubhnv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vsubhn_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vsubhnv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vsubhn_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vsubhnv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vsubhn_u64 (uint64x2_t __a, uint64x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vsubhnv2di ((int64x2_t) __a, (int64x2_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vrsubhn_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int8x8_t)__builtin_neon_vsubhnv8hi (__a, __b, 5); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vrsubhn_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int16x4_t)__builtin_neon_vsubhnv4si (__a, __b, 5); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vrsubhn_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int32x2_t)__builtin_neon_vsubhnv2di (__a, __b, 5); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vrsubhn_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vsubhnv8hi ((int16x8_t) __a, (int16x8_t) __b, 4); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vrsubhn_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vsubhnv4si ((int32x4_t) __a, (int32x4_t) __b, 4); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vrsubhn_u64 (uint64x2_t __a, uint64x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vsubhnv2di ((int64x2_t) __a, (int64x2_t) __b, 4); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vceq_s8 (int8x8_t __a, int8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vceqv8qi (__a, __b, 1); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vceq_s16 (int16x4_t __a, int16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vceqv4hi (__a, __b, 1); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vceq_s32 (int32x2_t __a, int32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vceqv2si (__a, __b, 1); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vceq_f32 (float32x2_t __a, float32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vceqv2sf (__a, __b, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vceq_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vceqv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vceq_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vceqv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vceq_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vceqv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vceq_p8 (poly8x8_t __a, poly8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vceqv8qi ((int8x8_t) __a, (int8x8_t) __b, 2); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vceqq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vceqv16qi (__a, __b, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vceqq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vceqv8hi (__a, __b, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vceqq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vceqv4si (__a, __b, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vceqq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vceqv4sf (__a, __b, 3); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vceqq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vceqv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vceqq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vceqv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vceqq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vceqv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vceqq_p8 (poly8x16_t __a, poly8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vceqv16qi ((int8x16_t) __a, (int8x16_t) __b, 2); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vcge_s8 (int8x8_t __a, int8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vcgev8qi (__a, __b, 1); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vcge_s16 (int16x4_t __a, int16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vcgev4hi (__a, __b, 1); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcge_s32 (int32x2_t __a, int32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcgev2si (__a, __b, 1); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcge_f32 (float32x2_t __a, float32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcgev2sf (__a, __b, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vcge_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vcgeuv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vcge_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vcgeuv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcge_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcgeuv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vcgeq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vcgev16qi (__a, __b, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vcgeq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vcgev8hi (__a, __b, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcgeq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcgev4si (__a, __b, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcgeq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcgev4sf (__a, __b, 3); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vcgeq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vcgeuv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vcgeq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vcgeuv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcgeq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcgeuv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vcle_s8 (int8x8_t __a, int8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vcgev8qi (__b, __a, 1); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vcle_s16 (int16x4_t __a, int16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vcgev4hi (__b, __a, 1); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcle_s32 (int32x2_t __a, int32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcgev2si (__b, __a, 1); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcle_f32 (float32x2_t __a, float32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcgev2sf (__b, __a, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vcle_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vcgeuv8qi ((int8x8_t) __b, (int8x8_t) __a, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vcle_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vcgeuv4hi ((int16x4_t) __b, (int16x4_t) __a, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcle_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcgeuv2si ((int32x2_t) __b, (int32x2_t) __a, 0); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vcleq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vcgev16qi (__b, __a, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vcleq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vcgev8hi (__b, __a, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcleq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcgev4si (__b, __a, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcleq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcgev4sf (__b, __a, 3); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vcleq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vcgeuv16qi ((int8x16_t) __b, (int8x16_t) __a, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vcleq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vcgeuv8hi ((int16x8_t) __b, (int16x8_t) __a, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcleq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcgeuv4si ((int32x4_t) __b, (int32x4_t) __a, 0); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vcgt_s8 (int8x8_t __a, int8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vcgtv8qi (__a, __b, 1); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vcgt_s16 (int16x4_t __a, int16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vcgtv4hi (__a, __b, 1); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcgt_s32 (int32x2_t __a, int32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcgtv2si (__a, __b, 1); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcgt_f32 (float32x2_t __a, float32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcgtv2sf (__a, __b, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vcgt_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vcgtuv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vcgt_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vcgtuv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcgt_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcgtuv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vcgtq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vcgtv16qi (__a, __b, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vcgtq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vcgtv8hi (__a, __b, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcgtq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcgtv4si (__a, __b, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcgtq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcgtv4sf (__a, __b, 3); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vcgtq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vcgtuv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vcgtq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vcgtuv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcgtq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcgtuv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vclt_s8 (int8x8_t __a, int8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vcgtv8qi (__b, __a, 1); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vclt_s16 (int16x4_t __a, int16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vcgtv4hi (__b, __a, 1); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vclt_s32 (int32x2_t __a, int32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcgtv2si (__b, __a, 1); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vclt_f32 (float32x2_t __a, float32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcgtv2sf (__b, __a, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vclt_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vcgtuv8qi ((int8x8_t) __b, (int8x8_t) __a, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vclt_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vcgtuv4hi ((int16x4_t) __b, (int16x4_t) __a, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vclt_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcgtuv2si ((int32x2_t) __b, (int32x2_t) __a, 0); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vcltq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vcgtv16qi (__b, __a, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vcltq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vcgtv8hi (__b, __a, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcltq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcgtv4si (__b, __a, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcltq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcgtv4sf (__b, __a, 3); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vcltq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vcgtuv16qi ((int8x16_t) __b, (int8x16_t) __a, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vcltq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vcgtuv8hi ((int16x8_t) __b, (int16x8_t) __a, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcltq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcgtuv4si ((int32x4_t) __b, (int32x4_t) __a, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcage_f32 (float32x2_t __a, float32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcagev2sf (__a, __b, 3); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcageq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcagev4sf (__a, __b, 3); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcale_f32 (float32x2_t __a, float32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcagev2sf (__b, __a, 3); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcaleq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcagev4sf (__b, __a, 3); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcagt_f32 (float32x2_t __a, float32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcagtv2sf (__a, __b, 3); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcagtq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcagtv4sf (__a, __b, 3); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcalt_f32 (float32x2_t __a, float32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vcagtv2sf (__b, __a, 3); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcaltq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vcagtv4sf (__b, __a, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vtst_s8 (int8x8_t __a, int8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vtstv8qi (__a, __b, 1); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vtst_s16 (int16x4_t __a, int16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vtstv4hi (__a, __b, 1); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vtst_s32 (int32x2_t __a, int32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vtstv2si (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vtst_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vtstv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vtst_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vtstv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vtst_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vtstv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vtst_p8 (poly8x8_t __a, poly8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vtstv8qi ((int8x8_t) __a, (int8x8_t) __b, 2); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vtstq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vtstv16qi (__a, __b, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vtstq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vtstv8hi (__a, __b, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vtstq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vtstv4si (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vtstq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vtstv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vtstq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vtstv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vtstq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vtstv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vtstq_p8 (poly8x16_t __a, poly8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vtstv16qi ((int8x16_t) __a, (int8x16_t) __b, 2); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vabd_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vabdv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vabd_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vabdv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vabd_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vabdv2si (__a, __b, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vabd_f32 (float32x2_t __a, float32x2_t __b) +{ + return (float32x2_t)__builtin_neon_vabdv2sf (__a, __b, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vabd_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vabdv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vabd_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vabdv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vabd_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vabdv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vabdq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vabdv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vabdq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vabdv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vabdq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vabdv4si (__a, __b, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vabdq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (float32x4_t)__builtin_neon_vabdv4sf (__a, __b, 3); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vabdq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vabdv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vabdq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vabdv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vabdq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vabdv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vabdl_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int16x8_t)__builtin_neon_vabdlv8qi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vabdl_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int32x4_t)__builtin_neon_vabdlv4hi (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vabdl_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int64x2_t)__builtin_neon_vabdlv2si (__a, __b, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vabdl_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vabdlv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vabdl_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vabdlv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vabdl_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vabdlv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vaba_s8 (int8x8_t __a, int8x8_t __b, int8x8_t __c) +{ + return (int8x8_t)__builtin_neon_vabav8qi (__a, __b, __c, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vaba_s16 (int16x4_t __a, int16x4_t __b, int16x4_t __c) +{ + return (int16x4_t)__builtin_neon_vabav4hi (__a, __b, __c, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vaba_s32 (int32x2_t __a, int32x2_t __b, int32x2_t __c) +{ + return (int32x2_t)__builtin_neon_vabav2si (__a, __b, __c, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vaba_u8 (uint8x8_t __a, uint8x8_t __b, uint8x8_t __c) +{ + return (uint8x8_t)__builtin_neon_vabav8qi ((int8x8_t) __a, (int8x8_t) __b, (int8x8_t) __c, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vaba_u16 (uint16x4_t __a, uint16x4_t __b, uint16x4_t __c) +{ + return (uint16x4_t)__builtin_neon_vabav4hi ((int16x4_t) __a, (int16x4_t) __b, (int16x4_t) __c, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vaba_u32 (uint32x2_t __a, uint32x2_t __b, uint32x2_t __c) +{ + return (uint32x2_t)__builtin_neon_vabav2si ((int32x2_t) __a, (int32x2_t) __b, (int32x2_t) __c, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vabaq_s8 (int8x16_t __a, int8x16_t __b, int8x16_t __c) +{ + return (int8x16_t)__builtin_neon_vabav16qi (__a, __b, __c, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vabaq_s16 (int16x8_t __a, int16x8_t __b, int16x8_t __c) +{ + return (int16x8_t)__builtin_neon_vabav8hi (__a, __b, __c, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vabaq_s32 (int32x4_t __a, int32x4_t __b, int32x4_t __c) +{ + return (int32x4_t)__builtin_neon_vabav4si (__a, __b, __c, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vabaq_u8 (uint8x16_t __a, uint8x16_t __b, uint8x16_t __c) +{ + return (uint8x16_t)__builtin_neon_vabav16qi ((int8x16_t) __a, (int8x16_t) __b, (int8x16_t) __c, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vabaq_u16 (uint16x8_t __a, uint16x8_t __b, uint16x8_t __c) +{ + return (uint16x8_t)__builtin_neon_vabav8hi ((int16x8_t) __a, (int16x8_t) __b, (int16x8_t) __c, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vabaq_u32 (uint32x4_t __a, uint32x4_t __b, uint32x4_t __c) +{ + return (uint32x4_t)__builtin_neon_vabav4si ((int32x4_t) __a, (int32x4_t) __b, (int32x4_t) __c, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vabal_s8 (int16x8_t __a, int8x8_t __b, int8x8_t __c) +{ + return (int16x8_t)__builtin_neon_vabalv8qi (__a, __b, __c, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vabal_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c) +{ + return (int32x4_t)__builtin_neon_vabalv4hi (__a, __b, __c, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vabal_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c) +{ + return (int64x2_t)__builtin_neon_vabalv2si (__a, __b, __c, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vabal_u8 (uint16x8_t __a, uint8x8_t __b, uint8x8_t __c) +{ + return (uint16x8_t)__builtin_neon_vabalv8qi ((int16x8_t) __a, (int8x8_t) __b, (int8x8_t) __c, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vabal_u16 (uint32x4_t __a, uint16x4_t __b, uint16x4_t __c) +{ + return (uint32x4_t)__builtin_neon_vabalv4hi ((int32x4_t) __a, (int16x4_t) __b, (int16x4_t) __c, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vabal_u32 (uint64x2_t __a, uint32x2_t __b, uint32x2_t __c) +{ + return (uint64x2_t)__builtin_neon_vabalv2si ((int64x2_t) __a, (int32x2_t) __b, (int32x2_t) __c, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vmax_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vmaxv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vmax_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vmaxv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vmax_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vmaxv2si (__a, __b, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vmax_f32 (float32x2_t __a, float32x2_t __b) +{ + return (float32x2_t)__builtin_neon_vmaxv2sf (__a, __b, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vmax_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vmaxv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vmax_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vmaxv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vmax_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vmaxv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vmaxq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vmaxv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmaxq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vmaxv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmaxq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vmaxv4si (__a, __b, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vmaxq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (float32x4_t)__builtin_neon_vmaxv4sf (__a, __b, 3); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vmaxq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vmaxv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmaxq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vmaxv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmaxq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vmaxv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vmin_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vminv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vmin_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vminv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vmin_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vminv2si (__a, __b, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vmin_f32 (float32x2_t __a, float32x2_t __b) +{ + return (float32x2_t)__builtin_neon_vminv2sf (__a, __b, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vmin_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vminv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vmin_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vminv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vmin_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vminv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vminq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vminv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vminq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vminv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vminq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vminv4si (__a, __b, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vminq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (float32x4_t)__builtin_neon_vminv4sf (__a, __b, 3); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vminq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vminv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vminq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vminv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vminq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vminv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vpadd_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vpaddv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vpadd_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vpaddv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vpadd_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vpaddv2si (__a, __b, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vpadd_f32 (float32x2_t __a, float32x2_t __b) +{ + return (float32x2_t)__builtin_neon_vpaddv2sf (__a, __b, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vpadd_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vpaddv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vpadd_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vpaddv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vpadd_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vpaddv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vpaddl_s8 (int8x8_t __a) +{ + return (int16x4_t)__builtin_neon_vpaddlv8qi (__a, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vpaddl_s16 (int16x4_t __a) +{ + return (int32x2_t)__builtin_neon_vpaddlv4hi (__a, 1); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vpaddl_s32 (int32x2_t __a) +{ + return (int64x1_t)__builtin_neon_vpaddlv2si (__a, 1); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vpaddl_u8 (uint8x8_t __a) +{ + return (uint16x4_t)__builtin_neon_vpaddlv8qi ((int8x8_t) __a, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vpaddl_u16 (uint16x4_t __a) +{ + return (uint32x2_t)__builtin_neon_vpaddlv4hi ((int16x4_t) __a, 0); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vpaddl_u32 (uint32x2_t __a) +{ + return (uint64x1_t)__builtin_neon_vpaddlv2si ((int32x2_t) __a, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vpaddlq_s8 (int8x16_t __a) +{ + return (int16x8_t)__builtin_neon_vpaddlv16qi (__a, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vpaddlq_s16 (int16x8_t __a) +{ + return (int32x4_t)__builtin_neon_vpaddlv8hi (__a, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vpaddlq_s32 (int32x4_t __a) +{ + return (int64x2_t)__builtin_neon_vpaddlv4si (__a, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vpaddlq_u8 (uint8x16_t __a) +{ + return (uint16x8_t)__builtin_neon_vpaddlv16qi ((int8x16_t) __a, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vpaddlq_u16 (uint16x8_t __a) +{ + return (uint32x4_t)__builtin_neon_vpaddlv8hi ((int16x8_t) __a, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vpaddlq_u32 (uint32x4_t __a) +{ + return (uint64x2_t)__builtin_neon_vpaddlv4si ((int32x4_t) __a, 0); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vpadal_s8 (int16x4_t __a, int8x8_t __b) +{ + return (int16x4_t)__builtin_neon_vpadalv8qi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vpadal_s16 (int32x2_t __a, int16x4_t __b) +{ + return (int32x2_t)__builtin_neon_vpadalv4hi (__a, __b, 1); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vpadal_s32 (int64x1_t __a, int32x2_t __b) +{ + return (int64x1_t)__builtin_neon_vpadalv2si (__a, __b, 1); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vpadal_u8 (uint16x4_t __a, uint8x8_t __b) +{ + return (uint16x4_t)__builtin_neon_vpadalv8qi ((int16x4_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vpadal_u16 (uint32x2_t __a, uint16x4_t __b) +{ + return (uint32x2_t)__builtin_neon_vpadalv4hi ((int32x2_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vpadal_u32 (uint64x1_t __a, uint32x2_t __b) +{ + return (uint64x1_t)__builtin_neon_vpadalv2si ((int64x1_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vpadalq_s8 (int16x8_t __a, int8x16_t __b) +{ + return (int16x8_t)__builtin_neon_vpadalv16qi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vpadalq_s16 (int32x4_t __a, int16x8_t __b) +{ + return (int32x4_t)__builtin_neon_vpadalv8hi (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vpadalq_s32 (int64x2_t __a, int32x4_t __b) +{ + return (int64x2_t)__builtin_neon_vpadalv4si (__a, __b, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vpadalq_u8 (uint16x8_t __a, uint8x16_t __b) +{ + return (uint16x8_t)__builtin_neon_vpadalv16qi ((int16x8_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vpadalq_u16 (uint32x4_t __a, uint16x8_t __b) +{ + return (uint32x4_t)__builtin_neon_vpadalv8hi ((int32x4_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vpadalq_u32 (uint64x2_t __a, uint32x4_t __b) +{ + return (uint64x2_t)__builtin_neon_vpadalv4si ((int64x2_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vpmax_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vpmaxv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vpmax_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vpmaxv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vpmax_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vpmaxv2si (__a, __b, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vpmax_f32 (float32x2_t __a, float32x2_t __b) +{ + return (float32x2_t)__builtin_neon_vpmaxv2sf (__a, __b, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vpmax_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vpmaxv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vpmax_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vpmaxv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vpmax_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vpmaxv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vpmin_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vpminv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vpmin_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vpminv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vpmin_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vpminv2si (__a, __b, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vpmin_f32 (float32x2_t __a, float32x2_t __b) +{ + return (float32x2_t)__builtin_neon_vpminv2sf (__a, __b, 3); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vpmin_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vpminv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vpmin_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vpminv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vpmin_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vpminv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vrecps_f32 (float32x2_t __a, float32x2_t __b) +{ + return (float32x2_t)__builtin_neon_vrecpsv2sf (__a, __b, 3); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vrecpsq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (float32x4_t)__builtin_neon_vrecpsv4sf (__a, __b, 3); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vrsqrts_f32 (float32x2_t __a, float32x2_t __b) +{ + return (float32x2_t)__builtin_neon_vrsqrtsv2sf (__a, __b, 3); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vrsqrtsq_f32 (float32x4_t __a, float32x4_t __b) +{ + return (float32x4_t)__builtin_neon_vrsqrtsv4sf (__a, __b, 3); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vshl_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vshlv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vshl_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vshlv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vshl_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vshlv2si (__a, __b, 1); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vshl_s64 (int64x1_t __a, int64x1_t __b) +{ + return (int64x1_t)__builtin_neon_vshldi (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vshl_u8 (uint8x8_t __a, int8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vshlv8qi ((int8x8_t) __a, __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vshl_u16 (uint16x4_t __a, int16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vshlv4hi ((int16x4_t) __a, __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vshl_u32 (uint32x2_t __a, int32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vshlv2si ((int32x2_t) __a, __b, 0); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vshl_u64 (uint64x1_t __a, int64x1_t __b) +{ + return (uint64x1_t)__builtin_neon_vshldi ((int64x1_t) __a, __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vshlq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vshlv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vshlq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vshlv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vshlq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vshlv4si (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vshlq_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int64x2_t)__builtin_neon_vshlv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vshlq_u8 (uint8x16_t __a, int8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vshlv16qi ((int8x16_t) __a, __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vshlq_u16 (uint16x8_t __a, int16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vshlv8hi ((int16x8_t) __a, __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vshlq_u32 (uint32x4_t __a, int32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vshlv4si ((int32x4_t) __a, __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vshlq_u64 (uint64x2_t __a, int64x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vshlv2di ((int64x2_t) __a, __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vrshl_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vshlv8qi (__a, __b, 5); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vrshl_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vshlv4hi (__a, __b, 5); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vrshl_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vshlv2si (__a, __b, 5); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vrshl_s64 (int64x1_t __a, int64x1_t __b) +{ + return (int64x1_t)__builtin_neon_vshldi (__a, __b, 5); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vrshl_u8 (uint8x8_t __a, int8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vshlv8qi ((int8x8_t) __a, __b, 4); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vrshl_u16 (uint16x4_t __a, int16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vshlv4hi ((int16x4_t) __a, __b, 4); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vrshl_u32 (uint32x2_t __a, int32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vshlv2si ((int32x2_t) __a, __b, 4); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vrshl_u64 (uint64x1_t __a, int64x1_t __b) +{ + return (uint64x1_t)__builtin_neon_vshldi ((int64x1_t) __a, __b, 4); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vrshlq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vshlv16qi (__a, __b, 5); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vrshlq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vshlv8hi (__a, __b, 5); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vrshlq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vshlv4si (__a, __b, 5); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vrshlq_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int64x2_t)__builtin_neon_vshlv2di (__a, __b, 5); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vrshlq_u8 (uint8x16_t __a, int8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vshlv16qi ((int8x16_t) __a, __b, 4); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vrshlq_u16 (uint16x8_t __a, int16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vshlv8hi ((int16x8_t) __a, __b, 4); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vrshlq_u32 (uint32x4_t __a, int32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vshlv4si ((int32x4_t) __a, __b, 4); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vrshlq_u64 (uint64x2_t __a, int64x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vshlv2di ((int64x2_t) __a, __b, 4); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vqshl_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vqshlv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqshl_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vqshlv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqshl_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vqshlv2si (__a, __b, 1); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vqshl_s64 (int64x1_t __a, int64x1_t __b) +{ + return (int64x1_t)__builtin_neon_vqshldi (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vqshl_u8 (uint8x8_t __a, int8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vqshlv8qi ((int8x8_t) __a, __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vqshl_u16 (uint16x4_t __a, int16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vqshlv4hi ((int16x4_t) __a, __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vqshl_u32 (uint32x2_t __a, int32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vqshlv2si ((int32x2_t) __a, __b, 0); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vqshl_u64 (uint64x1_t __a, int64x1_t __b) +{ + return (uint64x1_t)__builtin_neon_vqshldi ((int64x1_t) __a, __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vqshlq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vqshlv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vqshlq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vqshlv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqshlq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vqshlv4si (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vqshlq_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int64x2_t)__builtin_neon_vqshlv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vqshlq_u8 (uint8x16_t __a, int8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vqshlv16qi ((int8x16_t) __a, __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vqshlq_u16 (uint16x8_t __a, int16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vqshlv8hi ((int16x8_t) __a, __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vqshlq_u32 (uint32x4_t __a, int32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vqshlv4si ((int32x4_t) __a, __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vqshlq_u64 (uint64x2_t __a, int64x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vqshlv2di ((int64x2_t) __a, __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vqrshl_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vqshlv8qi (__a, __b, 5); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqrshl_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vqshlv4hi (__a, __b, 5); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqrshl_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vqshlv2si (__a, __b, 5); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vqrshl_s64 (int64x1_t __a, int64x1_t __b) +{ + return (int64x1_t)__builtin_neon_vqshldi (__a, __b, 5); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vqrshl_u8 (uint8x8_t __a, int8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vqshlv8qi ((int8x8_t) __a, __b, 4); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vqrshl_u16 (uint16x4_t __a, int16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vqshlv4hi ((int16x4_t) __a, __b, 4); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vqrshl_u32 (uint32x2_t __a, int32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vqshlv2si ((int32x2_t) __a, __b, 4); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vqrshl_u64 (uint64x1_t __a, int64x1_t __b) +{ + return (uint64x1_t)__builtin_neon_vqshldi ((int64x1_t) __a, __b, 4); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vqrshlq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vqshlv16qi (__a, __b, 5); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vqrshlq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vqshlv8hi (__a, __b, 5); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqrshlq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vqshlv4si (__a, __b, 5); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vqrshlq_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int64x2_t)__builtin_neon_vqshlv2di (__a, __b, 5); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vqrshlq_u8 (uint8x16_t __a, int8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vqshlv16qi ((int8x16_t) __a, __b, 4); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vqrshlq_u16 (uint16x8_t __a, int16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vqshlv8hi ((int16x8_t) __a, __b, 4); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vqrshlq_u32 (uint32x4_t __a, int32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vqshlv4si ((int32x4_t) __a, __b, 4); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vqrshlq_u64 (uint64x2_t __a, int64x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vqshlv2di ((int64x2_t) __a, __b, 4); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vshr_n_s8 (int8x8_t __a, const int __b) +{ + return (int8x8_t)__builtin_neon_vshr_nv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vshr_n_s16 (int16x4_t __a, const int __b) +{ + return (int16x4_t)__builtin_neon_vshr_nv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vshr_n_s32 (int32x2_t __a, const int __b) +{ + return (int32x2_t)__builtin_neon_vshr_nv2si (__a, __b, 1); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vshr_n_s64 (int64x1_t __a, const int __b) +{ + return (int64x1_t)__builtin_neon_vshr_ndi (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vshr_n_u8 (uint8x8_t __a, const int __b) +{ + return (uint8x8_t)__builtin_neon_vshr_nv8qi ((int8x8_t) __a, __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vshr_n_u16 (uint16x4_t __a, const int __b) +{ + return (uint16x4_t)__builtin_neon_vshr_nv4hi ((int16x4_t) __a, __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vshr_n_u32 (uint32x2_t __a, const int __b) +{ + return (uint32x2_t)__builtin_neon_vshr_nv2si ((int32x2_t) __a, __b, 0); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vshr_n_u64 (uint64x1_t __a, const int __b) +{ + return (uint64x1_t)__builtin_neon_vshr_ndi ((int64x1_t) __a, __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vshrq_n_s8 (int8x16_t __a, const int __b) +{ + return (int8x16_t)__builtin_neon_vshr_nv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vshrq_n_s16 (int16x8_t __a, const int __b) +{ + return (int16x8_t)__builtin_neon_vshr_nv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vshrq_n_s32 (int32x4_t __a, const int __b) +{ + return (int32x4_t)__builtin_neon_vshr_nv4si (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vshrq_n_s64 (int64x2_t __a, const int __b) +{ + return (int64x2_t)__builtin_neon_vshr_nv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vshrq_n_u8 (uint8x16_t __a, const int __b) +{ + return (uint8x16_t)__builtin_neon_vshr_nv16qi ((int8x16_t) __a, __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vshrq_n_u16 (uint16x8_t __a, const int __b) +{ + return (uint16x8_t)__builtin_neon_vshr_nv8hi ((int16x8_t) __a, __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vshrq_n_u32 (uint32x4_t __a, const int __b) +{ + return (uint32x4_t)__builtin_neon_vshr_nv4si ((int32x4_t) __a, __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vshrq_n_u64 (uint64x2_t __a, const int __b) +{ + return (uint64x2_t)__builtin_neon_vshr_nv2di ((int64x2_t) __a, __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vrshr_n_s8 (int8x8_t __a, const int __b) +{ + return (int8x8_t)__builtin_neon_vshr_nv8qi (__a, __b, 5); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vrshr_n_s16 (int16x4_t __a, const int __b) +{ + return (int16x4_t)__builtin_neon_vshr_nv4hi (__a, __b, 5); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vrshr_n_s32 (int32x2_t __a, const int __b) +{ + return (int32x2_t)__builtin_neon_vshr_nv2si (__a, __b, 5); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vrshr_n_s64 (int64x1_t __a, const int __b) +{ + return (int64x1_t)__builtin_neon_vshr_ndi (__a, __b, 5); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vrshr_n_u8 (uint8x8_t __a, const int __b) +{ + return (uint8x8_t)__builtin_neon_vshr_nv8qi ((int8x8_t) __a, __b, 4); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vrshr_n_u16 (uint16x4_t __a, const int __b) +{ + return (uint16x4_t)__builtin_neon_vshr_nv4hi ((int16x4_t) __a, __b, 4); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vrshr_n_u32 (uint32x2_t __a, const int __b) +{ + return (uint32x2_t)__builtin_neon_vshr_nv2si ((int32x2_t) __a, __b, 4); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vrshr_n_u64 (uint64x1_t __a, const int __b) +{ + return (uint64x1_t)__builtin_neon_vshr_ndi ((int64x1_t) __a, __b, 4); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vrshrq_n_s8 (int8x16_t __a, const int __b) +{ + return (int8x16_t)__builtin_neon_vshr_nv16qi (__a, __b, 5); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vrshrq_n_s16 (int16x8_t __a, const int __b) +{ + return (int16x8_t)__builtin_neon_vshr_nv8hi (__a, __b, 5); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vrshrq_n_s32 (int32x4_t __a, const int __b) +{ + return (int32x4_t)__builtin_neon_vshr_nv4si (__a, __b, 5); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vrshrq_n_s64 (int64x2_t __a, const int __b) +{ + return (int64x2_t)__builtin_neon_vshr_nv2di (__a, __b, 5); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vrshrq_n_u8 (uint8x16_t __a, const int __b) +{ + return (uint8x16_t)__builtin_neon_vshr_nv16qi ((int8x16_t) __a, __b, 4); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vrshrq_n_u16 (uint16x8_t __a, const int __b) +{ + return (uint16x8_t)__builtin_neon_vshr_nv8hi ((int16x8_t) __a, __b, 4); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vrshrq_n_u32 (uint32x4_t __a, const int __b) +{ + return (uint32x4_t)__builtin_neon_vshr_nv4si ((int32x4_t) __a, __b, 4); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vrshrq_n_u64 (uint64x2_t __a, const int __b) +{ + return (uint64x2_t)__builtin_neon_vshr_nv2di ((int64x2_t) __a, __b, 4); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vshrn_n_s16 (int16x8_t __a, const int __b) +{ + return (int8x8_t)__builtin_neon_vshrn_nv8hi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vshrn_n_s32 (int32x4_t __a, const int __b) +{ + return (int16x4_t)__builtin_neon_vshrn_nv4si (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vshrn_n_s64 (int64x2_t __a, const int __b) +{ + return (int32x2_t)__builtin_neon_vshrn_nv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vshrn_n_u16 (uint16x8_t __a, const int __b) +{ + return (uint8x8_t)__builtin_neon_vshrn_nv8hi ((int16x8_t) __a, __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vshrn_n_u32 (uint32x4_t __a, const int __b) +{ + return (uint16x4_t)__builtin_neon_vshrn_nv4si ((int32x4_t) __a, __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vshrn_n_u64 (uint64x2_t __a, const int __b) +{ + return (uint32x2_t)__builtin_neon_vshrn_nv2di ((int64x2_t) __a, __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vrshrn_n_s16 (int16x8_t __a, const int __b) +{ + return (int8x8_t)__builtin_neon_vshrn_nv8hi (__a, __b, 5); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vrshrn_n_s32 (int32x4_t __a, const int __b) +{ + return (int16x4_t)__builtin_neon_vshrn_nv4si (__a, __b, 5); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vrshrn_n_s64 (int64x2_t __a, const int __b) +{ + return (int32x2_t)__builtin_neon_vshrn_nv2di (__a, __b, 5); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vrshrn_n_u16 (uint16x8_t __a, const int __b) +{ + return (uint8x8_t)__builtin_neon_vshrn_nv8hi ((int16x8_t) __a, __b, 4); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vrshrn_n_u32 (uint32x4_t __a, const int __b) +{ + return (uint16x4_t)__builtin_neon_vshrn_nv4si ((int32x4_t) __a, __b, 4); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vrshrn_n_u64 (uint64x2_t __a, const int __b) +{ + return (uint32x2_t)__builtin_neon_vshrn_nv2di ((int64x2_t) __a, __b, 4); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vqshrn_n_s16 (int16x8_t __a, const int __b) +{ + return (int8x8_t)__builtin_neon_vqshrn_nv8hi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqshrn_n_s32 (int32x4_t __a, const int __b) +{ + return (int16x4_t)__builtin_neon_vqshrn_nv4si (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqshrn_n_s64 (int64x2_t __a, const int __b) +{ + return (int32x2_t)__builtin_neon_vqshrn_nv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vqshrn_n_u16 (uint16x8_t __a, const int __b) +{ + return (uint8x8_t)__builtin_neon_vqshrn_nv8hi ((int16x8_t) __a, __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vqshrn_n_u32 (uint32x4_t __a, const int __b) +{ + return (uint16x4_t)__builtin_neon_vqshrn_nv4si ((int32x4_t) __a, __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vqshrn_n_u64 (uint64x2_t __a, const int __b) +{ + return (uint32x2_t)__builtin_neon_vqshrn_nv2di ((int64x2_t) __a, __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vqrshrn_n_s16 (int16x8_t __a, const int __b) +{ + return (int8x8_t)__builtin_neon_vqshrn_nv8hi (__a, __b, 5); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqrshrn_n_s32 (int32x4_t __a, const int __b) +{ + return (int16x4_t)__builtin_neon_vqshrn_nv4si (__a, __b, 5); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqrshrn_n_s64 (int64x2_t __a, const int __b) +{ + return (int32x2_t)__builtin_neon_vqshrn_nv2di (__a, __b, 5); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vqrshrn_n_u16 (uint16x8_t __a, const int __b) +{ + return (uint8x8_t)__builtin_neon_vqshrn_nv8hi ((int16x8_t) __a, __b, 4); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vqrshrn_n_u32 (uint32x4_t __a, const int __b) +{ + return (uint16x4_t)__builtin_neon_vqshrn_nv4si ((int32x4_t) __a, __b, 4); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vqrshrn_n_u64 (uint64x2_t __a, const int __b) +{ + return (uint32x2_t)__builtin_neon_vqshrn_nv2di ((int64x2_t) __a, __b, 4); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vqshrun_n_s16 (int16x8_t __a, const int __b) +{ + return (uint8x8_t)__builtin_neon_vqshrun_nv8hi (__a, __b, 1); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vqshrun_n_s32 (int32x4_t __a, const int __b) +{ + return (uint16x4_t)__builtin_neon_vqshrun_nv4si (__a, __b, 1); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vqshrun_n_s64 (int64x2_t __a, const int __b) +{ + return (uint32x2_t)__builtin_neon_vqshrun_nv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vqrshrun_n_s16 (int16x8_t __a, const int __b) +{ + return (uint8x8_t)__builtin_neon_vqshrun_nv8hi (__a, __b, 5); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vqrshrun_n_s32 (int32x4_t __a, const int __b) +{ + return (uint16x4_t)__builtin_neon_vqshrun_nv4si (__a, __b, 5); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vqrshrun_n_s64 (int64x2_t __a, const int __b) +{ + return (uint32x2_t)__builtin_neon_vqshrun_nv2di (__a, __b, 5); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vshl_n_s8 (int8x8_t __a, const int __b) +{ + return (int8x8_t)__builtin_neon_vshl_nv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vshl_n_s16 (int16x4_t __a, const int __b) +{ + return (int16x4_t)__builtin_neon_vshl_nv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vshl_n_s32 (int32x2_t __a, const int __b) +{ + return (int32x2_t)__builtin_neon_vshl_nv2si (__a, __b, 1); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vshl_n_s64 (int64x1_t __a, const int __b) +{ + return (int64x1_t)__builtin_neon_vshl_ndi (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vshl_n_u8 (uint8x8_t __a, const int __b) +{ + return (uint8x8_t)__builtin_neon_vshl_nv8qi ((int8x8_t) __a, __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vshl_n_u16 (uint16x4_t __a, const int __b) +{ + return (uint16x4_t)__builtin_neon_vshl_nv4hi ((int16x4_t) __a, __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vshl_n_u32 (uint32x2_t __a, const int __b) +{ + return (uint32x2_t)__builtin_neon_vshl_nv2si ((int32x2_t) __a, __b, 0); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vshl_n_u64 (uint64x1_t __a, const int __b) +{ + return (uint64x1_t)__builtin_neon_vshl_ndi ((int64x1_t) __a, __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vshlq_n_s8 (int8x16_t __a, const int __b) +{ + return (int8x16_t)__builtin_neon_vshl_nv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vshlq_n_s16 (int16x8_t __a, const int __b) +{ + return (int16x8_t)__builtin_neon_vshl_nv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vshlq_n_s32 (int32x4_t __a, const int __b) +{ + return (int32x4_t)__builtin_neon_vshl_nv4si (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vshlq_n_s64 (int64x2_t __a, const int __b) +{ + return (int64x2_t)__builtin_neon_vshl_nv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vshlq_n_u8 (uint8x16_t __a, const int __b) +{ + return (uint8x16_t)__builtin_neon_vshl_nv16qi ((int8x16_t) __a, __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vshlq_n_u16 (uint16x8_t __a, const int __b) +{ + return (uint16x8_t)__builtin_neon_vshl_nv8hi ((int16x8_t) __a, __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vshlq_n_u32 (uint32x4_t __a, const int __b) +{ + return (uint32x4_t)__builtin_neon_vshl_nv4si ((int32x4_t) __a, __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vshlq_n_u64 (uint64x2_t __a, const int __b) +{ + return (uint64x2_t)__builtin_neon_vshl_nv2di ((int64x2_t) __a, __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vqshl_n_s8 (int8x8_t __a, const int __b) +{ + return (int8x8_t)__builtin_neon_vqshl_nv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqshl_n_s16 (int16x4_t __a, const int __b) +{ + return (int16x4_t)__builtin_neon_vqshl_nv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqshl_n_s32 (int32x2_t __a, const int __b) +{ + return (int32x2_t)__builtin_neon_vqshl_nv2si (__a, __b, 1); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vqshl_n_s64 (int64x1_t __a, const int __b) +{ + return (int64x1_t)__builtin_neon_vqshl_ndi (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vqshl_n_u8 (uint8x8_t __a, const int __b) +{ + return (uint8x8_t)__builtin_neon_vqshl_nv8qi ((int8x8_t) __a, __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vqshl_n_u16 (uint16x4_t __a, const int __b) +{ + return (uint16x4_t)__builtin_neon_vqshl_nv4hi ((int16x4_t) __a, __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vqshl_n_u32 (uint32x2_t __a, const int __b) +{ + return (uint32x2_t)__builtin_neon_vqshl_nv2si ((int32x2_t) __a, __b, 0); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vqshl_n_u64 (uint64x1_t __a, const int __b) +{ + return (uint64x1_t)__builtin_neon_vqshl_ndi ((int64x1_t) __a, __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vqshlq_n_s8 (int8x16_t __a, const int __b) +{ + return (int8x16_t)__builtin_neon_vqshl_nv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vqshlq_n_s16 (int16x8_t __a, const int __b) +{ + return (int16x8_t)__builtin_neon_vqshl_nv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqshlq_n_s32 (int32x4_t __a, const int __b) +{ + return (int32x4_t)__builtin_neon_vqshl_nv4si (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vqshlq_n_s64 (int64x2_t __a, const int __b) +{ + return (int64x2_t)__builtin_neon_vqshl_nv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vqshlq_n_u8 (uint8x16_t __a, const int __b) +{ + return (uint8x16_t)__builtin_neon_vqshl_nv16qi ((int8x16_t) __a, __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vqshlq_n_u16 (uint16x8_t __a, const int __b) +{ + return (uint16x8_t)__builtin_neon_vqshl_nv8hi ((int16x8_t) __a, __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vqshlq_n_u32 (uint32x4_t __a, const int __b) +{ + return (uint32x4_t)__builtin_neon_vqshl_nv4si ((int32x4_t) __a, __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vqshlq_n_u64 (uint64x2_t __a, const int __b) +{ + return (uint64x2_t)__builtin_neon_vqshl_nv2di ((int64x2_t) __a, __b, 0); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vqshlu_n_s8 (int8x8_t __a, const int __b) +{ + return (uint8x8_t)__builtin_neon_vqshlu_nv8qi (__a, __b, 1); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vqshlu_n_s16 (int16x4_t __a, const int __b) +{ + return (uint16x4_t)__builtin_neon_vqshlu_nv4hi (__a, __b, 1); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vqshlu_n_s32 (int32x2_t __a, const int __b) +{ + return (uint32x2_t)__builtin_neon_vqshlu_nv2si (__a, __b, 1); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vqshlu_n_s64 (int64x1_t __a, const int __b) +{ + return (uint64x1_t)__builtin_neon_vqshlu_ndi (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vqshluq_n_s8 (int8x16_t __a, const int __b) +{ + return (uint8x16_t)__builtin_neon_vqshlu_nv16qi (__a, __b, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vqshluq_n_s16 (int16x8_t __a, const int __b) +{ + return (uint16x8_t)__builtin_neon_vqshlu_nv8hi (__a, __b, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vqshluq_n_s32 (int32x4_t __a, const int __b) +{ + return (uint32x4_t)__builtin_neon_vqshlu_nv4si (__a, __b, 1); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vqshluq_n_s64 (int64x2_t __a, const int __b) +{ + return (uint64x2_t)__builtin_neon_vqshlu_nv2di (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vshll_n_s8 (int8x8_t __a, const int __b) +{ + return (int16x8_t)__builtin_neon_vshll_nv8qi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vshll_n_s16 (int16x4_t __a, const int __b) +{ + return (int32x4_t)__builtin_neon_vshll_nv4hi (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vshll_n_s32 (int32x2_t __a, const int __b) +{ + return (int64x2_t)__builtin_neon_vshll_nv2si (__a, __b, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vshll_n_u8 (uint8x8_t __a, const int __b) +{ + return (uint16x8_t)__builtin_neon_vshll_nv8qi ((int8x8_t) __a, __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vshll_n_u16 (uint16x4_t __a, const int __b) +{ + return (uint32x4_t)__builtin_neon_vshll_nv4hi ((int16x4_t) __a, __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vshll_n_u32 (uint32x2_t __a, const int __b) +{ + return (uint64x2_t)__builtin_neon_vshll_nv2si ((int32x2_t) __a, __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vsra_n_s8 (int8x8_t __a, int8x8_t __b, const int __c) +{ + return (int8x8_t)__builtin_neon_vsra_nv8qi (__a, __b, __c, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vsra_n_s16 (int16x4_t __a, int16x4_t __b, const int __c) +{ + return (int16x4_t)__builtin_neon_vsra_nv4hi (__a, __b, __c, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vsra_n_s32 (int32x2_t __a, int32x2_t __b, const int __c) +{ + return (int32x2_t)__builtin_neon_vsra_nv2si (__a, __b, __c, 1); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vsra_n_s64 (int64x1_t __a, int64x1_t __b, const int __c) +{ + return (int64x1_t)__builtin_neon_vsra_ndi (__a, __b, __c, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vsra_n_u8 (uint8x8_t __a, uint8x8_t __b, const int __c) +{ + return (uint8x8_t)__builtin_neon_vsra_nv8qi ((int8x8_t) __a, (int8x8_t) __b, __c, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vsra_n_u16 (uint16x4_t __a, uint16x4_t __b, const int __c) +{ + return (uint16x4_t)__builtin_neon_vsra_nv4hi ((int16x4_t) __a, (int16x4_t) __b, __c, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vsra_n_u32 (uint32x2_t __a, uint32x2_t __b, const int __c) +{ + return (uint32x2_t)__builtin_neon_vsra_nv2si ((int32x2_t) __a, (int32x2_t) __b, __c, 0); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vsra_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c) +{ + return (uint64x1_t)__builtin_neon_vsra_ndi ((int64x1_t) __a, (int64x1_t) __b, __c, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vsraq_n_s8 (int8x16_t __a, int8x16_t __b, const int __c) +{ + return (int8x16_t)__builtin_neon_vsra_nv16qi (__a, __b, __c, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vsraq_n_s16 (int16x8_t __a, int16x8_t __b, const int __c) +{ + return (int16x8_t)__builtin_neon_vsra_nv8hi (__a, __b, __c, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vsraq_n_s32 (int32x4_t __a, int32x4_t __b, const int __c) +{ + return (int32x4_t)__builtin_neon_vsra_nv4si (__a, __b, __c, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vsraq_n_s64 (int64x2_t __a, int64x2_t __b, const int __c) +{ + return (int64x2_t)__builtin_neon_vsra_nv2di (__a, __b, __c, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vsraq_n_u8 (uint8x16_t __a, uint8x16_t __b, const int __c) +{ + return (uint8x16_t)__builtin_neon_vsra_nv16qi ((int8x16_t) __a, (int8x16_t) __b, __c, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vsraq_n_u16 (uint16x8_t __a, uint16x8_t __b, const int __c) +{ + return (uint16x8_t)__builtin_neon_vsra_nv8hi ((int16x8_t) __a, (int16x8_t) __b, __c, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsraq_n_u32 (uint32x4_t __a, uint32x4_t __b, const int __c) +{ + return (uint32x4_t)__builtin_neon_vsra_nv4si ((int32x4_t) __a, (int32x4_t) __b, __c, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vsraq_n_u64 (uint64x2_t __a, uint64x2_t __b, const int __c) +{ + return (uint64x2_t)__builtin_neon_vsra_nv2di ((int64x2_t) __a, (int64x2_t) __b, __c, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vrsra_n_s8 (int8x8_t __a, int8x8_t __b, const int __c) +{ + return (int8x8_t)__builtin_neon_vsra_nv8qi (__a, __b, __c, 5); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vrsra_n_s16 (int16x4_t __a, int16x4_t __b, const int __c) +{ + return (int16x4_t)__builtin_neon_vsra_nv4hi (__a, __b, __c, 5); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vrsra_n_s32 (int32x2_t __a, int32x2_t __b, const int __c) +{ + return (int32x2_t)__builtin_neon_vsra_nv2si (__a, __b, __c, 5); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vrsra_n_s64 (int64x1_t __a, int64x1_t __b, const int __c) +{ + return (int64x1_t)__builtin_neon_vsra_ndi (__a, __b, __c, 5); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vrsra_n_u8 (uint8x8_t __a, uint8x8_t __b, const int __c) +{ + return (uint8x8_t)__builtin_neon_vsra_nv8qi ((int8x8_t) __a, (int8x8_t) __b, __c, 4); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vrsra_n_u16 (uint16x4_t __a, uint16x4_t __b, const int __c) +{ + return (uint16x4_t)__builtin_neon_vsra_nv4hi ((int16x4_t) __a, (int16x4_t) __b, __c, 4); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vrsra_n_u32 (uint32x2_t __a, uint32x2_t __b, const int __c) +{ + return (uint32x2_t)__builtin_neon_vsra_nv2si ((int32x2_t) __a, (int32x2_t) __b, __c, 4); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vrsra_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c) +{ + return (uint64x1_t)__builtin_neon_vsra_ndi ((int64x1_t) __a, (int64x1_t) __b, __c, 4); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vrsraq_n_s8 (int8x16_t __a, int8x16_t __b, const int __c) +{ + return (int8x16_t)__builtin_neon_vsra_nv16qi (__a, __b, __c, 5); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vrsraq_n_s16 (int16x8_t __a, int16x8_t __b, const int __c) +{ + return (int16x8_t)__builtin_neon_vsra_nv8hi (__a, __b, __c, 5); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vrsraq_n_s32 (int32x4_t __a, int32x4_t __b, const int __c) +{ + return (int32x4_t)__builtin_neon_vsra_nv4si (__a, __b, __c, 5); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vrsraq_n_s64 (int64x2_t __a, int64x2_t __b, const int __c) +{ + return (int64x2_t)__builtin_neon_vsra_nv2di (__a, __b, __c, 5); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vrsraq_n_u8 (uint8x16_t __a, uint8x16_t __b, const int __c) +{ + return (uint8x16_t)__builtin_neon_vsra_nv16qi ((int8x16_t) __a, (int8x16_t) __b, __c, 4); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vrsraq_n_u16 (uint16x8_t __a, uint16x8_t __b, const int __c) +{ + return (uint16x8_t)__builtin_neon_vsra_nv8hi ((int16x8_t) __a, (int16x8_t) __b, __c, 4); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vrsraq_n_u32 (uint32x4_t __a, uint32x4_t __b, const int __c) +{ + return (uint32x4_t)__builtin_neon_vsra_nv4si ((int32x4_t) __a, (int32x4_t) __b, __c, 4); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vrsraq_n_u64 (uint64x2_t __a, uint64x2_t __b, const int __c) +{ + return (uint64x2_t)__builtin_neon_vsra_nv2di ((int64x2_t) __a, (int64x2_t) __b, __c, 4); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vsri_n_p64 (poly64x1_t __a, poly64x1_t __b, const int __c) +{ + return (poly64x1_t)__builtin_neon_vsri_ndi (__a, __b, __c); +} + +#endif +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vsri_n_s8 (int8x8_t __a, int8x8_t __b, const int __c) +{ + return (int8x8_t)__builtin_neon_vsri_nv8qi (__a, __b, __c); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vsri_n_s16 (int16x4_t __a, int16x4_t __b, const int __c) +{ + return (int16x4_t)__builtin_neon_vsri_nv4hi (__a, __b, __c); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vsri_n_s32 (int32x2_t __a, int32x2_t __b, const int __c) +{ + return (int32x2_t)__builtin_neon_vsri_nv2si (__a, __b, __c); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vsri_n_s64 (int64x1_t __a, int64x1_t __b, const int __c) +{ + return (int64x1_t)__builtin_neon_vsri_ndi (__a, __b, __c); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vsri_n_u8 (uint8x8_t __a, uint8x8_t __b, const int __c) +{ + return (uint8x8_t)__builtin_neon_vsri_nv8qi ((int8x8_t) __a, (int8x8_t) __b, __c); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vsri_n_u16 (uint16x4_t __a, uint16x4_t __b, const int __c) +{ + return (uint16x4_t)__builtin_neon_vsri_nv4hi ((int16x4_t) __a, (int16x4_t) __b, __c); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vsri_n_u32 (uint32x2_t __a, uint32x2_t __b, const int __c) +{ + return (uint32x2_t)__builtin_neon_vsri_nv2si ((int32x2_t) __a, (int32x2_t) __b, __c); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vsri_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c) +{ + return (uint64x1_t)__builtin_neon_vsri_ndi ((int64x1_t) __a, (int64x1_t) __b, __c); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vsri_n_p8 (poly8x8_t __a, poly8x8_t __b, const int __c) +{ + return (poly8x8_t)__builtin_neon_vsri_nv8qi ((int8x8_t) __a, (int8x8_t) __b, __c); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vsri_n_p16 (poly16x4_t __a, poly16x4_t __b, const int __c) +{ + return (poly16x4_t)__builtin_neon_vsri_nv4hi ((int16x4_t) __a, (int16x4_t) __b, __c); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vsriq_n_p64 (poly64x2_t __a, poly64x2_t __b, const int __c) +{ + return (poly64x2_t)__builtin_neon_vsri_nv2di ((int64x2_t) __a, (int64x2_t) __b, __c); +} + +#endif +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vsriq_n_s8 (int8x16_t __a, int8x16_t __b, const int __c) +{ + return (int8x16_t)__builtin_neon_vsri_nv16qi (__a, __b, __c); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vsriq_n_s16 (int16x8_t __a, int16x8_t __b, const int __c) +{ + return (int16x8_t)__builtin_neon_vsri_nv8hi (__a, __b, __c); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vsriq_n_s32 (int32x4_t __a, int32x4_t __b, const int __c) +{ + return (int32x4_t)__builtin_neon_vsri_nv4si (__a, __b, __c); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vsriq_n_s64 (int64x2_t __a, int64x2_t __b, const int __c) +{ + return (int64x2_t)__builtin_neon_vsri_nv2di (__a, __b, __c); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vsriq_n_u8 (uint8x16_t __a, uint8x16_t __b, const int __c) +{ + return (uint8x16_t)__builtin_neon_vsri_nv16qi ((int8x16_t) __a, (int8x16_t) __b, __c); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vsriq_n_u16 (uint16x8_t __a, uint16x8_t __b, const int __c) +{ + return (uint16x8_t)__builtin_neon_vsri_nv8hi ((int16x8_t) __a, (int16x8_t) __b, __c); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsriq_n_u32 (uint32x4_t __a, uint32x4_t __b, const int __c) +{ + return (uint32x4_t)__builtin_neon_vsri_nv4si ((int32x4_t) __a, (int32x4_t) __b, __c); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vsriq_n_u64 (uint64x2_t __a, uint64x2_t __b, const int __c) +{ + return (uint64x2_t)__builtin_neon_vsri_nv2di ((int64x2_t) __a, (int64x2_t) __b, __c); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vsriq_n_p8 (poly8x16_t __a, poly8x16_t __b, const int __c) +{ + return (poly8x16_t)__builtin_neon_vsri_nv16qi ((int8x16_t) __a, (int8x16_t) __b, __c); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vsriq_n_p16 (poly16x8_t __a, poly16x8_t __b, const int __c) +{ + return (poly16x8_t)__builtin_neon_vsri_nv8hi ((int16x8_t) __a, (int16x8_t) __b, __c); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vsli_n_p64 (poly64x1_t __a, poly64x1_t __b, const int __c) +{ + return (poly64x1_t)__builtin_neon_vsli_ndi (__a, __b, __c); +} + +#endif +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vsli_n_s8 (int8x8_t __a, int8x8_t __b, const int __c) +{ + return (int8x8_t)__builtin_neon_vsli_nv8qi (__a, __b, __c); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vsli_n_s16 (int16x4_t __a, int16x4_t __b, const int __c) +{ + return (int16x4_t)__builtin_neon_vsli_nv4hi (__a, __b, __c); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vsli_n_s32 (int32x2_t __a, int32x2_t __b, const int __c) +{ + return (int32x2_t)__builtin_neon_vsli_nv2si (__a, __b, __c); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vsli_n_s64 (int64x1_t __a, int64x1_t __b, const int __c) +{ + return (int64x1_t)__builtin_neon_vsli_ndi (__a, __b, __c); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vsli_n_u8 (uint8x8_t __a, uint8x8_t __b, const int __c) +{ + return (uint8x8_t)__builtin_neon_vsli_nv8qi ((int8x8_t) __a, (int8x8_t) __b, __c); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vsli_n_u16 (uint16x4_t __a, uint16x4_t __b, const int __c) +{ + return (uint16x4_t)__builtin_neon_vsli_nv4hi ((int16x4_t) __a, (int16x4_t) __b, __c); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vsli_n_u32 (uint32x2_t __a, uint32x2_t __b, const int __c) +{ + return (uint32x2_t)__builtin_neon_vsli_nv2si ((int32x2_t) __a, (int32x2_t) __b, __c); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vsli_n_u64 (uint64x1_t __a, uint64x1_t __b, const int __c) +{ + return (uint64x1_t)__builtin_neon_vsli_ndi ((int64x1_t) __a, (int64x1_t) __b, __c); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vsli_n_p8 (poly8x8_t __a, poly8x8_t __b, const int __c) +{ + return (poly8x8_t)__builtin_neon_vsli_nv8qi ((int8x8_t) __a, (int8x8_t) __b, __c); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vsli_n_p16 (poly16x4_t __a, poly16x4_t __b, const int __c) +{ + return (poly16x4_t)__builtin_neon_vsli_nv4hi ((int16x4_t) __a, (int16x4_t) __b, __c); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vsliq_n_p64 (poly64x2_t __a, poly64x2_t __b, const int __c) +{ + return (poly64x2_t)__builtin_neon_vsli_nv2di ((int64x2_t) __a, (int64x2_t) __b, __c); +} + +#endif +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vsliq_n_s8 (int8x16_t __a, int8x16_t __b, const int __c) +{ + return (int8x16_t)__builtin_neon_vsli_nv16qi (__a, __b, __c); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vsliq_n_s16 (int16x8_t __a, int16x8_t __b, const int __c) +{ + return (int16x8_t)__builtin_neon_vsli_nv8hi (__a, __b, __c); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vsliq_n_s32 (int32x4_t __a, int32x4_t __b, const int __c) +{ + return (int32x4_t)__builtin_neon_vsli_nv4si (__a, __b, __c); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vsliq_n_s64 (int64x2_t __a, int64x2_t __b, const int __c) +{ + return (int64x2_t)__builtin_neon_vsli_nv2di (__a, __b, __c); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vsliq_n_u8 (uint8x16_t __a, uint8x16_t __b, const int __c) +{ + return (uint8x16_t)__builtin_neon_vsli_nv16qi ((int8x16_t) __a, (int8x16_t) __b, __c); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vsliq_n_u16 (uint16x8_t __a, uint16x8_t __b, const int __c) +{ + return (uint16x8_t)__builtin_neon_vsli_nv8hi ((int16x8_t) __a, (int16x8_t) __b, __c); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsliq_n_u32 (uint32x4_t __a, uint32x4_t __b, const int __c) +{ + return (uint32x4_t)__builtin_neon_vsli_nv4si ((int32x4_t) __a, (int32x4_t) __b, __c); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vsliq_n_u64 (uint64x2_t __a, uint64x2_t __b, const int __c) +{ + return (uint64x2_t)__builtin_neon_vsli_nv2di ((int64x2_t) __a, (int64x2_t) __b, __c); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vsliq_n_p8 (poly8x16_t __a, poly8x16_t __b, const int __c) +{ + return (poly8x16_t)__builtin_neon_vsli_nv16qi ((int8x16_t) __a, (int8x16_t) __b, __c); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vsliq_n_p16 (poly16x8_t __a, poly16x8_t __b, const int __c) +{ + return (poly16x8_t)__builtin_neon_vsli_nv8hi ((int16x8_t) __a, (int16x8_t) __b, __c); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vabs_s8 (int8x8_t __a) +{ + return (int8x8_t)__builtin_neon_vabsv8qi (__a, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vabs_s16 (int16x4_t __a) +{ + return (int16x4_t)__builtin_neon_vabsv4hi (__a, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vabs_s32 (int32x2_t __a) +{ + return (int32x2_t)__builtin_neon_vabsv2si (__a, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vabs_f32 (float32x2_t __a) +{ + return (float32x2_t)__builtin_neon_vabsv2sf (__a, 3); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vabsq_s8 (int8x16_t __a) +{ + return (int8x16_t)__builtin_neon_vabsv16qi (__a, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vabsq_s16 (int16x8_t __a) +{ + return (int16x8_t)__builtin_neon_vabsv8hi (__a, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vabsq_s32 (int32x4_t __a) +{ + return (int32x4_t)__builtin_neon_vabsv4si (__a, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vabsq_f32 (float32x4_t __a) +{ + return (float32x4_t)__builtin_neon_vabsv4sf (__a, 3); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vqabs_s8 (int8x8_t __a) +{ + return (int8x8_t)__builtin_neon_vqabsv8qi (__a, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqabs_s16 (int16x4_t __a) +{ + return (int16x4_t)__builtin_neon_vqabsv4hi (__a, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqabs_s32 (int32x2_t __a) +{ + return (int32x2_t)__builtin_neon_vqabsv2si (__a, 1); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vqabsq_s8 (int8x16_t __a) +{ + return (int8x16_t)__builtin_neon_vqabsv16qi (__a, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vqabsq_s16 (int16x8_t __a) +{ + return (int16x8_t)__builtin_neon_vqabsv8hi (__a, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqabsq_s32 (int32x4_t __a) +{ + return (int32x4_t)__builtin_neon_vqabsv4si (__a, 1); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vneg_s8 (int8x8_t __a) +{ + return (int8x8_t)__builtin_neon_vnegv8qi (__a, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vneg_s16 (int16x4_t __a) +{ + return (int16x4_t)__builtin_neon_vnegv4hi (__a, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vneg_s32 (int32x2_t __a) +{ + return (int32x2_t)__builtin_neon_vnegv2si (__a, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vneg_f32 (float32x2_t __a) +{ + return (float32x2_t)__builtin_neon_vnegv2sf (__a, 3); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vnegq_s8 (int8x16_t __a) +{ + return (int8x16_t)__builtin_neon_vnegv16qi (__a, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vnegq_s16 (int16x8_t __a) +{ + return (int16x8_t)__builtin_neon_vnegv8hi (__a, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vnegq_s32 (int32x4_t __a) +{ + return (int32x4_t)__builtin_neon_vnegv4si (__a, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vnegq_f32 (float32x4_t __a) +{ + return (float32x4_t)__builtin_neon_vnegv4sf (__a, 3); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vqneg_s8 (int8x8_t __a) +{ + return (int8x8_t)__builtin_neon_vqnegv8qi (__a, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqneg_s16 (int16x4_t __a) +{ + return (int16x4_t)__builtin_neon_vqnegv4hi (__a, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqneg_s32 (int32x2_t __a) +{ + return (int32x2_t)__builtin_neon_vqnegv2si (__a, 1); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vqnegq_s8 (int8x16_t __a) +{ + return (int8x16_t)__builtin_neon_vqnegv16qi (__a, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vqnegq_s16 (int16x8_t __a) +{ + return (int16x8_t)__builtin_neon_vqnegv8hi (__a, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqnegq_s32 (int32x4_t __a) +{ + return (int32x4_t)__builtin_neon_vqnegv4si (__a, 1); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vmvn_s8 (int8x8_t __a) +{ + return (int8x8_t)__builtin_neon_vmvnv8qi (__a, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vmvn_s16 (int16x4_t __a) +{ + return (int16x4_t)__builtin_neon_vmvnv4hi (__a, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vmvn_s32 (int32x2_t __a) +{ + return (int32x2_t)__builtin_neon_vmvnv2si (__a, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vmvn_u8 (uint8x8_t __a) +{ + return (uint8x8_t)__builtin_neon_vmvnv8qi ((int8x8_t) __a, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vmvn_u16 (uint16x4_t __a) +{ + return (uint16x4_t)__builtin_neon_vmvnv4hi ((int16x4_t) __a, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vmvn_u32 (uint32x2_t __a) +{ + return (uint32x2_t)__builtin_neon_vmvnv2si ((int32x2_t) __a, 0); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vmvn_p8 (poly8x8_t __a) +{ + return (poly8x8_t)__builtin_neon_vmvnv8qi ((int8x8_t) __a, 2); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vmvnq_s8 (int8x16_t __a) +{ + return (int8x16_t)__builtin_neon_vmvnv16qi (__a, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmvnq_s16 (int16x8_t __a) +{ + return (int16x8_t)__builtin_neon_vmvnv8hi (__a, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmvnq_s32 (int32x4_t __a) +{ + return (int32x4_t)__builtin_neon_vmvnv4si (__a, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vmvnq_u8 (uint8x16_t __a) +{ + return (uint8x16_t)__builtin_neon_vmvnv16qi ((int8x16_t) __a, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmvnq_u16 (uint16x8_t __a) +{ + return (uint16x8_t)__builtin_neon_vmvnv8hi ((int16x8_t) __a, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmvnq_u32 (uint32x4_t __a) +{ + return (uint32x4_t)__builtin_neon_vmvnv4si ((int32x4_t) __a, 0); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vmvnq_p8 (poly8x16_t __a) +{ + return (poly8x16_t)__builtin_neon_vmvnv16qi ((int8x16_t) __a, 2); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vcls_s8 (int8x8_t __a) +{ + return (int8x8_t)__builtin_neon_vclsv8qi (__a, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vcls_s16 (int16x4_t __a) +{ + return (int16x4_t)__builtin_neon_vclsv4hi (__a, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vcls_s32 (int32x2_t __a) +{ + return (int32x2_t)__builtin_neon_vclsv2si (__a, 1); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vclsq_s8 (int8x16_t __a) +{ + return (int8x16_t)__builtin_neon_vclsv16qi (__a, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vclsq_s16 (int16x8_t __a) +{ + return (int16x8_t)__builtin_neon_vclsv8hi (__a, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vclsq_s32 (int32x4_t __a) +{ + return (int32x4_t)__builtin_neon_vclsv4si (__a, 1); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vclz_s8 (int8x8_t __a) +{ + return (int8x8_t)__builtin_neon_vclzv8qi (__a, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vclz_s16 (int16x4_t __a) +{ + return (int16x4_t)__builtin_neon_vclzv4hi (__a, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vclz_s32 (int32x2_t __a) +{ + return (int32x2_t)__builtin_neon_vclzv2si (__a, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vclz_u8 (uint8x8_t __a) +{ + return (uint8x8_t)__builtin_neon_vclzv8qi ((int8x8_t) __a, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vclz_u16 (uint16x4_t __a) +{ + return (uint16x4_t)__builtin_neon_vclzv4hi ((int16x4_t) __a, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vclz_u32 (uint32x2_t __a) +{ + return (uint32x2_t)__builtin_neon_vclzv2si ((int32x2_t) __a, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vclzq_s8 (int8x16_t __a) +{ + return (int8x16_t)__builtin_neon_vclzv16qi (__a, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vclzq_s16 (int16x8_t __a) +{ + return (int16x8_t)__builtin_neon_vclzv8hi (__a, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vclzq_s32 (int32x4_t __a) +{ + return (int32x4_t)__builtin_neon_vclzv4si (__a, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vclzq_u8 (uint8x16_t __a) +{ + return (uint8x16_t)__builtin_neon_vclzv16qi ((int8x16_t) __a, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vclzq_u16 (uint16x8_t __a) +{ + return (uint16x8_t)__builtin_neon_vclzv8hi ((int16x8_t) __a, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vclzq_u32 (uint32x4_t __a) +{ + return (uint32x4_t)__builtin_neon_vclzv4si ((int32x4_t) __a, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vcnt_s8 (int8x8_t __a) +{ + return (int8x8_t)__builtin_neon_vcntv8qi (__a, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vcnt_u8 (uint8x8_t __a) +{ + return (uint8x8_t)__builtin_neon_vcntv8qi ((int8x8_t) __a, 0); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vcnt_p8 (poly8x8_t __a) +{ + return (poly8x8_t)__builtin_neon_vcntv8qi ((int8x8_t) __a, 2); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vcntq_s8 (int8x16_t __a) +{ + return (int8x16_t)__builtin_neon_vcntv16qi (__a, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vcntq_u8 (uint8x16_t __a) +{ + return (uint8x16_t)__builtin_neon_vcntv16qi ((int8x16_t) __a, 0); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vcntq_p8 (poly8x16_t __a) +{ + return (poly8x16_t)__builtin_neon_vcntv16qi ((int8x16_t) __a, 2); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vrecpe_f32 (float32x2_t __a) +{ + return (float32x2_t)__builtin_neon_vrecpev2sf (__a, 3); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vrecpe_u32 (uint32x2_t __a) +{ + return (uint32x2_t)__builtin_neon_vrecpev2si ((int32x2_t) __a, 0); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vrecpeq_f32 (float32x4_t __a) +{ + return (float32x4_t)__builtin_neon_vrecpev4sf (__a, 3); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vrecpeq_u32 (uint32x4_t __a) +{ + return (uint32x4_t)__builtin_neon_vrecpev4si ((int32x4_t) __a, 0); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vrsqrte_f32 (float32x2_t __a) +{ + return (float32x2_t)__builtin_neon_vrsqrtev2sf (__a, 3); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vrsqrte_u32 (uint32x2_t __a) +{ + return (uint32x2_t)__builtin_neon_vrsqrtev2si ((int32x2_t) __a, 0); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vrsqrteq_f32 (float32x4_t __a) +{ + return (float32x4_t)__builtin_neon_vrsqrtev4sf (__a, 3); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vrsqrteq_u32 (uint32x4_t __a) +{ + return (uint32x4_t)__builtin_neon_vrsqrtev4si ((int32x4_t) __a, 0); +} + +__extension__ static __inline int8_t __attribute__ ((__always_inline__)) +vget_lane_s8 (int8x8_t __a, const int __b) +{ + return (int8_t)__builtin_neon_vget_lanev8qi (__a, __b, 1); +} + +__extension__ static __inline int16_t __attribute__ ((__always_inline__)) +vget_lane_s16 (int16x4_t __a, const int __b) +{ + return (int16_t)__builtin_neon_vget_lanev4hi (__a, __b, 1); +} + +__extension__ static __inline int32_t __attribute__ ((__always_inline__)) +vget_lane_s32 (int32x2_t __a, const int __b) +{ + return (int32_t)__builtin_neon_vget_lanev2si (__a, __b, 1); +} + +__extension__ static __inline float32_t __attribute__ ((__always_inline__)) +vget_lane_f32 (float32x2_t __a, const int __b) +{ + return (float32_t)__builtin_neon_vget_lanev2sf (__a, __b, 3); +} + +__extension__ static __inline uint8_t __attribute__ ((__always_inline__)) +vget_lane_u8 (uint8x8_t __a, const int __b) +{ + return (uint8_t)__builtin_neon_vget_lanev8qi ((int8x8_t) __a, __b, 0); +} + +__extension__ static __inline uint16_t __attribute__ ((__always_inline__)) +vget_lane_u16 (uint16x4_t __a, const int __b) +{ + return (uint16_t)__builtin_neon_vget_lanev4hi ((int16x4_t) __a, __b, 0); +} + +__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) +vget_lane_u32 (uint32x2_t __a, const int __b) +{ + return (uint32_t)__builtin_neon_vget_lanev2si ((int32x2_t) __a, __b, 0); +} + +__extension__ static __inline poly8_t __attribute__ ((__always_inline__)) +vget_lane_p8 (poly8x8_t __a, const int __b) +{ + return (poly8_t)__builtin_neon_vget_lanev8qi ((int8x8_t) __a, __b, 2); +} + +__extension__ static __inline poly16_t __attribute__ ((__always_inline__)) +vget_lane_p16 (poly16x4_t __a, const int __b) +{ + return (poly16_t)__builtin_neon_vget_lanev4hi ((int16x4_t) __a, __b, 2); +} + +__extension__ static __inline int64_t __attribute__ ((__always_inline__)) +vget_lane_s64 (int64x1_t __a, const int __b) +{ + return (int64_t)__builtin_neon_vget_lanedi (__a, __b, 1); +} + +__extension__ static __inline uint64_t __attribute__ ((__always_inline__)) +vget_lane_u64 (uint64x1_t __a, const int __b) +{ + return (uint64_t)__builtin_neon_vget_lanedi ((int64x1_t) __a, __b, 0); +} + +__extension__ static __inline int8_t __attribute__ ((__always_inline__)) +vgetq_lane_s8 (int8x16_t __a, const int __b) +{ + return (int8_t)__builtin_neon_vget_lanev16qi (__a, __b, 1); +} + +__extension__ static __inline int16_t __attribute__ ((__always_inline__)) +vgetq_lane_s16 (int16x8_t __a, const int __b) +{ + return (int16_t)__builtin_neon_vget_lanev8hi (__a, __b, 1); +} + +__extension__ static __inline int32_t __attribute__ ((__always_inline__)) +vgetq_lane_s32 (int32x4_t __a, const int __b) +{ + return (int32_t)__builtin_neon_vget_lanev4si (__a, __b, 1); +} + +__extension__ static __inline float32_t __attribute__ ((__always_inline__)) +vgetq_lane_f32 (float32x4_t __a, const int __b) +{ + return (float32_t)__builtin_neon_vget_lanev4sf (__a, __b, 3); +} + +__extension__ static __inline uint8_t __attribute__ ((__always_inline__)) +vgetq_lane_u8 (uint8x16_t __a, const int __b) +{ + return (uint8_t)__builtin_neon_vget_lanev16qi ((int8x16_t) __a, __b, 0); +} + +__extension__ static __inline uint16_t __attribute__ ((__always_inline__)) +vgetq_lane_u16 (uint16x8_t __a, const int __b) +{ + return (uint16_t)__builtin_neon_vget_lanev8hi ((int16x8_t) __a, __b, 0); +} + +__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) +vgetq_lane_u32 (uint32x4_t __a, const int __b) +{ + return (uint32_t)__builtin_neon_vget_lanev4si ((int32x4_t) __a, __b, 0); +} + +__extension__ static __inline poly8_t __attribute__ ((__always_inline__)) +vgetq_lane_p8 (poly8x16_t __a, const int __b) +{ + return (poly8_t)__builtin_neon_vget_lanev16qi ((int8x16_t) __a, __b, 2); +} + +__extension__ static __inline poly16_t __attribute__ ((__always_inline__)) +vgetq_lane_p16 (poly16x8_t __a, const int __b) +{ + return (poly16_t)__builtin_neon_vget_lanev8hi ((int16x8_t) __a, __b, 2); +} + +__extension__ static __inline int64_t __attribute__ ((__always_inline__)) +vgetq_lane_s64 (int64x2_t __a, const int __b) +{ + return (int64_t)__builtin_neon_vget_lanev2di (__a, __b, 1); +} + +__extension__ static __inline uint64_t __attribute__ ((__always_inline__)) +vgetq_lane_u64 (uint64x2_t __a, const int __b) +{ + return (uint64_t)__builtin_neon_vget_lanev2di ((int64x2_t) __a, __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vset_lane_s8 (int8_t __a, int8x8_t __b, const int __c) +{ + return (int8x8_t)__builtin_neon_vset_lanev8qi ((__builtin_neon_qi) __a, __b, __c); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vset_lane_s16 (int16_t __a, int16x4_t __b, const int __c) +{ + return (int16x4_t)__builtin_neon_vset_lanev4hi ((__builtin_neon_hi) __a, __b, __c); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vset_lane_s32 (int32_t __a, int32x2_t __b, const int __c) +{ + return (int32x2_t)__builtin_neon_vset_lanev2si ((__builtin_neon_si) __a, __b, __c); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vset_lane_f32 (float32_t __a, float32x2_t __b, const int __c) +{ + return (float32x2_t)__builtin_neon_vset_lanev2sf ((__builtin_neon_sf) __a, __b, __c); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vset_lane_u8 (uint8_t __a, uint8x8_t __b, const int __c) +{ + return (uint8x8_t)__builtin_neon_vset_lanev8qi ((__builtin_neon_qi) __a, (int8x8_t) __b, __c); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vset_lane_u16 (uint16_t __a, uint16x4_t __b, const int __c) +{ + return (uint16x4_t)__builtin_neon_vset_lanev4hi ((__builtin_neon_hi) __a, (int16x4_t) __b, __c); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vset_lane_u32 (uint32_t __a, uint32x2_t __b, const int __c) +{ + return (uint32x2_t)__builtin_neon_vset_lanev2si ((__builtin_neon_si) __a, (int32x2_t) __b, __c); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vset_lane_p8 (poly8_t __a, poly8x8_t __b, const int __c) +{ + return (poly8x8_t)__builtin_neon_vset_lanev8qi ((__builtin_neon_qi) __a, (int8x8_t) __b, __c); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vset_lane_p16 (poly16_t __a, poly16x4_t __b, const int __c) +{ + return (poly16x4_t)__builtin_neon_vset_lanev4hi ((__builtin_neon_hi) __a, (int16x4_t) __b, __c); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vset_lane_s64 (int64_t __a, int64x1_t __b, const int __c) +{ + return (int64x1_t)__builtin_neon_vset_lanedi ((__builtin_neon_di) __a, __b, __c); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vset_lane_u64 (uint64_t __a, uint64x1_t __b, const int __c) +{ + return (uint64x1_t)__builtin_neon_vset_lanedi ((__builtin_neon_di) __a, (int64x1_t) __b, __c); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vsetq_lane_s8 (int8_t __a, int8x16_t __b, const int __c) +{ + return (int8x16_t)__builtin_neon_vset_lanev16qi ((__builtin_neon_qi) __a, __b, __c); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vsetq_lane_s16 (int16_t __a, int16x8_t __b, const int __c) +{ + return (int16x8_t)__builtin_neon_vset_lanev8hi ((__builtin_neon_hi) __a, __b, __c); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vsetq_lane_s32 (int32_t __a, int32x4_t __b, const int __c) +{ + return (int32x4_t)__builtin_neon_vset_lanev4si ((__builtin_neon_si) __a, __b, __c); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vsetq_lane_f32 (float32_t __a, float32x4_t __b, const int __c) +{ + return (float32x4_t)__builtin_neon_vset_lanev4sf ((__builtin_neon_sf) __a, __b, __c); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vsetq_lane_u8 (uint8_t __a, uint8x16_t __b, const int __c) +{ + return (uint8x16_t)__builtin_neon_vset_lanev16qi ((__builtin_neon_qi) __a, (int8x16_t) __b, __c); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vsetq_lane_u16 (uint16_t __a, uint16x8_t __b, const int __c) +{ + return (uint16x8_t)__builtin_neon_vset_lanev8hi ((__builtin_neon_hi) __a, (int16x8_t) __b, __c); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsetq_lane_u32 (uint32_t __a, uint32x4_t __b, const int __c) +{ + return (uint32x4_t)__builtin_neon_vset_lanev4si ((__builtin_neon_si) __a, (int32x4_t) __b, __c); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vsetq_lane_p8 (poly8_t __a, poly8x16_t __b, const int __c) +{ + return (poly8x16_t)__builtin_neon_vset_lanev16qi ((__builtin_neon_qi) __a, (int8x16_t) __b, __c); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vsetq_lane_p16 (poly16_t __a, poly16x8_t __b, const int __c) +{ + return (poly16x8_t)__builtin_neon_vset_lanev8hi ((__builtin_neon_hi) __a, (int16x8_t) __b, __c); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vsetq_lane_s64 (int64_t __a, int64x2_t __b, const int __c) +{ + return (int64x2_t)__builtin_neon_vset_lanev2di ((__builtin_neon_di) __a, __b, __c); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vsetq_lane_u64 (uint64_t __a, uint64x2_t __b, const int __c) +{ + return (uint64x2_t)__builtin_neon_vset_lanev2di ((__builtin_neon_di) __a, (int64x2_t) __b, __c); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vcreate_p64 (uint64_t __a) +{ + return (poly64x1_t)__builtin_neon_vcreatedi ((__builtin_neon_di) __a); +} + +#endif +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vcreate_s8 (uint64_t __a) +{ + return (int8x8_t)__builtin_neon_vcreatev8qi ((__builtin_neon_di) __a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vcreate_s16 (uint64_t __a) +{ + return (int16x4_t)__builtin_neon_vcreatev4hi ((__builtin_neon_di) __a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vcreate_s32 (uint64_t __a) +{ + return (int32x2_t)__builtin_neon_vcreatev2si ((__builtin_neon_di) __a); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vcreate_s64 (uint64_t __a) +{ + return (int64x1_t)__builtin_neon_vcreatedi ((__builtin_neon_di) __a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vcreate_f32 (uint64_t __a) +{ + return (float32x2_t)__builtin_neon_vcreatev2sf ((__builtin_neon_di) __a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vcreate_u8 (uint64_t __a) +{ + return (uint8x8_t)__builtin_neon_vcreatev8qi ((__builtin_neon_di) __a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vcreate_u16 (uint64_t __a) +{ + return (uint16x4_t)__builtin_neon_vcreatev4hi ((__builtin_neon_di) __a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcreate_u32 (uint64_t __a) +{ + return (uint32x2_t)__builtin_neon_vcreatev2si ((__builtin_neon_di) __a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vcreate_u64 (uint64_t __a) +{ + return (uint64x1_t)__builtin_neon_vcreatedi ((__builtin_neon_di) __a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vcreate_p8 (uint64_t __a) +{ + return (poly8x8_t)__builtin_neon_vcreatev8qi ((__builtin_neon_di) __a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vcreate_p16 (uint64_t __a) +{ + return (poly16x4_t)__builtin_neon_vcreatev4hi ((__builtin_neon_di) __a); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vdup_n_s8 (int8_t __a) +{ + return (int8x8_t)__builtin_neon_vdup_nv8qi ((__builtin_neon_qi) __a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vdup_n_s16 (int16_t __a) +{ + return (int16x4_t)__builtin_neon_vdup_nv4hi ((__builtin_neon_hi) __a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vdup_n_s32 (int32_t __a) +{ + return (int32x2_t)__builtin_neon_vdup_nv2si ((__builtin_neon_si) __a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vdup_n_f32 (float32_t __a) +{ + return (float32x2_t)__builtin_neon_vdup_nv2sf ((__builtin_neon_sf) __a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vdup_n_u8 (uint8_t __a) +{ + return (uint8x8_t)__builtin_neon_vdup_nv8qi ((__builtin_neon_qi) __a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vdup_n_u16 (uint16_t __a) +{ + return (uint16x4_t)__builtin_neon_vdup_nv4hi ((__builtin_neon_hi) __a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vdup_n_u32 (uint32_t __a) +{ + return (uint32x2_t)__builtin_neon_vdup_nv2si ((__builtin_neon_si) __a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vdup_n_p8 (poly8_t __a) +{ + return (poly8x8_t)__builtin_neon_vdup_nv8qi ((__builtin_neon_qi) __a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vdup_n_p16 (poly16_t __a) +{ + return (poly16x4_t)__builtin_neon_vdup_nv4hi ((__builtin_neon_hi) __a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vdup_n_p64 (poly64_t __a) +{ + return (poly64x1_t)__builtin_neon_vdup_ndi ((__builtin_neon_di) __a); +} + +#endif +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vdup_n_s64 (int64_t __a) +{ + return (int64x1_t)__builtin_neon_vdup_ndi ((__builtin_neon_di) __a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vdup_n_u64 (uint64_t __a) +{ + return (uint64x1_t)__builtin_neon_vdup_ndi ((__builtin_neon_di) __a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vdupq_n_p64 (poly64_t __a) +{ + return (poly64x2_t)__builtin_neon_vdup_nv2di ((__builtin_neon_di) __a); +} + +#endif +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vdupq_n_s8 (int8_t __a) +{ + return (int8x16_t)__builtin_neon_vdup_nv16qi ((__builtin_neon_qi) __a); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vdupq_n_s16 (int16_t __a) +{ + return (int16x8_t)__builtin_neon_vdup_nv8hi ((__builtin_neon_hi) __a); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vdupq_n_s32 (int32_t __a) +{ + return (int32x4_t)__builtin_neon_vdup_nv4si ((__builtin_neon_si) __a); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vdupq_n_f32 (float32_t __a) +{ + return (float32x4_t)__builtin_neon_vdup_nv4sf ((__builtin_neon_sf) __a); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vdupq_n_u8 (uint8_t __a) +{ + return (uint8x16_t)__builtin_neon_vdup_nv16qi ((__builtin_neon_qi) __a); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vdupq_n_u16 (uint16_t __a) +{ + return (uint16x8_t)__builtin_neon_vdup_nv8hi ((__builtin_neon_hi) __a); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vdupq_n_u32 (uint32_t __a) +{ + return (uint32x4_t)__builtin_neon_vdup_nv4si ((__builtin_neon_si) __a); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vdupq_n_p8 (poly8_t __a) +{ + return (poly8x16_t)__builtin_neon_vdup_nv16qi ((__builtin_neon_qi) __a); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vdupq_n_p16 (poly16_t __a) +{ + return (poly16x8_t)__builtin_neon_vdup_nv8hi ((__builtin_neon_hi) __a); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vdupq_n_s64 (int64_t __a) +{ + return (int64x2_t)__builtin_neon_vdup_nv2di ((__builtin_neon_di) __a); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vdupq_n_u64 (uint64_t __a) +{ + return (uint64x2_t)__builtin_neon_vdup_nv2di ((__builtin_neon_di) __a); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vmov_n_s8 (int8_t __a) +{ + return (int8x8_t)__builtin_neon_vdup_nv8qi ((__builtin_neon_qi) __a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vmov_n_s16 (int16_t __a) +{ + return (int16x4_t)__builtin_neon_vdup_nv4hi ((__builtin_neon_hi) __a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vmov_n_s32 (int32_t __a) +{ + return (int32x2_t)__builtin_neon_vdup_nv2si ((__builtin_neon_si) __a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vmov_n_f32 (float32_t __a) +{ + return (float32x2_t)__builtin_neon_vdup_nv2sf ((__builtin_neon_sf) __a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vmov_n_u8 (uint8_t __a) +{ + return (uint8x8_t)__builtin_neon_vdup_nv8qi ((__builtin_neon_qi) __a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vmov_n_u16 (uint16_t __a) +{ + return (uint16x4_t)__builtin_neon_vdup_nv4hi ((__builtin_neon_hi) __a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vmov_n_u32 (uint32_t __a) +{ + return (uint32x2_t)__builtin_neon_vdup_nv2si ((__builtin_neon_si) __a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vmov_n_p8 (poly8_t __a) +{ + return (poly8x8_t)__builtin_neon_vdup_nv8qi ((__builtin_neon_qi) __a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vmov_n_p16 (poly16_t __a) +{ + return (poly16x4_t)__builtin_neon_vdup_nv4hi ((__builtin_neon_hi) __a); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vmov_n_s64 (int64_t __a) +{ + return (int64x1_t)__builtin_neon_vdup_ndi ((__builtin_neon_di) __a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vmov_n_u64 (uint64_t __a) +{ + return (uint64x1_t)__builtin_neon_vdup_ndi ((__builtin_neon_di) __a); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vmovq_n_s8 (int8_t __a) +{ + return (int8x16_t)__builtin_neon_vdup_nv16qi ((__builtin_neon_qi) __a); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmovq_n_s16 (int16_t __a) +{ + return (int16x8_t)__builtin_neon_vdup_nv8hi ((__builtin_neon_hi) __a); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmovq_n_s32 (int32_t __a) +{ + return (int32x4_t)__builtin_neon_vdup_nv4si ((__builtin_neon_si) __a); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vmovq_n_f32 (float32_t __a) +{ + return (float32x4_t)__builtin_neon_vdup_nv4sf ((__builtin_neon_sf) __a); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vmovq_n_u8 (uint8_t __a) +{ + return (uint8x16_t)__builtin_neon_vdup_nv16qi ((__builtin_neon_qi) __a); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmovq_n_u16 (uint16_t __a) +{ + return (uint16x8_t)__builtin_neon_vdup_nv8hi ((__builtin_neon_hi) __a); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmovq_n_u32 (uint32_t __a) +{ + return (uint32x4_t)__builtin_neon_vdup_nv4si ((__builtin_neon_si) __a); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vmovq_n_p8 (poly8_t __a) +{ + return (poly8x16_t)__builtin_neon_vdup_nv16qi ((__builtin_neon_qi) __a); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vmovq_n_p16 (poly16_t __a) +{ + return (poly16x8_t)__builtin_neon_vdup_nv8hi ((__builtin_neon_hi) __a); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vmovq_n_s64 (int64_t __a) +{ + return (int64x2_t)__builtin_neon_vdup_nv2di ((__builtin_neon_di) __a); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vmovq_n_u64 (uint64_t __a) +{ + return (uint64x2_t)__builtin_neon_vdup_nv2di ((__builtin_neon_di) __a); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vdup_lane_s8 (int8x8_t __a, const int __b) +{ + return (int8x8_t)__builtin_neon_vdup_lanev8qi (__a, __b); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vdup_lane_s16 (int16x4_t __a, const int __b) +{ + return (int16x4_t)__builtin_neon_vdup_lanev4hi (__a, __b); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vdup_lane_s32 (int32x2_t __a, const int __b) +{ + return (int32x2_t)__builtin_neon_vdup_lanev2si (__a, __b); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vdup_lane_f32 (float32x2_t __a, const int __b) +{ + return (float32x2_t)__builtin_neon_vdup_lanev2sf (__a, __b); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vdup_lane_u8 (uint8x8_t __a, const int __b) +{ + return (uint8x8_t)__builtin_neon_vdup_lanev8qi ((int8x8_t) __a, __b); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vdup_lane_u16 (uint16x4_t __a, const int __b) +{ + return (uint16x4_t)__builtin_neon_vdup_lanev4hi ((int16x4_t) __a, __b); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vdup_lane_u32 (uint32x2_t __a, const int __b) +{ + return (uint32x2_t)__builtin_neon_vdup_lanev2si ((int32x2_t) __a, __b); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vdup_lane_p8 (poly8x8_t __a, const int __b) +{ + return (poly8x8_t)__builtin_neon_vdup_lanev8qi ((int8x8_t) __a, __b); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vdup_lane_p16 (poly16x4_t __a, const int __b) +{ + return (poly16x4_t)__builtin_neon_vdup_lanev4hi ((int16x4_t) __a, __b); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vdup_lane_p64 (poly64x1_t __a, const int __b) +{ + return (poly64x1_t)__builtin_neon_vdup_lanedi (__a, __b); +} + +#endif +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vdup_lane_s64 (int64x1_t __a, const int __b) +{ + return (int64x1_t)__builtin_neon_vdup_lanedi (__a, __b); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vdup_lane_u64 (uint64x1_t __a, const int __b) +{ + return (uint64x1_t)__builtin_neon_vdup_lanedi ((int64x1_t) __a, __b); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vdupq_lane_s8 (int8x8_t __a, const int __b) +{ + return (int8x16_t)__builtin_neon_vdup_lanev16qi (__a, __b); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vdupq_lane_s16 (int16x4_t __a, const int __b) +{ + return (int16x8_t)__builtin_neon_vdup_lanev8hi (__a, __b); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vdupq_lane_s32 (int32x2_t __a, const int __b) +{ + return (int32x4_t)__builtin_neon_vdup_lanev4si (__a, __b); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vdupq_lane_f32 (float32x2_t __a, const int __b) +{ + return (float32x4_t)__builtin_neon_vdup_lanev4sf (__a, __b); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vdupq_lane_u8 (uint8x8_t __a, const int __b) +{ + return (uint8x16_t)__builtin_neon_vdup_lanev16qi ((int8x8_t) __a, __b); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vdupq_lane_u16 (uint16x4_t __a, const int __b) +{ + return (uint16x8_t)__builtin_neon_vdup_lanev8hi ((int16x4_t) __a, __b); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vdupq_lane_u32 (uint32x2_t __a, const int __b) +{ + return (uint32x4_t)__builtin_neon_vdup_lanev4si ((int32x2_t) __a, __b); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vdupq_lane_p8 (poly8x8_t __a, const int __b) +{ + return (poly8x16_t)__builtin_neon_vdup_lanev16qi ((int8x8_t) __a, __b); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vdupq_lane_p16 (poly16x4_t __a, const int __b) +{ + return (poly16x8_t)__builtin_neon_vdup_lanev8hi ((int16x4_t) __a, __b); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vdupq_lane_p64 (poly64x1_t __a, const int __b) +{ + return (poly64x2_t)__builtin_neon_vdup_lanev2di (__a, __b); +} + +#endif +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vdupq_lane_s64 (int64x1_t __a, const int __b) +{ + return (int64x2_t)__builtin_neon_vdup_lanev2di (__a, __b); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vdupq_lane_u64 (uint64x1_t __a, const int __b) +{ + return (uint64x2_t)__builtin_neon_vdup_lanev2di ((int64x1_t) __a, __b); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vcombine_p64 (poly64x1_t __a, poly64x1_t __b) +{ + return (poly64x2_t)__builtin_neon_vcombinedi (__a, __b); +} + +#endif +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vcombine_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x16_t)__builtin_neon_vcombinev8qi (__a, __b); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vcombine_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x8_t)__builtin_neon_vcombinev4hi (__a, __b); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vcombine_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x4_t)__builtin_neon_vcombinev2si (__a, __b); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vcombine_s64 (int64x1_t __a, int64x1_t __b) +{ + return (int64x2_t)__builtin_neon_vcombinedi (__a, __b); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vcombine_f32 (float32x2_t __a, float32x2_t __b) +{ + return (float32x4_t)__builtin_neon_vcombinev2sf (__a, __b); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vcombine_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x16_t)__builtin_neon_vcombinev8qi ((int8x8_t) __a, (int8x8_t) __b); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vcombine_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x8_t)__builtin_neon_vcombinev4hi ((int16x4_t) __a, (int16x4_t) __b); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcombine_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x4_t)__builtin_neon_vcombinev2si ((int32x2_t) __a, (int32x2_t) __b); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vcombine_u64 (uint64x1_t __a, uint64x1_t __b) +{ + return (uint64x2_t)__builtin_neon_vcombinedi ((int64x1_t) __a, (int64x1_t) __b); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vcombine_p8 (poly8x8_t __a, poly8x8_t __b) +{ + return (poly8x16_t)__builtin_neon_vcombinev8qi ((int8x8_t) __a, (int8x8_t) __b); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vcombine_p16 (poly16x4_t __a, poly16x4_t __b) +{ + return (poly16x8_t)__builtin_neon_vcombinev4hi ((int16x4_t) __a, (int16x4_t) __b); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vget_high_p64 (poly64x2_t __a) +{ + return (poly64x1_t)__builtin_neon_vget_highv2di ((int64x2_t) __a); +} + +#endif +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vget_high_s8 (int8x16_t __a) +{ + return (int8x8_t)__builtin_neon_vget_highv16qi (__a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vget_high_s16 (int16x8_t __a) +{ + return (int16x4_t)__builtin_neon_vget_highv8hi (__a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vget_high_s32 (int32x4_t __a) +{ + return (int32x2_t)__builtin_neon_vget_highv4si (__a); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vget_high_s64 (int64x2_t __a) +{ + return (int64x1_t)__builtin_neon_vget_highv2di (__a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vget_high_f32 (float32x4_t __a) +{ + return (float32x2_t)__builtin_neon_vget_highv4sf (__a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vget_high_u8 (uint8x16_t __a) +{ + return (uint8x8_t)__builtin_neon_vget_highv16qi ((int8x16_t) __a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vget_high_u16 (uint16x8_t __a) +{ + return (uint16x4_t)__builtin_neon_vget_highv8hi ((int16x8_t) __a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vget_high_u32 (uint32x4_t __a) +{ + return (uint32x2_t)__builtin_neon_vget_highv4si ((int32x4_t) __a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vget_high_u64 (uint64x2_t __a) +{ + return (uint64x1_t)__builtin_neon_vget_highv2di ((int64x2_t) __a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vget_high_p8 (poly8x16_t __a) +{ + return (poly8x8_t)__builtin_neon_vget_highv16qi ((int8x16_t) __a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vget_high_p16 (poly16x8_t __a) +{ + return (poly16x4_t)__builtin_neon_vget_highv8hi ((int16x8_t) __a); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vget_low_s8 (int8x16_t __a) +{ + return (int8x8_t)__builtin_neon_vget_lowv16qi (__a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vget_low_s16 (int16x8_t __a) +{ + return (int16x4_t)__builtin_neon_vget_lowv8hi (__a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vget_low_s32 (int32x4_t __a) +{ + return (int32x2_t)__builtin_neon_vget_lowv4si (__a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vget_low_f32 (float32x4_t __a) +{ + return (float32x2_t)__builtin_neon_vget_lowv4sf (__a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vget_low_u8 (uint8x16_t __a) +{ + return (uint8x8_t)__builtin_neon_vget_lowv16qi ((int8x16_t) __a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vget_low_u16 (uint16x8_t __a) +{ + return (uint16x4_t)__builtin_neon_vget_lowv8hi ((int16x8_t) __a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vget_low_u32 (uint32x4_t __a) +{ + return (uint32x2_t)__builtin_neon_vget_lowv4si ((int32x4_t) __a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vget_low_p8 (poly8x16_t __a) +{ + return (poly8x8_t)__builtin_neon_vget_lowv16qi ((int8x16_t) __a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vget_low_p16 (poly16x8_t __a) +{ + return (poly16x4_t)__builtin_neon_vget_lowv8hi ((int16x8_t) __a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vget_low_p64 (poly64x2_t __a) +{ + return (poly64x1_t)__builtin_neon_vget_lowv2di ((int64x2_t) __a); +} + +#endif +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vget_low_s64 (int64x2_t __a) +{ + return (int64x1_t)__builtin_neon_vget_lowv2di (__a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vget_low_u64 (uint64x2_t __a) +{ + return (uint64x1_t)__builtin_neon_vget_lowv2di ((int64x2_t) __a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vcvt_s32_f32 (float32x2_t __a) +{ + return (int32x2_t)__builtin_neon_vcvtv2sf (__a, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vcvt_f32_s32 (int32x2_t __a) +{ + return (float32x2_t)__builtin_neon_vcvtv2si (__a, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vcvt_f32_u32 (uint32x2_t __a) +{ + return (float32x2_t)__builtin_neon_vcvtv2si ((int32x2_t) __a, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcvt_u32_f32 (float32x2_t __a) +{ + return (uint32x2_t)__builtin_neon_vcvtv2sf (__a, 0); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vcvtq_s32_f32 (float32x4_t __a) +{ + return (int32x4_t)__builtin_neon_vcvtv4sf (__a, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vcvtq_f32_s32 (int32x4_t __a) +{ + return (float32x4_t)__builtin_neon_vcvtv4si (__a, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vcvtq_f32_u32 (uint32x4_t __a) +{ + return (float32x4_t)__builtin_neon_vcvtv4si ((int32x4_t) __a, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcvtq_u32_f32 (float32x4_t __a) +{ + return (uint32x4_t)__builtin_neon_vcvtv4sf (__a, 0); +} + +#if ((__ARM_FP & 0x2) != 0) +__extension__ static __inline float16x4_t __attribute__ ((__always_inline__)) +vcvt_f16_f32 (float32x4_t __a) +{ + return (float16x4_t)__builtin_neon_vcvtv4hfv4sf (__a); +} + +#endif +#if ((__ARM_FP & 0x2) != 0) +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vcvt_f32_f16 (float16x4_t __a) +{ + return (float32x4_t)__builtin_neon_vcvtv4sfv4hf (__a); +} + +#endif +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vcvt_n_s32_f32 (float32x2_t __a, const int __b) +{ + return (int32x2_t)__builtin_neon_vcvt_nv2sf (__a, __b, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vcvt_n_f32_s32 (int32x2_t __a, const int __b) +{ + return (float32x2_t)__builtin_neon_vcvt_nv2si (__a, __b, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vcvt_n_f32_u32 (uint32x2_t __a, const int __b) +{ + return (float32x2_t)__builtin_neon_vcvt_nv2si ((int32x2_t) __a, __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vcvt_n_u32_f32 (float32x2_t __a, const int __b) +{ + return (uint32x2_t)__builtin_neon_vcvt_nv2sf (__a, __b, 0); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vcvtq_n_s32_f32 (float32x4_t __a, const int __b) +{ + return (int32x4_t)__builtin_neon_vcvt_nv4sf (__a, __b, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vcvtq_n_f32_s32 (int32x4_t __a, const int __b) +{ + return (float32x4_t)__builtin_neon_vcvt_nv4si (__a, __b, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vcvtq_n_f32_u32 (uint32x4_t __a, const int __b) +{ + return (float32x4_t)__builtin_neon_vcvt_nv4si ((int32x4_t) __a, __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vcvtq_n_u32_f32 (float32x4_t __a, const int __b) +{ + return (uint32x4_t)__builtin_neon_vcvt_nv4sf (__a, __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vmovn_s16 (int16x8_t __a) +{ + return (int8x8_t)__builtin_neon_vmovnv8hi (__a, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vmovn_s32 (int32x4_t __a) +{ + return (int16x4_t)__builtin_neon_vmovnv4si (__a, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vmovn_s64 (int64x2_t __a) +{ + return (int32x2_t)__builtin_neon_vmovnv2di (__a, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vmovn_u16 (uint16x8_t __a) +{ + return (uint8x8_t)__builtin_neon_vmovnv8hi ((int16x8_t) __a, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vmovn_u32 (uint32x4_t __a) +{ + return (uint16x4_t)__builtin_neon_vmovnv4si ((int32x4_t) __a, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vmovn_u64 (uint64x2_t __a) +{ + return (uint32x2_t)__builtin_neon_vmovnv2di ((int64x2_t) __a, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vqmovn_s16 (int16x8_t __a) +{ + return (int8x8_t)__builtin_neon_vqmovnv8hi (__a, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqmovn_s32 (int32x4_t __a) +{ + return (int16x4_t)__builtin_neon_vqmovnv4si (__a, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqmovn_s64 (int64x2_t __a) +{ + return (int32x2_t)__builtin_neon_vqmovnv2di (__a, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vqmovn_u16 (uint16x8_t __a) +{ + return (uint8x8_t)__builtin_neon_vqmovnv8hi ((int16x8_t) __a, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vqmovn_u32 (uint32x4_t __a) +{ + return (uint16x4_t)__builtin_neon_vqmovnv4si ((int32x4_t) __a, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vqmovn_u64 (uint64x2_t __a) +{ + return (uint32x2_t)__builtin_neon_vqmovnv2di ((int64x2_t) __a, 0); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vqmovun_s16 (int16x8_t __a) +{ + return (uint8x8_t)__builtin_neon_vqmovunv8hi (__a, 1); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vqmovun_s32 (int32x4_t __a) +{ + return (uint16x4_t)__builtin_neon_vqmovunv4si (__a, 1); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vqmovun_s64 (int64x2_t __a) +{ + return (uint32x2_t)__builtin_neon_vqmovunv2di (__a, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmovl_s8 (int8x8_t __a) +{ + return (int16x8_t)__builtin_neon_vmovlv8qi (__a, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmovl_s16 (int16x4_t __a) +{ + return (int32x4_t)__builtin_neon_vmovlv4hi (__a, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vmovl_s32 (int32x2_t __a) +{ + return (int64x2_t)__builtin_neon_vmovlv2si (__a, 1); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmovl_u8 (uint8x8_t __a) +{ + return (uint16x8_t)__builtin_neon_vmovlv8qi ((int8x8_t) __a, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmovl_u16 (uint16x4_t __a) +{ + return (uint32x4_t)__builtin_neon_vmovlv4hi ((int16x4_t) __a, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vmovl_u32 (uint32x2_t __a) +{ + return (uint64x2_t)__builtin_neon_vmovlv2si ((int32x2_t) __a, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vtbl1_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vtbl1v8qi (__a, __b); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vtbl1_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vtbl1v8qi ((int8x8_t) __a, (int8x8_t) __b); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vtbl1_p8 (poly8x8_t __a, uint8x8_t __b) +{ + return (poly8x8_t)__builtin_neon_vtbl1v8qi ((int8x8_t) __a, (int8x8_t) __b); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vtbl2_s8 (int8x8x2_t __a, int8x8_t __b) +{ + union { int8x8x2_t __i; __builtin_neon_ti __o; } __au = { __a }; + return (int8x8_t)__builtin_neon_vtbl2v8qi (__au.__o, __b); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vtbl2_u8 (uint8x8x2_t __a, uint8x8_t __b) +{ + union { uint8x8x2_t __i; __builtin_neon_ti __o; } __au = { __a }; + return (uint8x8_t)__builtin_neon_vtbl2v8qi (__au.__o, (int8x8_t) __b); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vtbl2_p8 (poly8x8x2_t __a, uint8x8_t __b) +{ + union { poly8x8x2_t __i; __builtin_neon_ti __o; } __au = { __a }; + return (poly8x8_t)__builtin_neon_vtbl2v8qi (__au.__o, (int8x8_t) __b); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vtbl3_s8 (int8x8x3_t __a, int8x8_t __b) +{ + union { int8x8x3_t __i; __builtin_neon_ei __o; } __au = { __a }; + return (int8x8_t)__builtin_neon_vtbl3v8qi (__au.__o, __b); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vtbl3_u8 (uint8x8x3_t __a, uint8x8_t __b) +{ + union { uint8x8x3_t __i; __builtin_neon_ei __o; } __au = { __a }; + return (uint8x8_t)__builtin_neon_vtbl3v8qi (__au.__o, (int8x8_t) __b); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vtbl3_p8 (poly8x8x3_t __a, uint8x8_t __b) +{ + union { poly8x8x3_t __i; __builtin_neon_ei __o; } __au = { __a }; + return (poly8x8_t)__builtin_neon_vtbl3v8qi (__au.__o, (int8x8_t) __b); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vtbl4_s8 (int8x8x4_t __a, int8x8_t __b) +{ + union { int8x8x4_t __i; __builtin_neon_oi __o; } __au = { __a }; + return (int8x8_t)__builtin_neon_vtbl4v8qi (__au.__o, __b); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vtbl4_u8 (uint8x8x4_t __a, uint8x8_t __b) +{ + union { uint8x8x4_t __i; __builtin_neon_oi __o; } __au = { __a }; + return (uint8x8_t)__builtin_neon_vtbl4v8qi (__au.__o, (int8x8_t) __b); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vtbl4_p8 (poly8x8x4_t __a, uint8x8_t __b) +{ + union { poly8x8x4_t __i; __builtin_neon_oi __o; } __au = { __a }; + return (poly8x8_t)__builtin_neon_vtbl4v8qi (__au.__o, (int8x8_t) __b); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vtbx1_s8 (int8x8_t __a, int8x8_t __b, int8x8_t __c) +{ + return (int8x8_t)__builtin_neon_vtbx1v8qi (__a, __b, __c); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vtbx1_u8 (uint8x8_t __a, uint8x8_t __b, uint8x8_t __c) +{ + return (uint8x8_t)__builtin_neon_vtbx1v8qi ((int8x8_t) __a, (int8x8_t) __b, (int8x8_t) __c); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vtbx1_p8 (poly8x8_t __a, poly8x8_t __b, uint8x8_t __c) +{ + return (poly8x8_t)__builtin_neon_vtbx1v8qi ((int8x8_t) __a, (int8x8_t) __b, (int8x8_t) __c); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vtbx2_s8 (int8x8_t __a, int8x8x2_t __b, int8x8_t __c) +{ + union { int8x8x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + return (int8x8_t)__builtin_neon_vtbx2v8qi (__a, __bu.__o, __c); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vtbx2_u8 (uint8x8_t __a, uint8x8x2_t __b, uint8x8_t __c) +{ + union { uint8x8x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + return (uint8x8_t)__builtin_neon_vtbx2v8qi ((int8x8_t) __a, __bu.__o, (int8x8_t) __c); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vtbx2_p8 (poly8x8_t __a, poly8x8x2_t __b, uint8x8_t __c) +{ + union { poly8x8x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + return (poly8x8_t)__builtin_neon_vtbx2v8qi ((int8x8_t) __a, __bu.__o, (int8x8_t) __c); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vtbx3_s8 (int8x8_t __a, int8x8x3_t __b, int8x8_t __c) +{ + union { int8x8x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + return (int8x8_t)__builtin_neon_vtbx3v8qi (__a, __bu.__o, __c); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vtbx3_u8 (uint8x8_t __a, uint8x8x3_t __b, uint8x8_t __c) +{ + union { uint8x8x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + return (uint8x8_t)__builtin_neon_vtbx3v8qi ((int8x8_t) __a, __bu.__o, (int8x8_t) __c); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vtbx3_p8 (poly8x8_t __a, poly8x8x3_t __b, uint8x8_t __c) +{ + union { poly8x8x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + return (poly8x8_t)__builtin_neon_vtbx3v8qi ((int8x8_t) __a, __bu.__o, (int8x8_t) __c); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vtbx4_s8 (int8x8_t __a, int8x8x4_t __b, int8x8_t __c) +{ + union { int8x8x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + return (int8x8_t)__builtin_neon_vtbx4v8qi (__a, __bu.__o, __c); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vtbx4_u8 (uint8x8_t __a, uint8x8x4_t __b, uint8x8_t __c) +{ + union { uint8x8x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + return (uint8x8_t)__builtin_neon_vtbx4v8qi ((int8x8_t) __a, __bu.__o, (int8x8_t) __c); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vtbx4_p8 (poly8x8_t __a, poly8x8x4_t __b, uint8x8_t __c) +{ + union { poly8x8x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + return (poly8x8_t)__builtin_neon_vtbx4v8qi ((int8x8_t) __a, __bu.__o, (int8x8_t) __c); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vmul_lane_s16 (int16x4_t __a, int16x4_t __b, const int __c) +{ + return (int16x4_t)__builtin_neon_vmul_lanev4hi (__a, __b, __c, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vmul_lane_s32 (int32x2_t __a, int32x2_t __b, const int __c) +{ + return (int32x2_t)__builtin_neon_vmul_lanev2si (__a, __b, __c, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vmul_lane_f32 (float32x2_t __a, float32x2_t __b, const int __c) +{ + return (float32x2_t)__builtin_neon_vmul_lanev2sf (__a, __b, __c, 3); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vmul_lane_u16 (uint16x4_t __a, uint16x4_t __b, const int __c) +{ + return (uint16x4_t)__builtin_neon_vmul_lanev4hi ((int16x4_t) __a, (int16x4_t) __b, __c, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vmul_lane_u32 (uint32x2_t __a, uint32x2_t __b, const int __c) +{ + return (uint32x2_t)__builtin_neon_vmul_lanev2si ((int32x2_t) __a, (int32x2_t) __b, __c, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmulq_lane_s16 (int16x8_t __a, int16x4_t __b, const int __c) +{ + return (int16x8_t)__builtin_neon_vmul_lanev8hi (__a, __b, __c, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmulq_lane_s32 (int32x4_t __a, int32x2_t __b, const int __c) +{ + return (int32x4_t)__builtin_neon_vmul_lanev4si (__a, __b, __c, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vmulq_lane_f32 (float32x4_t __a, float32x2_t __b, const int __c) +{ + return (float32x4_t)__builtin_neon_vmul_lanev4sf (__a, __b, __c, 3); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmulq_lane_u16 (uint16x8_t __a, uint16x4_t __b, const int __c) +{ + return (uint16x8_t)__builtin_neon_vmul_lanev8hi ((int16x8_t) __a, (int16x4_t) __b, __c, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmulq_lane_u32 (uint32x4_t __a, uint32x2_t __b, const int __c) +{ + return (uint32x4_t)__builtin_neon_vmul_lanev4si ((int32x4_t) __a, (int32x2_t) __b, __c, 0); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vmla_lane_s16 (int16x4_t __a, int16x4_t __b, int16x4_t __c, const int __d) +{ + return (int16x4_t)__builtin_neon_vmla_lanev4hi (__a, __b, __c, __d, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vmla_lane_s32 (int32x2_t __a, int32x2_t __b, int32x2_t __c, const int __d) +{ + return (int32x2_t)__builtin_neon_vmla_lanev2si (__a, __b, __c, __d, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vmla_lane_f32 (float32x2_t __a, float32x2_t __b, float32x2_t __c, const int __d) +{ + return (float32x2_t)__builtin_neon_vmla_lanev2sf (__a, __b, __c, __d, 3); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vmla_lane_u16 (uint16x4_t __a, uint16x4_t __b, uint16x4_t __c, const int __d) +{ + return (uint16x4_t)__builtin_neon_vmla_lanev4hi ((int16x4_t) __a, (int16x4_t) __b, (int16x4_t) __c, __d, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vmla_lane_u32 (uint32x2_t __a, uint32x2_t __b, uint32x2_t __c, const int __d) +{ + return (uint32x2_t)__builtin_neon_vmla_lanev2si ((int32x2_t) __a, (int32x2_t) __b, (int32x2_t) __c, __d, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmlaq_lane_s16 (int16x8_t __a, int16x8_t __b, int16x4_t __c, const int __d) +{ + return (int16x8_t)__builtin_neon_vmla_lanev8hi (__a, __b, __c, __d, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmlaq_lane_s32 (int32x4_t __a, int32x4_t __b, int32x2_t __c, const int __d) +{ + return (int32x4_t)__builtin_neon_vmla_lanev4si (__a, __b, __c, __d, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vmlaq_lane_f32 (float32x4_t __a, float32x4_t __b, float32x2_t __c, const int __d) +{ + return (float32x4_t)__builtin_neon_vmla_lanev4sf (__a, __b, __c, __d, 3); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmlaq_lane_u16 (uint16x8_t __a, uint16x8_t __b, uint16x4_t __c, const int __d) +{ + return (uint16x8_t)__builtin_neon_vmla_lanev8hi ((int16x8_t) __a, (int16x8_t) __b, (int16x4_t) __c, __d, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmlaq_lane_u32 (uint32x4_t __a, uint32x4_t __b, uint32x2_t __c, const int __d) +{ + return (uint32x4_t)__builtin_neon_vmla_lanev4si ((int32x4_t) __a, (int32x4_t) __b, (int32x2_t) __c, __d, 0); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmlal_lane_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c, const int __d) +{ + return (int32x4_t)__builtin_neon_vmlal_lanev4hi (__a, __b, __c, __d, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vmlal_lane_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c, const int __d) +{ + return (int64x2_t)__builtin_neon_vmlal_lanev2si (__a, __b, __c, __d, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmlal_lane_u16 (uint32x4_t __a, uint16x4_t __b, uint16x4_t __c, const int __d) +{ + return (uint32x4_t)__builtin_neon_vmlal_lanev4hi ((int32x4_t) __a, (int16x4_t) __b, (int16x4_t) __c, __d, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vmlal_lane_u32 (uint64x2_t __a, uint32x2_t __b, uint32x2_t __c, const int __d) +{ + return (uint64x2_t)__builtin_neon_vmlal_lanev2si ((int64x2_t) __a, (int32x2_t) __b, (int32x2_t) __c, __d, 0); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqdmlal_lane_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c, const int __d) +{ + return (int32x4_t)__builtin_neon_vqdmlal_lanev4hi (__a, __b, __c, __d, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vqdmlal_lane_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c, const int __d) +{ + return (int64x2_t)__builtin_neon_vqdmlal_lanev2si (__a, __b, __c, __d, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vmls_lane_s16 (int16x4_t __a, int16x4_t __b, int16x4_t __c, const int __d) +{ + return (int16x4_t)__builtin_neon_vmls_lanev4hi (__a, __b, __c, __d, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vmls_lane_s32 (int32x2_t __a, int32x2_t __b, int32x2_t __c, const int __d) +{ + return (int32x2_t)__builtin_neon_vmls_lanev2si (__a, __b, __c, __d, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vmls_lane_f32 (float32x2_t __a, float32x2_t __b, float32x2_t __c, const int __d) +{ + return (float32x2_t)__builtin_neon_vmls_lanev2sf (__a, __b, __c, __d, 3); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vmls_lane_u16 (uint16x4_t __a, uint16x4_t __b, uint16x4_t __c, const int __d) +{ + return (uint16x4_t)__builtin_neon_vmls_lanev4hi ((int16x4_t) __a, (int16x4_t) __b, (int16x4_t) __c, __d, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vmls_lane_u32 (uint32x2_t __a, uint32x2_t __b, uint32x2_t __c, const int __d) +{ + return (uint32x2_t)__builtin_neon_vmls_lanev2si ((int32x2_t) __a, (int32x2_t) __b, (int32x2_t) __c, __d, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmlsq_lane_s16 (int16x8_t __a, int16x8_t __b, int16x4_t __c, const int __d) +{ + return (int16x8_t)__builtin_neon_vmls_lanev8hi (__a, __b, __c, __d, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmlsq_lane_s32 (int32x4_t __a, int32x4_t __b, int32x2_t __c, const int __d) +{ + return (int32x4_t)__builtin_neon_vmls_lanev4si (__a, __b, __c, __d, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vmlsq_lane_f32 (float32x4_t __a, float32x4_t __b, float32x2_t __c, const int __d) +{ + return (float32x4_t)__builtin_neon_vmls_lanev4sf (__a, __b, __c, __d, 3); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmlsq_lane_u16 (uint16x8_t __a, uint16x8_t __b, uint16x4_t __c, const int __d) +{ + return (uint16x8_t)__builtin_neon_vmls_lanev8hi ((int16x8_t) __a, (int16x8_t) __b, (int16x4_t) __c, __d, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmlsq_lane_u32 (uint32x4_t __a, uint32x4_t __b, uint32x2_t __c, const int __d) +{ + return (uint32x4_t)__builtin_neon_vmls_lanev4si ((int32x4_t) __a, (int32x4_t) __b, (int32x2_t) __c, __d, 0); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmlsl_lane_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c, const int __d) +{ + return (int32x4_t)__builtin_neon_vmlsl_lanev4hi (__a, __b, __c, __d, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vmlsl_lane_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c, const int __d) +{ + return (int64x2_t)__builtin_neon_vmlsl_lanev2si (__a, __b, __c, __d, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmlsl_lane_u16 (uint32x4_t __a, uint16x4_t __b, uint16x4_t __c, const int __d) +{ + return (uint32x4_t)__builtin_neon_vmlsl_lanev4hi ((int32x4_t) __a, (int16x4_t) __b, (int16x4_t) __c, __d, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vmlsl_lane_u32 (uint64x2_t __a, uint32x2_t __b, uint32x2_t __c, const int __d) +{ + return (uint64x2_t)__builtin_neon_vmlsl_lanev2si ((int64x2_t) __a, (int32x2_t) __b, (int32x2_t) __c, __d, 0); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqdmlsl_lane_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c, const int __d) +{ + return (int32x4_t)__builtin_neon_vqdmlsl_lanev4hi (__a, __b, __c, __d, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vqdmlsl_lane_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c, const int __d) +{ + return (int64x2_t)__builtin_neon_vqdmlsl_lanev2si (__a, __b, __c, __d, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmull_lane_s16 (int16x4_t __a, int16x4_t __b, const int __c) +{ + return (int32x4_t)__builtin_neon_vmull_lanev4hi (__a, __b, __c, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vmull_lane_s32 (int32x2_t __a, int32x2_t __b, const int __c) +{ + return (int64x2_t)__builtin_neon_vmull_lanev2si (__a, __b, __c, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmull_lane_u16 (uint16x4_t __a, uint16x4_t __b, const int __c) +{ + return (uint32x4_t)__builtin_neon_vmull_lanev4hi ((int16x4_t) __a, (int16x4_t) __b, __c, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vmull_lane_u32 (uint32x2_t __a, uint32x2_t __b, const int __c) +{ + return (uint64x2_t)__builtin_neon_vmull_lanev2si ((int32x2_t) __a, (int32x2_t) __b, __c, 0); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqdmull_lane_s16 (int16x4_t __a, int16x4_t __b, const int __c) +{ + return (int32x4_t)__builtin_neon_vqdmull_lanev4hi (__a, __b, __c, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vqdmull_lane_s32 (int32x2_t __a, int32x2_t __b, const int __c) +{ + return (int64x2_t)__builtin_neon_vqdmull_lanev2si (__a, __b, __c, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vqdmulhq_lane_s16 (int16x8_t __a, int16x4_t __b, const int __c) +{ + return (int16x8_t)__builtin_neon_vqdmulh_lanev8hi (__a, __b, __c, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqdmulhq_lane_s32 (int32x4_t __a, int32x2_t __b, const int __c) +{ + return (int32x4_t)__builtin_neon_vqdmulh_lanev4si (__a, __b, __c, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqdmulh_lane_s16 (int16x4_t __a, int16x4_t __b, const int __c) +{ + return (int16x4_t)__builtin_neon_vqdmulh_lanev4hi (__a, __b, __c, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqdmulh_lane_s32 (int32x2_t __a, int32x2_t __b, const int __c) +{ + return (int32x2_t)__builtin_neon_vqdmulh_lanev2si (__a, __b, __c, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vqrdmulhq_lane_s16 (int16x8_t __a, int16x4_t __b, const int __c) +{ + return (int16x8_t)__builtin_neon_vqdmulh_lanev8hi (__a, __b, __c, 5); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqrdmulhq_lane_s32 (int32x4_t __a, int32x2_t __b, const int __c) +{ + return (int32x4_t)__builtin_neon_vqdmulh_lanev4si (__a, __b, __c, 5); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqrdmulh_lane_s16 (int16x4_t __a, int16x4_t __b, const int __c) +{ + return (int16x4_t)__builtin_neon_vqdmulh_lanev4hi (__a, __b, __c, 5); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqrdmulh_lane_s32 (int32x2_t __a, int32x2_t __b, const int __c) +{ + return (int32x2_t)__builtin_neon_vqdmulh_lanev2si (__a, __b, __c, 5); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vmul_n_s16 (int16x4_t __a, int16_t __b) +{ + return (int16x4_t)__builtin_neon_vmul_nv4hi (__a, (__builtin_neon_hi) __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vmul_n_s32 (int32x2_t __a, int32_t __b) +{ + return (int32x2_t)__builtin_neon_vmul_nv2si (__a, (__builtin_neon_si) __b, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vmul_n_f32 (float32x2_t __a, float32_t __b) +{ + return (float32x2_t)__builtin_neon_vmul_nv2sf (__a, (__builtin_neon_sf) __b, 3); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vmul_n_u16 (uint16x4_t __a, uint16_t __b) +{ + return (uint16x4_t)__builtin_neon_vmul_nv4hi ((int16x4_t) __a, (__builtin_neon_hi) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vmul_n_u32 (uint32x2_t __a, uint32_t __b) +{ + return (uint32x2_t)__builtin_neon_vmul_nv2si ((int32x2_t) __a, (__builtin_neon_si) __b, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmulq_n_s16 (int16x8_t __a, int16_t __b) +{ + return (int16x8_t)__builtin_neon_vmul_nv8hi (__a, (__builtin_neon_hi) __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmulq_n_s32 (int32x4_t __a, int32_t __b) +{ + return (int32x4_t)__builtin_neon_vmul_nv4si (__a, (__builtin_neon_si) __b, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vmulq_n_f32 (float32x4_t __a, float32_t __b) +{ + return (float32x4_t)__builtin_neon_vmul_nv4sf (__a, (__builtin_neon_sf) __b, 3); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmulq_n_u16 (uint16x8_t __a, uint16_t __b) +{ + return (uint16x8_t)__builtin_neon_vmul_nv8hi ((int16x8_t) __a, (__builtin_neon_hi) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmulq_n_u32 (uint32x4_t __a, uint32_t __b) +{ + return (uint32x4_t)__builtin_neon_vmul_nv4si ((int32x4_t) __a, (__builtin_neon_si) __b, 0); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmull_n_s16 (int16x4_t __a, int16_t __b) +{ + return (int32x4_t)__builtin_neon_vmull_nv4hi (__a, (__builtin_neon_hi) __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vmull_n_s32 (int32x2_t __a, int32_t __b) +{ + return (int64x2_t)__builtin_neon_vmull_nv2si (__a, (__builtin_neon_si) __b, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmull_n_u16 (uint16x4_t __a, uint16_t __b) +{ + return (uint32x4_t)__builtin_neon_vmull_nv4hi ((int16x4_t) __a, (__builtin_neon_hi) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vmull_n_u32 (uint32x2_t __a, uint32_t __b) +{ + return (uint64x2_t)__builtin_neon_vmull_nv2si ((int32x2_t) __a, (__builtin_neon_si) __b, 0); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqdmull_n_s16 (int16x4_t __a, int16_t __b) +{ + return (int32x4_t)__builtin_neon_vqdmull_nv4hi (__a, (__builtin_neon_hi) __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vqdmull_n_s32 (int32x2_t __a, int32_t __b) +{ + return (int64x2_t)__builtin_neon_vqdmull_nv2si (__a, (__builtin_neon_si) __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vqdmulhq_n_s16 (int16x8_t __a, int16_t __b) +{ + return (int16x8_t)__builtin_neon_vqdmulh_nv8hi (__a, (__builtin_neon_hi) __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqdmulhq_n_s32 (int32x4_t __a, int32_t __b) +{ + return (int32x4_t)__builtin_neon_vqdmulh_nv4si (__a, (__builtin_neon_si) __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqdmulh_n_s16 (int16x4_t __a, int16_t __b) +{ + return (int16x4_t)__builtin_neon_vqdmulh_nv4hi (__a, (__builtin_neon_hi) __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqdmulh_n_s32 (int32x2_t __a, int32_t __b) +{ + return (int32x2_t)__builtin_neon_vqdmulh_nv2si (__a, (__builtin_neon_si) __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vqrdmulhq_n_s16 (int16x8_t __a, int16_t __b) +{ + return (int16x8_t)__builtin_neon_vqdmulh_nv8hi (__a, (__builtin_neon_hi) __b, 5); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqrdmulhq_n_s32 (int32x4_t __a, int32_t __b) +{ + return (int32x4_t)__builtin_neon_vqdmulh_nv4si (__a, (__builtin_neon_si) __b, 5); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vqrdmulh_n_s16 (int16x4_t __a, int16_t __b) +{ + return (int16x4_t)__builtin_neon_vqdmulh_nv4hi (__a, (__builtin_neon_hi) __b, 5); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vqrdmulh_n_s32 (int32x2_t __a, int32_t __b) +{ + return (int32x2_t)__builtin_neon_vqdmulh_nv2si (__a, (__builtin_neon_si) __b, 5); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vmla_n_s16 (int16x4_t __a, int16x4_t __b, int16_t __c) +{ + return (int16x4_t)__builtin_neon_vmla_nv4hi (__a, __b, (__builtin_neon_hi) __c, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vmla_n_s32 (int32x2_t __a, int32x2_t __b, int32_t __c) +{ + return (int32x2_t)__builtin_neon_vmla_nv2si (__a, __b, (__builtin_neon_si) __c, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vmla_n_f32 (float32x2_t __a, float32x2_t __b, float32_t __c) +{ + return (float32x2_t)__builtin_neon_vmla_nv2sf (__a, __b, (__builtin_neon_sf) __c, 3); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vmla_n_u16 (uint16x4_t __a, uint16x4_t __b, uint16_t __c) +{ + return (uint16x4_t)__builtin_neon_vmla_nv4hi ((int16x4_t) __a, (int16x4_t) __b, (__builtin_neon_hi) __c, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vmla_n_u32 (uint32x2_t __a, uint32x2_t __b, uint32_t __c) +{ + return (uint32x2_t)__builtin_neon_vmla_nv2si ((int32x2_t) __a, (int32x2_t) __b, (__builtin_neon_si) __c, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmlaq_n_s16 (int16x8_t __a, int16x8_t __b, int16_t __c) +{ + return (int16x8_t)__builtin_neon_vmla_nv8hi (__a, __b, (__builtin_neon_hi) __c, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmlaq_n_s32 (int32x4_t __a, int32x4_t __b, int32_t __c) +{ + return (int32x4_t)__builtin_neon_vmla_nv4si (__a, __b, (__builtin_neon_si) __c, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vmlaq_n_f32 (float32x4_t __a, float32x4_t __b, float32_t __c) +{ + return (float32x4_t)__builtin_neon_vmla_nv4sf (__a, __b, (__builtin_neon_sf) __c, 3); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmlaq_n_u16 (uint16x8_t __a, uint16x8_t __b, uint16_t __c) +{ + return (uint16x8_t)__builtin_neon_vmla_nv8hi ((int16x8_t) __a, (int16x8_t) __b, (__builtin_neon_hi) __c, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmlaq_n_u32 (uint32x4_t __a, uint32x4_t __b, uint32_t __c) +{ + return (uint32x4_t)__builtin_neon_vmla_nv4si ((int32x4_t) __a, (int32x4_t) __b, (__builtin_neon_si) __c, 0); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmlal_n_s16 (int32x4_t __a, int16x4_t __b, int16_t __c) +{ + return (int32x4_t)__builtin_neon_vmlal_nv4hi (__a, __b, (__builtin_neon_hi) __c, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vmlal_n_s32 (int64x2_t __a, int32x2_t __b, int32_t __c) +{ + return (int64x2_t)__builtin_neon_vmlal_nv2si (__a, __b, (__builtin_neon_si) __c, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmlal_n_u16 (uint32x4_t __a, uint16x4_t __b, uint16_t __c) +{ + return (uint32x4_t)__builtin_neon_vmlal_nv4hi ((int32x4_t) __a, (int16x4_t) __b, (__builtin_neon_hi) __c, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vmlal_n_u32 (uint64x2_t __a, uint32x2_t __b, uint32_t __c) +{ + return (uint64x2_t)__builtin_neon_vmlal_nv2si ((int64x2_t) __a, (int32x2_t) __b, (__builtin_neon_si) __c, 0); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqdmlal_n_s16 (int32x4_t __a, int16x4_t __b, int16_t __c) +{ + return (int32x4_t)__builtin_neon_vqdmlal_nv4hi (__a, __b, (__builtin_neon_hi) __c, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vqdmlal_n_s32 (int64x2_t __a, int32x2_t __b, int32_t __c) +{ + return (int64x2_t)__builtin_neon_vqdmlal_nv2si (__a, __b, (__builtin_neon_si) __c, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vmls_n_s16 (int16x4_t __a, int16x4_t __b, int16_t __c) +{ + return (int16x4_t)__builtin_neon_vmls_nv4hi (__a, __b, (__builtin_neon_hi) __c, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vmls_n_s32 (int32x2_t __a, int32x2_t __b, int32_t __c) +{ + return (int32x2_t)__builtin_neon_vmls_nv2si (__a, __b, (__builtin_neon_si) __c, 1); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vmls_n_f32 (float32x2_t __a, float32x2_t __b, float32_t __c) +{ + return (float32x2_t)__builtin_neon_vmls_nv2sf (__a, __b, (__builtin_neon_sf) __c, 3); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vmls_n_u16 (uint16x4_t __a, uint16x4_t __b, uint16_t __c) +{ + return (uint16x4_t)__builtin_neon_vmls_nv4hi ((int16x4_t) __a, (int16x4_t) __b, (__builtin_neon_hi) __c, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vmls_n_u32 (uint32x2_t __a, uint32x2_t __b, uint32_t __c) +{ + return (uint32x2_t)__builtin_neon_vmls_nv2si ((int32x2_t) __a, (int32x2_t) __b, (__builtin_neon_si) __c, 0); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vmlsq_n_s16 (int16x8_t __a, int16x8_t __b, int16_t __c) +{ + return (int16x8_t)__builtin_neon_vmls_nv8hi (__a, __b, (__builtin_neon_hi) __c, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmlsq_n_s32 (int32x4_t __a, int32x4_t __b, int32_t __c) +{ + return (int32x4_t)__builtin_neon_vmls_nv4si (__a, __b, (__builtin_neon_si) __c, 1); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vmlsq_n_f32 (float32x4_t __a, float32x4_t __b, float32_t __c) +{ + return (float32x4_t)__builtin_neon_vmls_nv4sf (__a, __b, (__builtin_neon_sf) __c, 3); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vmlsq_n_u16 (uint16x8_t __a, uint16x8_t __b, uint16_t __c) +{ + return (uint16x8_t)__builtin_neon_vmls_nv8hi ((int16x8_t) __a, (int16x8_t) __b, (__builtin_neon_hi) __c, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmlsq_n_u32 (uint32x4_t __a, uint32x4_t __b, uint32_t __c) +{ + return (uint32x4_t)__builtin_neon_vmls_nv4si ((int32x4_t) __a, (int32x4_t) __b, (__builtin_neon_si) __c, 0); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vmlsl_n_s16 (int32x4_t __a, int16x4_t __b, int16_t __c) +{ + return (int32x4_t)__builtin_neon_vmlsl_nv4hi (__a, __b, (__builtin_neon_hi) __c, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vmlsl_n_s32 (int64x2_t __a, int32x2_t __b, int32_t __c) +{ + return (int64x2_t)__builtin_neon_vmlsl_nv2si (__a, __b, (__builtin_neon_si) __c, 1); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vmlsl_n_u16 (uint32x4_t __a, uint16x4_t __b, uint16_t __c) +{ + return (uint32x4_t)__builtin_neon_vmlsl_nv4hi ((int32x4_t) __a, (int16x4_t) __b, (__builtin_neon_hi) __c, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vmlsl_n_u32 (uint64x2_t __a, uint32x2_t __b, uint32_t __c) +{ + return (uint64x2_t)__builtin_neon_vmlsl_nv2si ((int64x2_t) __a, (int32x2_t) __b, (__builtin_neon_si) __c, 0); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vqdmlsl_n_s16 (int32x4_t __a, int16x4_t __b, int16_t __c) +{ + return (int32x4_t)__builtin_neon_vqdmlsl_nv4hi (__a, __b, (__builtin_neon_hi) __c, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vqdmlsl_n_s32 (int64x2_t __a, int32x2_t __b, int32_t __c) +{ + return (int64x2_t)__builtin_neon_vqdmlsl_nv2si (__a, __b, (__builtin_neon_si) __c, 1); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vext_p64 (poly64x1_t __a, poly64x1_t __b, const int __c) +{ + return (poly64x1_t)__builtin_neon_vextdi (__a, __b, __c); +} + +#endif +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vext_s8 (int8x8_t __a, int8x8_t __b, const int __c) +{ + return (int8x8_t)__builtin_neon_vextv8qi (__a, __b, __c); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vext_s16 (int16x4_t __a, int16x4_t __b, const int __c) +{ + return (int16x4_t)__builtin_neon_vextv4hi (__a, __b, __c); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vext_s32 (int32x2_t __a, int32x2_t __b, const int __c) +{ + return (int32x2_t)__builtin_neon_vextv2si (__a, __b, __c); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vext_s64 (int64x1_t __a, int64x1_t __b, const int __c) +{ + return (int64x1_t)__builtin_neon_vextdi (__a, __b, __c); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vext_f32 (float32x2_t __a, float32x2_t __b, const int __c) +{ + return (float32x2_t)__builtin_neon_vextv2sf (__a, __b, __c); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vext_u8 (uint8x8_t __a, uint8x8_t __b, const int __c) +{ + return (uint8x8_t)__builtin_neon_vextv8qi ((int8x8_t) __a, (int8x8_t) __b, __c); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vext_u16 (uint16x4_t __a, uint16x4_t __b, const int __c) +{ + return (uint16x4_t)__builtin_neon_vextv4hi ((int16x4_t) __a, (int16x4_t) __b, __c); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vext_u32 (uint32x2_t __a, uint32x2_t __b, const int __c) +{ + return (uint32x2_t)__builtin_neon_vextv2si ((int32x2_t) __a, (int32x2_t) __b, __c); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vext_u64 (uint64x1_t __a, uint64x1_t __b, const int __c) +{ + return (uint64x1_t)__builtin_neon_vextdi ((int64x1_t) __a, (int64x1_t) __b, __c); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vext_p8 (poly8x8_t __a, poly8x8_t __b, const int __c) +{ + return (poly8x8_t)__builtin_neon_vextv8qi ((int8x8_t) __a, (int8x8_t) __b, __c); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vext_p16 (poly16x4_t __a, poly16x4_t __b, const int __c) +{ + return (poly16x4_t)__builtin_neon_vextv4hi ((int16x4_t) __a, (int16x4_t) __b, __c); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vextq_p64 (poly64x2_t __a, poly64x2_t __b, const int __c) +{ + return (poly64x2_t)__builtin_neon_vextv2di ((int64x2_t) __a, (int64x2_t) __b, __c); +} + +#endif +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vextq_s8 (int8x16_t __a, int8x16_t __b, const int __c) +{ + return (int8x16_t)__builtin_neon_vextv16qi (__a, __b, __c); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vextq_s16 (int16x8_t __a, int16x8_t __b, const int __c) +{ + return (int16x8_t)__builtin_neon_vextv8hi (__a, __b, __c); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vextq_s32 (int32x4_t __a, int32x4_t __b, const int __c) +{ + return (int32x4_t)__builtin_neon_vextv4si (__a, __b, __c); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vextq_s64 (int64x2_t __a, int64x2_t __b, const int __c) +{ + return (int64x2_t)__builtin_neon_vextv2di (__a, __b, __c); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vextq_f32 (float32x4_t __a, float32x4_t __b, const int __c) +{ + return (float32x4_t)__builtin_neon_vextv4sf (__a, __b, __c); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vextq_u8 (uint8x16_t __a, uint8x16_t __b, const int __c) +{ + return (uint8x16_t)__builtin_neon_vextv16qi ((int8x16_t) __a, (int8x16_t) __b, __c); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vextq_u16 (uint16x8_t __a, uint16x8_t __b, const int __c) +{ + return (uint16x8_t)__builtin_neon_vextv8hi ((int16x8_t) __a, (int16x8_t) __b, __c); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vextq_u32 (uint32x4_t __a, uint32x4_t __b, const int __c) +{ + return (uint32x4_t)__builtin_neon_vextv4si ((int32x4_t) __a, (int32x4_t) __b, __c); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vextq_u64 (uint64x2_t __a, uint64x2_t __b, const int __c) +{ + return (uint64x2_t)__builtin_neon_vextv2di ((int64x2_t) __a, (int64x2_t) __b, __c); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vextq_p8 (poly8x16_t __a, poly8x16_t __b, const int __c) +{ + return (poly8x16_t)__builtin_neon_vextv16qi ((int8x16_t) __a, (int8x16_t) __b, __c); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vextq_p16 (poly16x8_t __a, poly16x8_t __b, const int __c) +{ + return (poly16x8_t)__builtin_neon_vextv8hi ((int16x8_t) __a, (int16x8_t) __b, __c); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vrev64_s8 (int8x8_t __a) +{ + return (int8x8_t) __builtin_shuffle (__a, (uint8x8_t) { 7, 6, 5, 4, 3, 2, 1, 0 }); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vrev64_s16 (int16x4_t __a) +{ + return (int16x4_t) __builtin_shuffle (__a, (uint16x4_t) { 3, 2, 1, 0 }); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vrev64_s32 (int32x2_t __a) +{ + return (int32x2_t) __builtin_shuffle (__a, (uint32x2_t) { 1, 0 }); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vrev64_f32 (float32x2_t __a) +{ + return (float32x2_t) __builtin_shuffle (__a, (uint32x2_t) { 1, 0 }); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vrev64_u8 (uint8x8_t __a) +{ + return (uint8x8_t) __builtin_shuffle (__a, (uint8x8_t) { 7, 6, 5, 4, 3, 2, 1, 0 }); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vrev64_u16 (uint16x4_t __a) +{ + return (uint16x4_t) __builtin_shuffle (__a, (uint16x4_t) { 3, 2, 1, 0 }); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vrev64_u32 (uint32x2_t __a) +{ + return (uint32x2_t) __builtin_shuffle (__a, (uint32x2_t) { 1, 0 }); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vrev64_p8 (poly8x8_t __a) +{ + return (poly8x8_t) __builtin_shuffle (__a, (uint8x8_t) { 7, 6, 5, 4, 3, 2, 1, 0 }); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vrev64_p16 (poly16x4_t __a) +{ + return (poly16x4_t) __builtin_shuffle (__a, (uint16x4_t) { 3, 2, 1, 0 }); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vrev64q_s8 (int8x16_t __a) +{ + return (int8x16_t) __builtin_shuffle (__a, (uint8x16_t) { 7, 6, 5, 4, 3, 2, 1, 0, 15, 14, 13, 12, 11, 10, 9, 8 }); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vrev64q_s16 (int16x8_t __a) +{ + return (int16x8_t) __builtin_shuffle (__a, (uint16x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 }); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vrev64q_s32 (int32x4_t __a) +{ + return (int32x4_t) __builtin_shuffle (__a, (uint32x4_t) { 1, 0, 3, 2 }); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vrev64q_f32 (float32x4_t __a) +{ + return (float32x4_t) __builtin_shuffle (__a, (uint32x4_t) { 1, 0, 3, 2 }); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vrev64q_u8 (uint8x16_t __a) +{ + return (uint8x16_t) __builtin_shuffle (__a, (uint8x16_t) { 7, 6, 5, 4, 3, 2, 1, 0, 15, 14, 13, 12, 11, 10, 9, 8 }); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vrev64q_u16 (uint16x8_t __a) +{ + return (uint16x8_t) __builtin_shuffle (__a, (uint16x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 }); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vrev64q_u32 (uint32x4_t __a) +{ + return (uint32x4_t) __builtin_shuffle (__a, (uint32x4_t) { 1, 0, 3, 2 }); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vrev64q_p8 (poly8x16_t __a) +{ + return (poly8x16_t) __builtin_shuffle (__a, (uint8x16_t) { 7, 6, 5, 4, 3, 2, 1, 0, 15, 14, 13, 12, 11, 10, 9, 8 }); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vrev64q_p16 (poly16x8_t __a) +{ + return (poly16x8_t) __builtin_shuffle (__a, (uint16x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 }); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vrev32_s8 (int8x8_t __a) +{ + return (int8x8_t) __builtin_shuffle (__a, (uint8x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 }); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vrev32_s16 (int16x4_t __a) +{ + return (int16x4_t) __builtin_shuffle (__a, (uint16x4_t) { 1, 0, 3, 2 }); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vrev32_u8 (uint8x8_t __a) +{ + return (uint8x8_t) __builtin_shuffle (__a, (uint8x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 }); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vrev32_u16 (uint16x4_t __a) +{ + return (uint16x4_t) __builtin_shuffle (__a, (uint16x4_t) { 1, 0, 3, 2 }); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vrev32_p8 (poly8x8_t __a) +{ + return (poly8x8_t) __builtin_shuffle (__a, (uint8x8_t) { 3, 2, 1, 0, 7, 6, 5, 4 }); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vrev32_p16 (poly16x4_t __a) +{ + return (poly16x4_t) __builtin_shuffle (__a, (uint16x4_t) { 1, 0, 3, 2 }); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vrev32q_s8 (int8x16_t __a) +{ + return (int8x16_t) __builtin_shuffle (__a, (uint8x16_t) { 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 }); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vrev32q_s16 (int16x8_t __a) +{ + return (int16x8_t) __builtin_shuffle (__a, (uint16x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 }); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vrev32q_u8 (uint8x16_t __a) +{ + return (uint8x16_t) __builtin_shuffle (__a, (uint8x16_t) { 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 }); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vrev32q_u16 (uint16x8_t __a) +{ + return (uint16x8_t) __builtin_shuffle (__a, (uint16x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 }); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vrev32q_p8 (poly8x16_t __a) +{ + return (poly8x16_t) __builtin_shuffle (__a, (uint8x16_t) { 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 }); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vrev32q_p16 (poly16x8_t __a) +{ + return (poly16x8_t) __builtin_shuffle (__a, (uint16x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 }); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vrev16_s8 (int8x8_t __a) +{ + return (int8x8_t) __builtin_shuffle (__a, (uint8x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 }); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vrev16_u8 (uint8x8_t __a) +{ + return (uint8x8_t) __builtin_shuffle (__a, (uint8x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 }); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vrev16_p8 (poly8x8_t __a) +{ + return (poly8x8_t) __builtin_shuffle (__a, (uint8x8_t) { 1, 0, 3, 2, 5, 4, 7, 6 }); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vrev16q_s8 (int8x16_t __a) +{ + return (int8x16_t) __builtin_shuffle (__a, (uint8x16_t) { 1, 0, 3, 2, 5, 4, 7, 6, 9, 8, 11, 10, 13, 12, 15, 14 }); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vrev16q_u8 (uint8x16_t __a) +{ + return (uint8x16_t) __builtin_shuffle (__a, (uint8x16_t) { 1, 0, 3, 2, 5, 4, 7, 6, 9, 8, 11, 10, 13, 12, 15, 14 }); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vrev16q_p8 (poly8x16_t __a) +{ + return (poly8x16_t) __builtin_shuffle (__a, (uint8x16_t) { 1, 0, 3, 2, 5, 4, 7, 6, 9, 8, 11, 10, 13, 12, 15, 14 }); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vbsl_p64 (uint64x1_t __a, poly64x1_t __b, poly64x1_t __c) +{ + return (poly64x1_t)__builtin_neon_vbsldi ((int64x1_t) __a, __b, __c); +} + +#endif +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vbsl_s8 (uint8x8_t __a, int8x8_t __b, int8x8_t __c) +{ + return (int8x8_t)__builtin_neon_vbslv8qi ((int8x8_t) __a, __b, __c); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vbsl_s16 (uint16x4_t __a, int16x4_t __b, int16x4_t __c) +{ + return (int16x4_t)__builtin_neon_vbslv4hi ((int16x4_t) __a, __b, __c); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vbsl_s32 (uint32x2_t __a, int32x2_t __b, int32x2_t __c) +{ + return (int32x2_t)__builtin_neon_vbslv2si ((int32x2_t) __a, __b, __c); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vbsl_s64 (uint64x1_t __a, int64x1_t __b, int64x1_t __c) +{ + return (int64x1_t)__builtin_neon_vbsldi ((int64x1_t) __a, __b, __c); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vbsl_f32 (uint32x2_t __a, float32x2_t __b, float32x2_t __c) +{ + return (float32x2_t)__builtin_neon_vbslv2sf ((int32x2_t) __a, __b, __c); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vbsl_u8 (uint8x8_t __a, uint8x8_t __b, uint8x8_t __c) +{ + return (uint8x8_t)__builtin_neon_vbslv8qi ((int8x8_t) __a, (int8x8_t) __b, (int8x8_t) __c); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vbsl_u16 (uint16x4_t __a, uint16x4_t __b, uint16x4_t __c) +{ + return (uint16x4_t)__builtin_neon_vbslv4hi ((int16x4_t) __a, (int16x4_t) __b, (int16x4_t) __c); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vbsl_u32 (uint32x2_t __a, uint32x2_t __b, uint32x2_t __c) +{ + return (uint32x2_t)__builtin_neon_vbslv2si ((int32x2_t) __a, (int32x2_t) __b, (int32x2_t) __c); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vbsl_u64 (uint64x1_t __a, uint64x1_t __b, uint64x1_t __c) +{ + return (uint64x1_t)__builtin_neon_vbsldi ((int64x1_t) __a, (int64x1_t) __b, (int64x1_t) __c); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vbsl_p8 (uint8x8_t __a, poly8x8_t __b, poly8x8_t __c) +{ + return (poly8x8_t)__builtin_neon_vbslv8qi ((int8x8_t) __a, (int8x8_t) __b, (int8x8_t) __c); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vbsl_p16 (uint16x4_t __a, poly16x4_t __b, poly16x4_t __c) +{ + return (poly16x4_t)__builtin_neon_vbslv4hi ((int16x4_t) __a, (int16x4_t) __b, (int16x4_t) __c); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vbslq_p64 (uint64x2_t __a, poly64x2_t __b, poly64x2_t __c) +{ + return (poly64x2_t)__builtin_neon_vbslv2di ((int64x2_t) __a, (int64x2_t) __b, (int64x2_t) __c); +} + +#endif +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vbslq_s8 (uint8x16_t __a, int8x16_t __b, int8x16_t __c) +{ + return (int8x16_t)__builtin_neon_vbslv16qi ((int8x16_t) __a, __b, __c); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vbslq_s16 (uint16x8_t __a, int16x8_t __b, int16x8_t __c) +{ + return (int16x8_t)__builtin_neon_vbslv8hi ((int16x8_t) __a, __b, __c); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vbslq_s32 (uint32x4_t __a, int32x4_t __b, int32x4_t __c) +{ + return (int32x4_t)__builtin_neon_vbslv4si ((int32x4_t) __a, __b, __c); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vbslq_s64 (uint64x2_t __a, int64x2_t __b, int64x2_t __c) +{ + return (int64x2_t)__builtin_neon_vbslv2di ((int64x2_t) __a, __b, __c); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vbslq_f32 (uint32x4_t __a, float32x4_t __b, float32x4_t __c) +{ + return (float32x4_t)__builtin_neon_vbslv4sf ((int32x4_t) __a, __b, __c); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vbslq_u8 (uint8x16_t __a, uint8x16_t __b, uint8x16_t __c) +{ + return (uint8x16_t)__builtin_neon_vbslv16qi ((int8x16_t) __a, (int8x16_t) __b, (int8x16_t) __c); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vbslq_u16 (uint16x8_t __a, uint16x8_t __b, uint16x8_t __c) +{ + return (uint16x8_t)__builtin_neon_vbslv8hi ((int16x8_t) __a, (int16x8_t) __b, (int16x8_t) __c); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vbslq_u32 (uint32x4_t __a, uint32x4_t __b, uint32x4_t __c) +{ + return (uint32x4_t)__builtin_neon_vbslv4si ((int32x4_t) __a, (int32x4_t) __b, (int32x4_t) __c); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vbslq_u64 (uint64x2_t __a, uint64x2_t __b, uint64x2_t __c) +{ + return (uint64x2_t)__builtin_neon_vbslv2di ((int64x2_t) __a, (int64x2_t) __b, (int64x2_t) __c); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vbslq_p8 (uint8x16_t __a, poly8x16_t __b, poly8x16_t __c) +{ + return (poly8x16_t)__builtin_neon_vbslv16qi ((int8x16_t) __a, (int8x16_t) __b, (int8x16_t) __c); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vbslq_p16 (uint16x8_t __a, poly16x8_t __b, poly16x8_t __c) +{ + return (poly16x8_t)__builtin_neon_vbslv8hi ((int16x8_t) __a, (int16x8_t) __b, (int16x8_t) __c); +} + +/* For big-endian, the shuffle masks for ZIP, UZP and TRN must be changed as + follows. (nelt = the number of elements within a vector.) + + Firstly, a value of N within a mask, becomes (N ^ (nelt - 1)), as gcc vector + extension's indexing scheme is reversed *within each vector* (relative to the + neon intrinsics view), but without changing which of the two vectors. + + Secondly, the elements within each mask are reversed, as the mask is itself a + vector, and will itself be loaded in reverse order (again, relative to the + neon intrinsics view, i.e. that would result from a "vld1" instruction). */ + +__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) +vtrn_s8 (int8x8_t __a, int8x8_t __b) +{ + int8x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 9, 1, 11, 3, 13, 5, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 0, 10, 2, 12, 4, 14, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 1, 9, 3, 11, 5, 13, 7, 15 }); +#endif + return __rv; +} + +__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) +vtrn_s16 (int16x4_t __a, int16x4_t __b) +{ + int16x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 1, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 6, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 }); +#endif + return __rv; +} + +__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) +vtrn_u8 (uint8x8_t __a, uint8x8_t __b) +{ + uint8x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 9, 1, 11, 3, 13, 5, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 0, 10, 2, 12, 4, 14, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 1, 9, 3, 11, 5, 13, 7, 15 }); +#endif + return __rv; +} + +__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) +vtrn_u16 (uint16x4_t __a, uint16x4_t __b) +{ + uint16x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 1, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 6, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 }); +#endif + return __rv; +} + +__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) +vtrn_p8 (poly8x8_t __a, poly8x8_t __b) +{ + poly8x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 9, 1, 11, 3, 13, 5, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 0, 10, 2, 12, 4, 14, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 1, 9, 3, 11, 5, 13, 7, 15 }); +#endif + return __rv; +} + +__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) +vtrn_p16 (poly16x4_t __a, poly16x4_t __b) +{ + poly16x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 1, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 6, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 }); +#endif + return __rv; +} + +__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) +vtrn_s32 (int32x2_t __a, int32x2_t __b) +{ + int32x2x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif + return __rv; +} + +__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) +vtrn_f32 (float32x2_t __a, float32x2_t __b) +{ + float32x2x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif + return __rv; +} + +__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) +vtrn_u32 (uint32x2_t __a, uint32x2_t __b) +{ + uint32x2x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif + return __rv; +} + +__extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__)) +vtrnq_s8 (int8x16_t __a, int8x16_t __b) +{ + int8x16x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 17, 1, 19, 3, 21, 5, 23, 7, 25, 9, 27, 11, 29, 13, 31, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 0, 18, 2, 20, 4, 22, 6, 24, 8, 26, 10, 28, 12, 30, 14 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 }); +#endif + return __rv; +} + +__extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) +vtrnq_s16 (int16x8_t __a, int16x8_t __b) +{ + int16x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 9, 1, 11, 3, 13, 5, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 0, 10, 2, 12, 4, 14, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 1, 9, 3, 11, 5, 13, 7, 15 }); +#endif + return __rv; +} + +__extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) +vtrnq_s32 (int32x4_t __a, int32x4_t __b) +{ + int32x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 1, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 6, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 }); +#endif + return __rv; +} + +__extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) +vtrnq_f32 (float32x4_t __a, float32x4_t __b) +{ + float32x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 1, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 6, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 }); +#endif + return __rv; +} + +__extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__)) +vtrnq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + uint8x16x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 17, 1, 19, 3, 21, 5, 23, 7, 25, 9, 27, 11, 29, 13, 31, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 0, 18, 2, 20, 4, 22, 6, 24, 8, 26, 10, 28, 12, 30, 14 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 }); +#endif + return __rv; +} + +__extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) +vtrnq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + uint16x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 9, 1, 11, 3, 13, 5, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 0, 10, 2, 12, 4, 14, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 1, 9, 3, 11, 5, 13, 7, 15 }); +#endif + return __rv; +} + +__extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) +vtrnq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + uint32x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 1, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 6, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 }); +#endif + return __rv; +} + +__extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__)) +vtrnq_p8 (poly8x16_t __a, poly8x16_t __b) +{ + poly8x16x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 17, 1, 19, 3, 21, 5, 23, 7, 25, 9, 27, 11, 29, 13, 31, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 0, 18, 2, 20, 4, 22, 6, 24, 8, 26, 10, 28, 12, 30, 14 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 }); +#endif + return __rv; +} + +__extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) +vtrnq_p16 (poly16x8_t __a, poly16x8_t __b) +{ + poly16x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 9, 1, 11, 3, 13, 5, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 0, 10, 2, 12, 4, 14, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 1, 9, 3, 11, 5, 13, 7, 15 }); +#endif + return __rv; +} + +__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) +vzip_s8 (int8x8_t __a, int8x8_t __b) +{ + int8x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 12, 4, 13, 5, 14, 6, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 0, 9, 1, 10, 2, 11, 3 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 4, 12, 5, 13, 6, 14, 7, 15 }); +#endif + return __rv; +} + +__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) +vzip_s16 (int16x4_t __a, int16x4_t __b) +{ + int16x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 6, 2, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 5, 1 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 }); +#endif + return __rv; +} + +__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) +vzip_u8 (uint8x8_t __a, uint8x8_t __b) +{ + uint8x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 12, 4, 13, 5, 14, 6, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 0, 9, 1, 10, 2, 11, 3 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 4, 12, 5, 13, 6, 14, 7, 15 }); +#endif + return __rv; +} + +__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) +vzip_u16 (uint16x4_t __a, uint16x4_t __b) +{ + uint16x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 6, 2, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 5, 1 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 }); +#endif + return __rv; +} + +__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) +vzip_p8 (poly8x8_t __a, poly8x8_t __b) +{ + poly8x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 12, 4, 13, 5, 14, 6, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 0, 9, 1, 10, 2, 11, 3 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 4, 12, 5, 13, 6, 14, 7, 15 }); +#endif + return __rv; +} + +__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) +vzip_p16 (poly16x4_t __a, poly16x4_t __b) +{ + poly16x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 6, 2, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 5, 1 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 }); +#endif + return __rv; +} + +__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) +vzip_s32 (int32x2_t __a, int32x2_t __b) +{ + int32x2x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif + return __rv; +} + +__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) +vzip_f32 (float32x2_t __a, float32x2_t __b) +{ + float32x2x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif + return __rv; +} + +__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) +vzip_u32 (uint32x2_t __a, uint32x2_t __b) +{ + uint32x2x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif + return __rv; +} + +__extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__)) +vzipq_s8 (int8x16_t __a, int8x16_t __b) +{ + int8x16x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 24, 8, 25, 9, 26, 10, 27, 11, 28, 12, 29, 13, 30, 14, 31, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 0, 17, 1, 18, 2, 19, 3, 20, 4, 21, 5, 22, 6, 23, 7 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 }); +#endif + return __rv; +} + +__extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) +vzipq_s16 (int16x8_t __a, int16x8_t __b) +{ + int16x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 12, 4, 13, 5, 14, 6, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 0, 9, 1, 10, 2, 11, 3 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 4, 12, 5, 13, 6, 14, 7, 15 }); +#endif + return __rv; +} + +__extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) +vzipq_s32 (int32x4_t __a, int32x4_t __b) +{ + int32x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 6, 2, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 5, 1 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 }); +#endif + return __rv; +} + +__extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) +vzipq_f32 (float32x4_t __a, float32x4_t __b) +{ + float32x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 6, 2, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 5, 1 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 }); +#endif + return __rv; +} + +__extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__)) +vzipq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + uint8x16x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 24, 8, 25, 9, 26, 10, 27, 11, 28, 12, 29, 13, 30, 14, 31, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 0, 17, 1, 18, 2, 19, 3, 20, 4, 21, 5, 22, 6, 23, 7 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 }); +#endif + return __rv; +} + +__extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) +vzipq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + uint16x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 12, 4, 13, 5, 14, 6, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 0, 9, 1, 10, 2, 11, 3 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 4, 12, 5, 13, 6, 14, 7, 15 }); +#endif + return __rv; +} + +__extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) +vzipq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + uint32x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 6, 2, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 5, 1 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 }); +#endif + return __rv; +} + +__extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__)) +vzipq_p8 (poly8x16_t __a, poly8x16_t __b) +{ + poly8x16x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 24, 8, 25, 9, 26, 10, 27, 11, 28, 12, 29, 13, 30, 14, 31, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 0, 17, 1, 18, 2, 19, 3, 20, 4, 21, 5, 22, 6, 23, 7 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 }); +#endif + return __rv; +} + +__extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) +vzipq_p16 (poly16x8_t __a, poly16x8_t __b) +{ + poly16x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 12, 4, 13, 5, 14, 6, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 0, 9, 1, 10, 2, 11, 3 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 4, 12, 5, 13, 6, 14, 7, 15 }); +#endif + return __rv; +} + +__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) +vuzp_s8 (int8x8_t __a, int8x8_t __b) +{ + int8x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 9, 11, 13, 15, 1, 3, 5, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 10, 12, 14, 0, 2, 4, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 1, 3, 5, 7, 9, 11, 13, 15 }); +#endif + return __rv; +} + +__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) +vuzp_s16 (int16x4_t __a, int16x4_t __b) +{ + int16x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 7, 1, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 6, 0, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 }); +#endif + return __rv; +} + +__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) +vuzp_s32 (int32x2_t __a, int32x2_t __b) +{ + int32x2x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif + return __rv; +} + +__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) +vuzp_f32 (float32x2_t __a, float32x2_t __b) +{ + float32x2x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif + return __rv; +} + +__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) +vuzp_u8 (uint8x8_t __a, uint8x8_t __b) +{ + uint8x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 9, 11, 13, 15, 1, 3, 5, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 10, 12, 14, 0, 2, 4, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 1, 3, 5, 7, 9, 11, 13, 15 }); +#endif + return __rv; +} + +__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) +vuzp_u16 (uint16x4_t __a, uint16x4_t __b) +{ + uint16x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 7, 1, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 6, 0, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 }); +#endif + return __rv; +} + +__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) +vuzp_u32 (uint32x2_t __a, uint32x2_t __b) +{ + uint32x2x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif + return __rv; +} + +__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) +vuzp_p8 (poly8x8_t __a, poly8x8_t __b) +{ + poly8x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 9, 11, 13, 15, 1, 3, 5, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 10, 12, 14, 0, 2, 4, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 1, 3, 5, 7, 9, 11, 13, 15 }); +#endif + return __rv; +} + +__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) +vuzp_p16 (poly16x4_t __a, poly16x4_t __b) +{ + poly16x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 7, 1, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 6, 0, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 }); +#endif + return __rv; +} + +__extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__)) +vuzpq_s8 (int8x16_t __a, int8x16_t __b) +{ + int8x16x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 17, 19, 21, 23, 25, 27, 29, 31, 1, 3, 5, 7, 9, 11, 13, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 18, 20, 22, 24, 26, 28, 30, 0, 2, 4, 6, 8, 10, 12, 14 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 }); +#endif + return __rv; +} + +__extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) +vuzpq_s16 (int16x8_t __a, int16x8_t __b) +{ + int16x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 9, 11, 13, 15, 1, 3, 5, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 10, 12, 14, 0, 2, 4, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 1, 3, 5, 7, 9, 11, 13, 15 }); +#endif + return __rv; +} + +__extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) +vuzpq_s32 (int32x4_t __a, int32x4_t __b) +{ + int32x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 7, 1, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 6, 0, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 }); +#endif + return __rv; +} + +__extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) +vuzpq_f32 (float32x4_t __a, float32x4_t __b) +{ + float32x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 7, 1, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 6, 0, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 }); +#endif + return __rv; +} + +__extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__)) +vuzpq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + uint8x16x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 17, 19, 21, 23, 25, 27, 29, 31, 1, 3, 5, 7, 9, 11, 13, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 18, 20, 22, 24, 26, 28, 30, 0, 2, 4, 6, 8, 10, 12, 14 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 }); +#endif + return __rv; +} + +__extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) +vuzpq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + uint16x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 9, 11, 13, 15, 1, 3, 5, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 10, 12, 14, 0, 2, 4, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 1, 3, 5, 7, 9, 11, 13, 15 }); +#endif + return __rv; +} + +__extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) +vuzpq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + uint32x4x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 7, 1, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 6, 0, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 }); +#endif + return __rv; +} + +__extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__)) +vuzpq_p8 (poly8x16_t __a, poly8x16_t __b) +{ + poly8x16x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 17, 19, 21, 23, 25, 27, 29, 31, 1, 3, 5, 7, 9, 11, 13, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 18, 20, 22, 24, 26, 28, 30, 0, 2, 4, 6, 8, 10, 12, 14 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 }); +#endif + return __rv; +} + +__extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) +vuzpq_p16 (poly16x8_t __a, poly16x8_t __b) +{ + poly16x8x2_t __rv; +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 9, 11, 13, 15, 1, 3, 5, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 10, 12, 14, 0, 2, 4, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 1, 3, 5, 7, 9, 11, 13, 15 }); +#endif + return __rv; +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vld1_p64 (const poly64_t * __a) +{ + return (poly64x1_t)__builtin_neon_vld1di ((const __builtin_neon_di *) __a); +} + +#endif +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vld1_s8 (const int8_t * __a) +{ + return (int8x8_t)__builtin_neon_vld1v8qi ((const __builtin_neon_qi *) __a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vld1_s16 (const int16_t * __a) +{ + return (int16x4_t)__builtin_neon_vld1v4hi ((const __builtin_neon_hi *) __a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vld1_s32 (const int32_t * __a) +{ + return (int32x2_t)__builtin_neon_vld1v2si ((const __builtin_neon_si *) __a); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vld1_s64 (const int64_t * __a) +{ + return (int64x1_t)__builtin_neon_vld1di ((const __builtin_neon_di *) __a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vld1_f32 (const float32_t * __a) +{ + return (float32x2_t)__builtin_neon_vld1v2sf ((const __builtin_neon_sf *) __a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vld1_u8 (const uint8_t * __a) +{ + return (uint8x8_t)__builtin_neon_vld1v8qi ((const __builtin_neon_qi *) __a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vld1_u16 (const uint16_t * __a) +{ + return (uint16x4_t)__builtin_neon_vld1v4hi ((const __builtin_neon_hi *) __a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vld1_u32 (const uint32_t * __a) +{ + return (uint32x2_t)__builtin_neon_vld1v2si ((const __builtin_neon_si *) __a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vld1_u64 (const uint64_t * __a) +{ + return (uint64x1_t)__builtin_neon_vld1di ((const __builtin_neon_di *) __a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vld1_p8 (const poly8_t * __a) +{ + return (poly8x8_t)__builtin_neon_vld1v8qi ((const __builtin_neon_qi *) __a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vld1_p16 (const poly16_t * __a) +{ + return (poly16x4_t)__builtin_neon_vld1v4hi ((const __builtin_neon_hi *) __a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vld1q_p64 (const poly64_t * __a) +{ + return (poly64x2_t)__builtin_neon_vld1v2di ((const __builtin_neon_di *) __a); +} + +#endif +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vld1q_s8 (const int8_t * __a) +{ + return (int8x16_t)__builtin_neon_vld1v16qi ((const __builtin_neon_qi *) __a); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vld1q_s16 (const int16_t * __a) +{ + return (int16x8_t)__builtin_neon_vld1v8hi ((const __builtin_neon_hi *) __a); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vld1q_s32 (const int32_t * __a) +{ + return (int32x4_t)__builtin_neon_vld1v4si ((const __builtin_neon_si *) __a); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vld1q_s64 (const int64_t * __a) +{ + return (int64x2_t)__builtin_neon_vld1v2di ((const __builtin_neon_di *) __a); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vld1q_f32 (const float32_t * __a) +{ + return (float32x4_t)__builtin_neon_vld1v4sf ((const __builtin_neon_sf *) __a); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vld1q_u8 (const uint8_t * __a) +{ + return (uint8x16_t)__builtin_neon_vld1v16qi ((const __builtin_neon_qi *) __a); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vld1q_u16 (const uint16_t * __a) +{ + return (uint16x8_t)__builtin_neon_vld1v8hi ((const __builtin_neon_hi *) __a); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vld1q_u32 (const uint32_t * __a) +{ + return (uint32x4_t)__builtin_neon_vld1v4si ((const __builtin_neon_si *) __a); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vld1q_u64 (const uint64_t * __a) +{ + return (uint64x2_t)__builtin_neon_vld1v2di ((const __builtin_neon_di *) __a); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vld1q_p8 (const poly8_t * __a) +{ + return (poly8x16_t)__builtin_neon_vld1v16qi ((const __builtin_neon_qi *) __a); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vld1q_p16 (const poly16_t * __a) +{ + return (poly16x8_t)__builtin_neon_vld1v8hi ((const __builtin_neon_hi *) __a); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vld1_lane_s8 (const int8_t * __a, int8x8_t __b, const int __c) +{ + return (int8x8_t)__builtin_neon_vld1_lanev8qi ((const __builtin_neon_qi *) __a, __b, __c); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vld1_lane_s16 (const int16_t * __a, int16x4_t __b, const int __c) +{ + return (int16x4_t)__builtin_neon_vld1_lanev4hi ((const __builtin_neon_hi *) __a, __b, __c); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vld1_lane_s32 (const int32_t * __a, int32x2_t __b, const int __c) +{ + return (int32x2_t)__builtin_neon_vld1_lanev2si ((const __builtin_neon_si *) __a, __b, __c); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vld1_lane_f32 (const float32_t * __a, float32x2_t __b, const int __c) +{ + return (float32x2_t)__builtin_neon_vld1_lanev2sf ((const __builtin_neon_sf *) __a, __b, __c); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vld1_lane_u8 (const uint8_t * __a, uint8x8_t __b, const int __c) +{ + return (uint8x8_t)__builtin_neon_vld1_lanev8qi ((const __builtin_neon_qi *) __a, (int8x8_t) __b, __c); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vld1_lane_u16 (const uint16_t * __a, uint16x4_t __b, const int __c) +{ + return (uint16x4_t)__builtin_neon_vld1_lanev4hi ((const __builtin_neon_hi *) __a, (int16x4_t) __b, __c); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vld1_lane_u32 (const uint32_t * __a, uint32x2_t __b, const int __c) +{ + return (uint32x2_t)__builtin_neon_vld1_lanev2si ((const __builtin_neon_si *) __a, (int32x2_t) __b, __c); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vld1_lane_p8 (const poly8_t * __a, poly8x8_t __b, const int __c) +{ + return (poly8x8_t)__builtin_neon_vld1_lanev8qi ((const __builtin_neon_qi *) __a, (int8x8_t) __b, __c); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vld1_lane_p16 (const poly16_t * __a, poly16x4_t __b, const int __c) +{ + return (poly16x4_t)__builtin_neon_vld1_lanev4hi ((const __builtin_neon_hi *) __a, (int16x4_t) __b, __c); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vld1_lane_p64 (const poly64_t * __a, poly64x1_t __b, const int __c) +{ + return (poly64x1_t)__builtin_neon_vld1_lanedi ((const __builtin_neon_di *) __a, __b, __c); +} + +#endif +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vld1_lane_s64 (const int64_t * __a, int64x1_t __b, const int __c) +{ + return (int64x1_t)__builtin_neon_vld1_lanedi ((const __builtin_neon_di *) __a, __b, __c); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vld1_lane_u64 (const uint64_t * __a, uint64x1_t __b, const int __c) +{ + return (uint64x1_t)__builtin_neon_vld1_lanedi ((const __builtin_neon_di *) __a, (int64x1_t) __b, __c); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vld1q_lane_s8 (const int8_t * __a, int8x16_t __b, const int __c) +{ + return (int8x16_t)__builtin_neon_vld1_lanev16qi ((const __builtin_neon_qi *) __a, __b, __c); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vld1q_lane_s16 (const int16_t * __a, int16x8_t __b, const int __c) +{ + return (int16x8_t)__builtin_neon_vld1_lanev8hi ((const __builtin_neon_hi *) __a, __b, __c); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vld1q_lane_s32 (const int32_t * __a, int32x4_t __b, const int __c) +{ + return (int32x4_t)__builtin_neon_vld1_lanev4si ((const __builtin_neon_si *) __a, __b, __c); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vld1q_lane_f32 (const float32_t * __a, float32x4_t __b, const int __c) +{ + return (float32x4_t)__builtin_neon_vld1_lanev4sf ((const __builtin_neon_sf *) __a, __b, __c); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vld1q_lane_u8 (const uint8_t * __a, uint8x16_t __b, const int __c) +{ + return (uint8x16_t)__builtin_neon_vld1_lanev16qi ((const __builtin_neon_qi *) __a, (int8x16_t) __b, __c); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vld1q_lane_u16 (const uint16_t * __a, uint16x8_t __b, const int __c) +{ + return (uint16x8_t)__builtin_neon_vld1_lanev8hi ((const __builtin_neon_hi *) __a, (int16x8_t) __b, __c); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vld1q_lane_u32 (const uint32_t * __a, uint32x4_t __b, const int __c) +{ + return (uint32x4_t)__builtin_neon_vld1_lanev4si ((const __builtin_neon_si *) __a, (int32x4_t) __b, __c); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vld1q_lane_p8 (const poly8_t * __a, poly8x16_t __b, const int __c) +{ + return (poly8x16_t)__builtin_neon_vld1_lanev16qi ((const __builtin_neon_qi *) __a, (int8x16_t) __b, __c); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vld1q_lane_p16 (const poly16_t * __a, poly16x8_t __b, const int __c) +{ + return (poly16x8_t)__builtin_neon_vld1_lanev8hi ((const __builtin_neon_hi *) __a, (int16x8_t) __b, __c); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vld1q_lane_p64 (const poly64_t * __a, poly64x2_t __b, const int __c) +{ + return (poly64x2_t)__builtin_neon_vld1_lanev2di ((const __builtin_neon_di *) __a, (int64x2_t) __b, __c); +} + +#endif +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vld1q_lane_s64 (const int64_t * __a, int64x2_t __b, const int __c) +{ + return (int64x2_t)__builtin_neon_vld1_lanev2di ((const __builtin_neon_di *) __a, __b, __c); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vld1q_lane_u64 (const uint64_t * __a, uint64x2_t __b, const int __c) +{ + return (uint64x2_t)__builtin_neon_vld1_lanev2di ((const __builtin_neon_di *) __a, (int64x2_t) __b, __c); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vld1_dup_s8 (const int8_t * __a) +{ + return (int8x8_t)__builtin_neon_vld1_dupv8qi ((const __builtin_neon_qi *) __a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vld1_dup_s16 (const int16_t * __a) +{ + return (int16x4_t)__builtin_neon_vld1_dupv4hi ((const __builtin_neon_hi *) __a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vld1_dup_s32 (const int32_t * __a) +{ + return (int32x2_t)__builtin_neon_vld1_dupv2si ((const __builtin_neon_si *) __a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vld1_dup_f32 (const float32_t * __a) +{ + return (float32x2_t)__builtin_neon_vld1_dupv2sf ((const __builtin_neon_sf *) __a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vld1_dup_u8 (const uint8_t * __a) +{ + return (uint8x8_t)__builtin_neon_vld1_dupv8qi ((const __builtin_neon_qi *) __a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vld1_dup_u16 (const uint16_t * __a) +{ + return (uint16x4_t)__builtin_neon_vld1_dupv4hi ((const __builtin_neon_hi *) __a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vld1_dup_u32 (const uint32_t * __a) +{ + return (uint32x2_t)__builtin_neon_vld1_dupv2si ((const __builtin_neon_si *) __a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vld1_dup_p8 (const poly8_t * __a) +{ + return (poly8x8_t)__builtin_neon_vld1_dupv8qi ((const __builtin_neon_qi *) __a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vld1_dup_p16 (const poly16_t * __a) +{ + return (poly16x4_t)__builtin_neon_vld1_dupv4hi ((const __builtin_neon_hi *) __a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vld1_dup_p64 (const poly64_t * __a) +{ + return (poly64x1_t)__builtin_neon_vld1_dupdi ((const __builtin_neon_di *) __a); +} + +#endif +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vld1_dup_s64 (const int64_t * __a) +{ + return (int64x1_t)__builtin_neon_vld1_dupdi ((const __builtin_neon_di *) __a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vld1_dup_u64 (const uint64_t * __a) +{ + return (uint64x1_t)__builtin_neon_vld1_dupdi ((const __builtin_neon_di *) __a); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vld1q_dup_s8 (const int8_t * __a) +{ + return (int8x16_t)__builtin_neon_vld1_dupv16qi ((const __builtin_neon_qi *) __a); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vld1q_dup_s16 (const int16_t * __a) +{ + return (int16x8_t)__builtin_neon_vld1_dupv8hi ((const __builtin_neon_hi *) __a); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vld1q_dup_s32 (const int32_t * __a) +{ + return (int32x4_t)__builtin_neon_vld1_dupv4si ((const __builtin_neon_si *) __a); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vld1q_dup_f32 (const float32_t * __a) +{ + return (float32x4_t)__builtin_neon_vld1_dupv4sf ((const __builtin_neon_sf *) __a); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vld1q_dup_u8 (const uint8_t * __a) +{ + return (uint8x16_t)__builtin_neon_vld1_dupv16qi ((const __builtin_neon_qi *) __a); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vld1q_dup_u16 (const uint16_t * __a) +{ + return (uint16x8_t)__builtin_neon_vld1_dupv8hi ((const __builtin_neon_hi *) __a); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vld1q_dup_u32 (const uint32_t * __a) +{ + return (uint32x4_t)__builtin_neon_vld1_dupv4si ((const __builtin_neon_si *) __a); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vld1q_dup_p8 (const poly8_t * __a) +{ + return (poly8x16_t)__builtin_neon_vld1_dupv16qi ((const __builtin_neon_qi *) __a); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vld1q_dup_p16 (const poly16_t * __a) +{ + return (poly16x8_t)__builtin_neon_vld1_dupv8hi ((const __builtin_neon_hi *) __a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vld1q_dup_p64 (const poly64_t * __a) +{ + return (poly64x2_t)__builtin_neon_vld1_dupv2di ((const __builtin_neon_di *) __a); +} + +#endif +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vld1q_dup_s64 (const int64_t * __a) +{ + return (int64x2_t)__builtin_neon_vld1_dupv2di ((const __builtin_neon_di *) __a); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vld1q_dup_u64 (const uint64_t * __a) +{ + return (uint64x2_t)__builtin_neon_vld1_dupv2di ((const __builtin_neon_di *) __a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_p64 (poly64_t * __a, poly64x1_t __b) +{ + __builtin_neon_vst1di ((__builtin_neon_di *) __a, __b); +} + +#endif +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_s8 (int8_t * __a, int8x8_t __b) +{ + __builtin_neon_vst1v8qi ((__builtin_neon_qi *) __a, __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_s16 (int16_t * __a, int16x4_t __b) +{ + __builtin_neon_vst1v4hi ((__builtin_neon_hi *) __a, __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_s32 (int32_t * __a, int32x2_t __b) +{ + __builtin_neon_vst1v2si ((__builtin_neon_si *) __a, __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_s64 (int64_t * __a, int64x1_t __b) +{ + __builtin_neon_vst1di ((__builtin_neon_di *) __a, __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_f32 (float32_t * __a, float32x2_t __b) +{ + __builtin_neon_vst1v2sf ((__builtin_neon_sf *) __a, __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_u8 (uint8_t * __a, uint8x8_t __b) +{ + __builtin_neon_vst1v8qi ((__builtin_neon_qi *) __a, (int8x8_t) __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_u16 (uint16_t * __a, uint16x4_t __b) +{ + __builtin_neon_vst1v4hi ((__builtin_neon_hi *) __a, (int16x4_t) __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_u32 (uint32_t * __a, uint32x2_t __b) +{ + __builtin_neon_vst1v2si ((__builtin_neon_si *) __a, (int32x2_t) __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_u64 (uint64_t * __a, uint64x1_t __b) +{ + __builtin_neon_vst1di ((__builtin_neon_di *) __a, (int64x1_t) __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_p8 (poly8_t * __a, poly8x8_t __b) +{ + __builtin_neon_vst1v8qi ((__builtin_neon_qi *) __a, (int8x8_t) __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_p16 (poly16_t * __a, poly16x4_t __b) +{ + __builtin_neon_vst1v4hi ((__builtin_neon_hi *) __a, (int16x4_t) __b); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_p64 (poly64_t * __a, poly64x2_t __b) +{ + __builtin_neon_vst1v2di ((__builtin_neon_di *) __a, (int64x2_t) __b); +} + +#endif +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_s8 (int8_t * __a, int8x16_t __b) +{ + __builtin_neon_vst1v16qi ((__builtin_neon_qi *) __a, __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_s16 (int16_t * __a, int16x8_t __b) +{ + __builtin_neon_vst1v8hi ((__builtin_neon_hi *) __a, __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_s32 (int32_t * __a, int32x4_t __b) +{ + __builtin_neon_vst1v4si ((__builtin_neon_si *) __a, __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_s64 (int64_t * __a, int64x2_t __b) +{ + __builtin_neon_vst1v2di ((__builtin_neon_di *) __a, __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_f32 (float32_t * __a, float32x4_t __b) +{ + __builtin_neon_vst1v4sf ((__builtin_neon_sf *) __a, __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_u8 (uint8_t * __a, uint8x16_t __b) +{ + __builtin_neon_vst1v16qi ((__builtin_neon_qi *) __a, (int8x16_t) __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_u16 (uint16_t * __a, uint16x8_t __b) +{ + __builtin_neon_vst1v8hi ((__builtin_neon_hi *) __a, (int16x8_t) __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_u32 (uint32_t * __a, uint32x4_t __b) +{ + __builtin_neon_vst1v4si ((__builtin_neon_si *) __a, (int32x4_t) __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_u64 (uint64_t * __a, uint64x2_t __b) +{ + __builtin_neon_vst1v2di ((__builtin_neon_di *) __a, (int64x2_t) __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_p8 (poly8_t * __a, poly8x16_t __b) +{ + __builtin_neon_vst1v16qi ((__builtin_neon_qi *) __a, (int8x16_t) __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_p16 (poly16_t * __a, poly16x8_t __b) +{ + __builtin_neon_vst1v8hi ((__builtin_neon_hi *) __a, (int16x8_t) __b); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_lane_s8 (int8_t * __a, int8x8_t __b, const int __c) +{ + __builtin_neon_vst1_lanev8qi ((__builtin_neon_qi *) __a, __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_lane_s16 (int16_t * __a, int16x4_t __b, const int __c) +{ + __builtin_neon_vst1_lanev4hi ((__builtin_neon_hi *) __a, __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_lane_s32 (int32_t * __a, int32x2_t __b, const int __c) +{ + __builtin_neon_vst1_lanev2si ((__builtin_neon_si *) __a, __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_lane_f32 (float32_t * __a, float32x2_t __b, const int __c) +{ + __builtin_neon_vst1_lanev2sf ((__builtin_neon_sf *) __a, __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_lane_u8 (uint8_t * __a, uint8x8_t __b, const int __c) +{ + __builtin_neon_vst1_lanev8qi ((__builtin_neon_qi *) __a, (int8x8_t) __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_lane_u16 (uint16_t * __a, uint16x4_t __b, const int __c) +{ + __builtin_neon_vst1_lanev4hi ((__builtin_neon_hi *) __a, (int16x4_t) __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_lane_u32 (uint32_t * __a, uint32x2_t __b, const int __c) +{ + __builtin_neon_vst1_lanev2si ((__builtin_neon_si *) __a, (int32x2_t) __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_lane_p8 (poly8_t * __a, poly8x8_t __b, const int __c) +{ + __builtin_neon_vst1_lanev8qi ((__builtin_neon_qi *) __a, (int8x8_t) __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_lane_p16 (poly16_t * __a, poly16x4_t __b, const int __c) +{ + __builtin_neon_vst1_lanev4hi ((__builtin_neon_hi *) __a, (int16x4_t) __b, __c); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_lane_p64 (poly64_t * __a, poly64x1_t __b, const int __c) +{ + __builtin_neon_vst1_lanedi ((__builtin_neon_di *) __a, __b, __c); +} + +#endif +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_lane_s64 (int64_t * __a, int64x1_t __b, const int __c) +{ + __builtin_neon_vst1_lanedi ((__builtin_neon_di *) __a, __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1_lane_u64 (uint64_t * __a, uint64x1_t __b, const int __c) +{ + __builtin_neon_vst1_lanedi ((__builtin_neon_di *) __a, (int64x1_t) __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_lane_s8 (int8_t * __a, int8x16_t __b, const int __c) +{ + __builtin_neon_vst1_lanev16qi ((__builtin_neon_qi *) __a, __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_lane_s16 (int16_t * __a, int16x8_t __b, const int __c) +{ + __builtin_neon_vst1_lanev8hi ((__builtin_neon_hi *) __a, __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_lane_s32 (int32_t * __a, int32x4_t __b, const int __c) +{ + __builtin_neon_vst1_lanev4si ((__builtin_neon_si *) __a, __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_lane_f32 (float32_t * __a, float32x4_t __b, const int __c) +{ + __builtin_neon_vst1_lanev4sf ((__builtin_neon_sf *) __a, __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_lane_u8 (uint8_t * __a, uint8x16_t __b, const int __c) +{ + __builtin_neon_vst1_lanev16qi ((__builtin_neon_qi *) __a, (int8x16_t) __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_lane_u16 (uint16_t * __a, uint16x8_t __b, const int __c) +{ + __builtin_neon_vst1_lanev8hi ((__builtin_neon_hi *) __a, (int16x8_t) __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_lane_u32 (uint32_t * __a, uint32x4_t __b, const int __c) +{ + __builtin_neon_vst1_lanev4si ((__builtin_neon_si *) __a, (int32x4_t) __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_lane_p8 (poly8_t * __a, poly8x16_t __b, const int __c) +{ + __builtin_neon_vst1_lanev16qi ((__builtin_neon_qi *) __a, (int8x16_t) __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_lane_p16 (poly16_t * __a, poly16x8_t __b, const int __c) +{ + __builtin_neon_vst1_lanev8hi ((__builtin_neon_hi *) __a, (int16x8_t) __b, __c); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_lane_p64 (poly64_t * __a, poly64x2_t __b, const int __c) +{ + __builtin_neon_vst1_lanev2di ((__builtin_neon_di *) __a, (int64x2_t) __b, __c); +} + +#endif +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_lane_s64 (int64_t * __a, int64x2_t __b, const int __c) +{ + __builtin_neon_vst1_lanev2di ((__builtin_neon_di *) __a, __b, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst1q_lane_u64 (uint64_t * __a, uint64x2_t __b, const int __c) +{ + __builtin_neon_vst1_lanev2di ((__builtin_neon_di *) __a, (int64x2_t) __b, __c); +} + +__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) +vld2_s8 (const int8_t * __a) +{ + union { int8x8x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2v8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) +vld2_s16 (const int16_t * __a) +{ + union { int16x4x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2v4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) +vld2_s32 (const int32_t * __a) +{ + union { int32x2x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2v2si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) +vld2_f32 (const float32_t * __a) +{ + union { float32x2x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2v2sf ((const __builtin_neon_sf *) __a); + return __rv.__i; +} + +__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) +vld2_u8 (const uint8_t * __a) +{ + union { uint8x8x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2v8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) +vld2_u16 (const uint16_t * __a) +{ + union { uint16x4x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2v4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) +vld2_u32 (const uint32_t * __a) +{ + union { uint32x2x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2v2si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) +vld2_p8 (const poly8_t * __a) +{ + union { poly8x8x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2v8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) +vld2_p16 (const poly16_t * __a) +{ + union { poly16x4x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2v4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1x2_t __attribute__ ((__always_inline__)) +vld2_p64 (const poly64_t * __a) +{ + union { poly64x1x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2di ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +#endif +__extension__ static __inline int64x1x2_t __attribute__ ((__always_inline__)) +vld2_s64 (const int64_t * __a) +{ + union { int64x1x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2di ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +__extension__ static __inline uint64x1x2_t __attribute__ ((__always_inline__)) +vld2_u64 (const uint64_t * __a) +{ + union { uint64x1x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2di ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +__extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__)) +vld2q_s8 (const int8_t * __a) +{ + union { int8x16x2_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld2v16qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) +vld2q_s16 (const int16_t * __a) +{ + union { int16x8x2_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld2v8hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) +vld2q_s32 (const int32_t * __a) +{ + union { int32x4x2_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld2v4si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) +vld2q_f32 (const float32_t * __a) +{ + union { float32x4x2_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld2v4sf ((const __builtin_neon_sf *) __a); + return __rv.__i; +} + +__extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__)) +vld2q_u8 (const uint8_t * __a) +{ + union { uint8x16x2_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld2v16qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) +vld2q_u16 (const uint16_t * __a) +{ + union { uint16x8x2_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld2v8hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) +vld2q_u32 (const uint32_t * __a) +{ + union { uint32x4x2_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld2v4si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__)) +vld2q_p8 (const poly8_t * __a) +{ + union { poly8x16x2_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld2v16qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) +vld2q_p16 (const poly16_t * __a) +{ + union { poly16x8x2_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld2v8hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) +vld2_lane_s8 (const int8_t * __a, int8x8x2_t __b, const int __c) +{ + union { int8x8x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + union { int8x8x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_lanev8qi ((const __builtin_neon_qi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) +vld2_lane_s16 (const int16_t * __a, int16x4x2_t __b, const int __c) +{ + union { int16x4x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + union { int16x4x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_lanev4hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) +vld2_lane_s32 (const int32_t * __a, int32x2x2_t __b, const int __c) +{ + union { int32x2x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + union { int32x2x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_lanev2si ((const __builtin_neon_si *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) +vld2_lane_f32 (const float32_t * __a, float32x2x2_t __b, const int __c) +{ + union { float32x2x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + union { float32x2x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_lanev2sf ((const __builtin_neon_sf *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) +vld2_lane_u8 (const uint8_t * __a, uint8x8x2_t __b, const int __c) +{ + union { uint8x8x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + union { uint8x8x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_lanev8qi ((const __builtin_neon_qi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) +vld2_lane_u16 (const uint16_t * __a, uint16x4x2_t __b, const int __c) +{ + union { uint16x4x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + union { uint16x4x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_lanev4hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) +vld2_lane_u32 (const uint32_t * __a, uint32x2x2_t __b, const int __c) +{ + union { uint32x2x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + union { uint32x2x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_lanev2si ((const __builtin_neon_si *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) +vld2_lane_p8 (const poly8_t * __a, poly8x8x2_t __b, const int __c) +{ + union { poly8x8x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + union { poly8x8x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_lanev8qi ((const __builtin_neon_qi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) +vld2_lane_p16 (const poly16_t * __a, poly16x4x2_t __b, const int __c) +{ + union { poly16x4x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + union { poly16x4x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_lanev4hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) +vld2q_lane_s16 (const int16_t * __a, int16x8x2_t __b, const int __c) +{ + union { int16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + union { int16x8x2_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld2_lanev8hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) +vld2q_lane_s32 (const int32_t * __a, int32x4x2_t __b, const int __c) +{ + union { int32x4x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + union { int32x4x2_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld2_lanev4si ((const __builtin_neon_si *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) +vld2q_lane_f32 (const float32_t * __a, float32x4x2_t __b, const int __c) +{ + union { float32x4x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + union { float32x4x2_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld2_lanev4sf ((const __builtin_neon_sf *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) +vld2q_lane_u16 (const uint16_t * __a, uint16x8x2_t __b, const int __c) +{ + union { uint16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + union { uint16x8x2_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld2_lanev8hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) +vld2q_lane_u32 (const uint32_t * __a, uint32x4x2_t __b, const int __c) +{ + union { uint32x4x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + union { uint32x4x2_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld2_lanev4si ((const __builtin_neon_si *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) +vld2q_lane_p16 (const poly16_t * __a, poly16x8x2_t __b, const int __c) +{ + union { poly16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + union { poly16x8x2_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld2_lanev8hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) +vld2_dup_s8 (const int8_t * __a) +{ + union { int8x8x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_dupv8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) +vld2_dup_s16 (const int16_t * __a) +{ + union { int16x4x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_dupv4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) +vld2_dup_s32 (const int32_t * __a) +{ + union { int32x2x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_dupv2si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) +vld2_dup_f32 (const float32_t * __a) +{ + union { float32x2x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_dupv2sf ((const __builtin_neon_sf *) __a); + return __rv.__i; +} + +__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) +vld2_dup_u8 (const uint8_t * __a) +{ + union { uint8x8x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_dupv8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) +vld2_dup_u16 (const uint16_t * __a) +{ + union { uint16x4x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_dupv4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) +vld2_dup_u32 (const uint32_t * __a) +{ + union { uint32x2x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_dupv2si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) +vld2_dup_p8 (const poly8_t * __a) +{ + union { poly8x8x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_dupv8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) +vld2_dup_p16 (const poly16_t * __a) +{ + union { poly16x4x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_dupv4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1x2_t __attribute__ ((__always_inline__)) +vld2_dup_p64 (const poly64_t * __a) +{ + union { poly64x1x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_dupdi ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +#endif +__extension__ static __inline int64x1x2_t __attribute__ ((__always_inline__)) +vld2_dup_s64 (const int64_t * __a) +{ + union { int64x1x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_dupdi ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +__extension__ static __inline uint64x1x2_t __attribute__ ((__always_inline__)) +vld2_dup_u64 (const uint64_t * __a) +{ + union { uint64x1x2_t __i; __builtin_neon_ti __o; } __rv; + __rv.__o = __builtin_neon_vld2_dupdi ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_s8 (int8_t * __a, int8x8x2_t __b) +{ + union { int8x8x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2v8qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_s16 (int16_t * __a, int16x4x2_t __b) +{ + union { int16x4x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2v4hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_s32 (int32_t * __a, int32x2x2_t __b) +{ + union { int32x2x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2v2si ((__builtin_neon_si *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_f32 (float32_t * __a, float32x2x2_t __b) +{ + union { float32x2x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2v2sf ((__builtin_neon_sf *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_u8 (uint8_t * __a, uint8x8x2_t __b) +{ + union { uint8x8x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2v8qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_u16 (uint16_t * __a, uint16x4x2_t __b) +{ + union { uint16x4x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2v4hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_u32 (uint32_t * __a, uint32x2x2_t __b) +{ + union { uint32x2x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2v2si ((__builtin_neon_si *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_p8 (poly8_t * __a, poly8x8x2_t __b) +{ + union { poly8x8x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2v8qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_p16 (poly16_t * __a, poly16x4x2_t __b) +{ + union { poly16x4x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2v4hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_p64 (poly64_t * __a, poly64x1x2_t __b) +{ + union { poly64x1x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2di ((__builtin_neon_di *) __a, __bu.__o); +} + +#endif +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_s64 (int64_t * __a, int64x1x2_t __b) +{ + union { int64x1x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2di ((__builtin_neon_di *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_u64 (uint64_t * __a, uint64x1x2_t __b) +{ + union { uint64x1x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2di ((__builtin_neon_di *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2q_s8 (int8_t * __a, int8x16x2_t __b) +{ + union { int8x16x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst2v16qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2q_s16 (int16_t * __a, int16x8x2_t __b) +{ + union { int16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst2v8hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2q_s32 (int32_t * __a, int32x4x2_t __b) +{ + union { int32x4x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst2v4si ((__builtin_neon_si *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2q_f32 (float32_t * __a, float32x4x2_t __b) +{ + union { float32x4x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst2v4sf ((__builtin_neon_sf *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2q_u8 (uint8_t * __a, uint8x16x2_t __b) +{ + union { uint8x16x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst2v16qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2q_u16 (uint16_t * __a, uint16x8x2_t __b) +{ + union { uint16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst2v8hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2q_u32 (uint32_t * __a, uint32x4x2_t __b) +{ + union { uint32x4x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst2v4si ((__builtin_neon_si *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2q_p8 (poly8_t * __a, poly8x16x2_t __b) +{ + union { poly8x16x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst2v16qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2q_p16 (poly16_t * __a, poly16x8x2_t __b) +{ + union { poly16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst2v8hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_lane_s8 (int8_t * __a, int8x8x2_t __b, const int __c) +{ + union { int8x8x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2_lanev8qi ((__builtin_neon_qi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_lane_s16 (int16_t * __a, int16x4x2_t __b, const int __c) +{ + union { int16x4x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2_lanev4hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_lane_s32 (int32_t * __a, int32x2x2_t __b, const int __c) +{ + union { int32x2x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2_lanev2si ((__builtin_neon_si *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_lane_f32 (float32_t * __a, float32x2x2_t __b, const int __c) +{ + union { float32x2x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2_lanev2sf ((__builtin_neon_sf *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_lane_u8 (uint8_t * __a, uint8x8x2_t __b, const int __c) +{ + union { uint8x8x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2_lanev8qi ((__builtin_neon_qi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_lane_u16 (uint16_t * __a, uint16x4x2_t __b, const int __c) +{ + union { uint16x4x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2_lanev4hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_lane_u32 (uint32_t * __a, uint32x2x2_t __b, const int __c) +{ + union { uint32x2x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2_lanev2si ((__builtin_neon_si *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_lane_p8 (poly8_t * __a, poly8x8x2_t __b, const int __c) +{ + union { poly8x8x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2_lanev8qi ((__builtin_neon_qi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2_lane_p16 (poly16_t * __a, poly16x4x2_t __b, const int __c) +{ + union { poly16x4x2_t __i; __builtin_neon_ti __o; } __bu = { __b }; + __builtin_neon_vst2_lanev4hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2q_lane_s16 (int16_t * __a, int16x8x2_t __b, const int __c) +{ + union { int16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst2_lanev8hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2q_lane_s32 (int32_t * __a, int32x4x2_t __b, const int __c) +{ + union { int32x4x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst2_lanev4si ((__builtin_neon_si *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2q_lane_f32 (float32_t * __a, float32x4x2_t __b, const int __c) +{ + union { float32x4x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst2_lanev4sf ((__builtin_neon_sf *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2q_lane_u16 (uint16_t * __a, uint16x8x2_t __b, const int __c) +{ + union { uint16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst2_lanev8hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2q_lane_u32 (uint32_t * __a, uint32x4x2_t __b, const int __c) +{ + union { uint32x4x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst2_lanev4si ((__builtin_neon_si *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst2q_lane_p16 (poly16_t * __a, poly16x8x2_t __b, const int __c) +{ + union { poly16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst2_lanev8hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline int8x8x3_t __attribute__ ((__always_inline__)) +vld3_s8 (const int8_t * __a) +{ + union { int8x8x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3v8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline int16x4x3_t __attribute__ ((__always_inline__)) +vld3_s16 (const int16_t * __a) +{ + union { int16x4x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3v4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline int32x2x3_t __attribute__ ((__always_inline__)) +vld3_s32 (const int32_t * __a) +{ + union { int32x2x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3v2si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline float32x2x3_t __attribute__ ((__always_inline__)) +vld3_f32 (const float32_t * __a) +{ + union { float32x2x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3v2sf ((const __builtin_neon_sf *) __a); + return __rv.__i; +} + +__extension__ static __inline uint8x8x3_t __attribute__ ((__always_inline__)) +vld3_u8 (const uint8_t * __a) +{ + union { uint8x8x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3v8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint16x4x3_t __attribute__ ((__always_inline__)) +vld3_u16 (const uint16_t * __a) +{ + union { uint16x4x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3v4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint32x2x3_t __attribute__ ((__always_inline__)) +vld3_u32 (const uint32_t * __a) +{ + union { uint32x2x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3v2si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline poly8x8x3_t __attribute__ ((__always_inline__)) +vld3_p8 (const poly8_t * __a) +{ + union { poly8x8x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3v8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline poly16x4x3_t __attribute__ ((__always_inline__)) +vld3_p16 (const poly16_t * __a) +{ + union { poly16x4x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3v4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1x3_t __attribute__ ((__always_inline__)) +vld3_p64 (const poly64_t * __a) +{ + union { poly64x1x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3di ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +#endif +__extension__ static __inline int64x1x3_t __attribute__ ((__always_inline__)) +vld3_s64 (const int64_t * __a) +{ + union { int64x1x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3di ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +__extension__ static __inline uint64x1x3_t __attribute__ ((__always_inline__)) +vld3_u64 (const uint64_t * __a) +{ + union { uint64x1x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3di ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +__extension__ static __inline int8x16x3_t __attribute__ ((__always_inline__)) +vld3q_s8 (const int8_t * __a) +{ + union { int8x16x3_t __i; __builtin_neon_ci __o; } __rv; + __rv.__o = __builtin_neon_vld3v16qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline int16x8x3_t __attribute__ ((__always_inline__)) +vld3q_s16 (const int16_t * __a) +{ + union { int16x8x3_t __i; __builtin_neon_ci __o; } __rv; + __rv.__o = __builtin_neon_vld3v8hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline int32x4x3_t __attribute__ ((__always_inline__)) +vld3q_s32 (const int32_t * __a) +{ + union { int32x4x3_t __i; __builtin_neon_ci __o; } __rv; + __rv.__o = __builtin_neon_vld3v4si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline float32x4x3_t __attribute__ ((__always_inline__)) +vld3q_f32 (const float32_t * __a) +{ + union { float32x4x3_t __i; __builtin_neon_ci __o; } __rv; + __rv.__o = __builtin_neon_vld3v4sf ((const __builtin_neon_sf *) __a); + return __rv.__i; +} + +__extension__ static __inline uint8x16x3_t __attribute__ ((__always_inline__)) +vld3q_u8 (const uint8_t * __a) +{ + union { uint8x16x3_t __i; __builtin_neon_ci __o; } __rv; + __rv.__o = __builtin_neon_vld3v16qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint16x8x3_t __attribute__ ((__always_inline__)) +vld3q_u16 (const uint16_t * __a) +{ + union { uint16x8x3_t __i; __builtin_neon_ci __o; } __rv; + __rv.__o = __builtin_neon_vld3v8hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint32x4x3_t __attribute__ ((__always_inline__)) +vld3q_u32 (const uint32_t * __a) +{ + union { uint32x4x3_t __i; __builtin_neon_ci __o; } __rv; + __rv.__o = __builtin_neon_vld3v4si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline poly8x16x3_t __attribute__ ((__always_inline__)) +vld3q_p8 (const poly8_t * __a) +{ + union { poly8x16x3_t __i; __builtin_neon_ci __o; } __rv; + __rv.__o = __builtin_neon_vld3v16qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline poly16x8x3_t __attribute__ ((__always_inline__)) +vld3q_p16 (const poly16_t * __a) +{ + union { poly16x8x3_t __i; __builtin_neon_ci __o; } __rv; + __rv.__o = __builtin_neon_vld3v8hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline int8x8x3_t __attribute__ ((__always_inline__)) +vld3_lane_s8 (const int8_t * __a, int8x8x3_t __b, const int __c) +{ + union { int8x8x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + union { int8x8x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_lanev8qi ((const __builtin_neon_qi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline int16x4x3_t __attribute__ ((__always_inline__)) +vld3_lane_s16 (const int16_t * __a, int16x4x3_t __b, const int __c) +{ + union { int16x4x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + union { int16x4x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_lanev4hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline int32x2x3_t __attribute__ ((__always_inline__)) +vld3_lane_s32 (const int32_t * __a, int32x2x3_t __b, const int __c) +{ + union { int32x2x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + union { int32x2x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_lanev2si ((const __builtin_neon_si *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline float32x2x3_t __attribute__ ((__always_inline__)) +vld3_lane_f32 (const float32_t * __a, float32x2x3_t __b, const int __c) +{ + union { float32x2x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + union { float32x2x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_lanev2sf ((const __builtin_neon_sf *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline uint8x8x3_t __attribute__ ((__always_inline__)) +vld3_lane_u8 (const uint8_t * __a, uint8x8x3_t __b, const int __c) +{ + union { uint8x8x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + union { uint8x8x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_lanev8qi ((const __builtin_neon_qi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline uint16x4x3_t __attribute__ ((__always_inline__)) +vld3_lane_u16 (const uint16_t * __a, uint16x4x3_t __b, const int __c) +{ + union { uint16x4x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + union { uint16x4x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_lanev4hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline uint32x2x3_t __attribute__ ((__always_inline__)) +vld3_lane_u32 (const uint32_t * __a, uint32x2x3_t __b, const int __c) +{ + union { uint32x2x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + union { uint32x2x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_lanev2si ((const __builtin_neon_si *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline poly8x8x3_t __attribute__ ((__always_inline__)) +vld3_lane_p8 (const poly8_t * __a, poly8x8x3_t __b, const int __c) +{ + union { poly8x8x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + union { poly8x8x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_lanev8qi ((const __builtin_neon_qi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline poly16x4x3_t __attribute__ ((__always_inline__)) +vld3_lane_p16 (const poly16_t * __a, poly16x4x3_t __b, const int __c) +{ + union { poly16x4x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + union { poly16x4x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_lanev4hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline int16x8x3_t __attribute__ ((__always_inline__)) +vld3q_lane_s16 (const int16_t * __a, int16x8x3_t __b, const int __c) +{ + union { int16x8x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + union { int16x8x3_t __i; __builtin_neon_ci __o; } __rv; + __rv.__o = __builtin_neon_vld3_lanev8hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline int32x4x3_t __attribute__ ((__always_inline__)) +vld3q_lane_s32 (const int32_t * __a, int32x4x3_t __b, const int __c) +{ + union { int32x4x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + union { int32x4x3_t __i; __builtin_neon_ci __o; } __rv; + __rv.__o = __builtin_neon_vld3_lanev4si ((const __builtin_neon_si *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline float32x4x3_t __attribute__ ((__always_inline__)) +vld3q_lane_f32 (const float32_t * __a, float32x4x3_t __b, const int __c) +{ + union { float32x4x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + union { float32x4x3_t __i; __builtin_neon_ci __o; } __rv; + __rv.__o = __builtin_neon_vld3_lanev4sf ((const __builtin_neon_sf *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline uint16x8x3_t __attribute__ ((__always_inline__)) +vld3q_lane_u16 (const uint16_t * __a, uint16x8x3_t __b, const int __c) +{ + union { uint16x8x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + union { uint16x8x3_t __i; __builtin_neon_ci __o; } __rv; + __rv.__o = __builtin_neon_vld3_lanev8hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline uint32x4x3_t __attribute__ ((__always_inline__)) +vld3q_lane_u32 (const uint32_t * __a, uint32x4x3_t __b, const int __c) +{ + union { uint32x4x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + union { uint32x4x3_t __i; __builtin_neon_ci __o; } __rv; + __rv.__o = __builtin_neon_vld3_lanev4si ((const __builtin_neon_si *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline poly16x8x3_t __attribute__ ((__always_inline__)) +vld3q_lane_p16 (const poly16_t * __a, poly16x8x3_t __b, const int __c) +{ + union { poly16x8x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + union { poly16x8x3_t __i; __builtin_neon_ci __o; } __rv; + __rv.__o = __builtin_neon_vld3_lanev8hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline int8x8x3_t __attribute__ ((__always_inline__)) +vld3_dup_s8 (const int8_t * __a) +{ + union { int8x8x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_dupv8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline int16x4x3_t __attribute__ ((__always_inline__)) +vld3_dup_s16 (const int16_t * __a) +{ + union { int16x4x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_dupv4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline int32x2x3_t __attribute__ ((__always_inline__)) +vld3_dup_s32 (const int32_t * __a) +{ + union { int32x2x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_dupv2si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline float32x2x3_t __attribute__ ((__always_inline__)) +vld3_dup_f32 (const float32_t * __a) +{ + union { float32x2x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_dupv2sf ((const __builtin_neon_sf *) __a); + return __rv.__i; +} + +__extension__ static __inline uint8x8x3_t __attribute__ ((__always_inline__)) +vld3_dup_u8 (const uint8_t * __a) +{ + union { uint8x8x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_dupv8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint16x4x3_t __attribute__ ((__always_inline__)) +vld3_dup_u16 (const uint16_t * __a) +{ + union { uint16x4x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_dupv4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint32x2x3_t __attribute__ ((__always_inline__)) +vld3_dup_u32 (const uint32_t * __a) +{ + union { uint32x2x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_dupv2si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline poly8x8x3_t __attribute__ ((__always_inline__)) +vld3_dup_p8 (const poly8_t * __a) +{ + union { poly8x8x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_dupv8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline poly16x4x3_t __attribute__ ((__always_inline__)) +vld3_dup_p16 (const poly16_t * __a) +{ + union { poly16x4x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_dupv4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1x3_t __attribute__ ((__always_inline__)) +vld3_dup_p64 (const poly64_t * __a) +{ + union { poly64x1x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_dupdi ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +#endif +__extension__ static __inline int64x1x3_t __attribute__ ((__always_inline__)) +vld3_dup_s64 (const int64_t * __a) +{ + union { int64x1x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_dupdi ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +__extension__ static __inline uint64x1x3_t __attribute__ ((__always_inline__)) +vld3_dup_u64 (const uint64_t * __a) +{ + union { uint64x1x3_t __i; __builtin_neon_ei __o; } __rv; + __rv.__o = __builtin_neon_vld3_dupdi ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_s8 (int8_t * __a, int8x8x3_t __b) +{ + union { int8x8x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3v8qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_s16 (int16_t * __a, int16x4x3_t __b) +{ + union { int16x4x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3v4hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_s32 (int32_t * __a, int32x2x3_t __b) +{ + union { int32x2x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3v2si ((__builtin_neon_si *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_f32 (float32_t * __a, float32x2x3_t __b) +{ + union { float32x2x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3v2sf ((__builtin_neon_sf *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_u8 (uint8_t * __a, uint8x8x3_t __b) +{ + union { uint8x8x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3v8qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_u16 (uint16_t * __a, uint16x4x3_t __b) +{ + union { uint16x4x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3v4hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_u32 (uint32_t * __a, uint32x2x3_t __b) +{ + union { uint32x2x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3v2si ((__builtin_neon_si *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_p8 (poly8_t * __a, poly8x8x3_t __b) +{ + union { poly8x8x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3v8qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_p16 (poly16_t * __a, poly16x4x3_t __b) +{ + union { poly16x4x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3v4hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_p64 (poly64_t * __a, poly64x1x3_t __b) +{ + union { poly64x1x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3di ((__builtin_neon_di *) __a, __bu.__o); +} + +#endif +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_s64 (int64_t * __a, int64x1x3_t __b) +{ + union { int64x1x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3di ((__builtin_neon_di *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_u64 (uint64_t * __a, uint64x1x3_t __b) +{ + union { uint64x1x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3di ((__builtin_neon_di *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3q_s8 (int8_t * __a, int8x16x3_t __b) +{ + union { int8x16x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + __builtin_neon_vst3v16qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3q_s16 (int16_t * __a, int16x8x3_t __b) +{ + union { int16x8x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + __builtin_neon_vst3v8hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3q_s32 (int32_t * __a, int32x4x3_t __b) +{ + union { int32x4x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + __builtin_neon_vst3v4si ((__builtin_neon_si *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3q_f32 (float32_t * __a, float32x4x3_t __b) +{ + union { float32x4x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + __builtin_neon_vst3v4sf ((__builtin_neon_sf *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3q_u8 (uint8_t * __a, uint8x16x3_t __b) +{ + union { uint8x16x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + __builtin_neon_vst3v16qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3q_u16 (uint16_t * __a, uint16x8x3_t __b) +{ + union { uint16x8x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + __builtin_neon_vst3v8hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3q_u32 (uint32_t * __a, uint32x4x3_t __b) +{ + union { uint32x4x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + __builtin_neon_vst3v4si ((__builtin_neon_si *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3q_p8 (poly8_t * __a, poly8x16x3_t __b) +{ + union { poly8x16x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + __builtin_neon_vst3v16qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3q_p16 (poly16_t * __a, poly16x8x3_t __b) +{ + union { poly16x8x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + __builtin_neon_vst3v8hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_lane_s8 (int8_t * __a, int8x8x3_t __b, const int __c) +{ + union { int8x8x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3_lanev8qi ((__builtin_neon_qi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_lane_s16 (int16_t * __a, int16x4x3_t __b, const int __c) +{ + union { int16x4x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3_lanev4hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_lane_s32 (int32_t * __a, int32x2x3_t __b, const int __c) +{ + union { int32x2x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3_lanev2si ((__builtin_neon_si *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_lane_f32 (float32_t * __a, float32x2x3_t __b, const int __c) +{ + union { float32x2x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3_lanev2sf ((__builtin_neon_sf *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_lane_u8 (uint8_t * __a, uint8x8x3_t __b, const int __c) +{ + union { uint8x8x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3_lanev8qi ((__builtin_neon_qi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_lane_u16 (uint16_t * __a, uint16x4x3_t __b, const int __c) +{ + union { uint16x4x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3_lanev4hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_lane_u32 (uint32_t * __a, uint32x2x3_t __b, const int __c) +{ + union { uint32x2x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3_lanev2si ((__builtin_neon_si *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_lane_p8 (poly8_t * __a, poly8x8x3_t __b, const int __c) +{ + union { poly8x8x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3_lanev8qi ((__builtin_neon_qi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3_lane_p16 (poly16_t * __a, poly16x4x3_t __b, const int __c) +{ + union { poly16x4x3_t __i; __builtin_neon_ei __o; } __bu = { __b }; + __builtin_neon_vst3_lanev4hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3q_lane_s16 (int16_t * __a, int16x8x3_t __b, const int __c) +{ + union { int16x8x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + __builtin_neon_vst3_lanev8hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3q_lane_s32 (int32_t * __a, int32x4x3_t __b, const int __c) +{ + union { int32x4x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + __builtin_neon_vst3_lanev4si ((__builtin_neon_si *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3q_lane_f32 (float32_t * __a, float32x4x3_t __b, const int __c) +{ + union { float32x4x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + __builtin_neon_vst3_lanev4sf ((__builtin_neon_sf *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3q_lane_u16 (uint16_t * __a, uint16x8x3_t __b, const int __c) +{ + union { uint16x8x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + __builtin_neon_vst3_lanev8hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3q_lane_u32 (uint32_t * __a, uint32x4x3_t __b, const int __c) +{ + union { uint32x4x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + __builtin_neon_vst3_lanev4si ((__builtin_neon_si *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst3q_lane_p16 (poly16_t * __a, poly16x8x3_t __b, const int __c) +{ + union { poly16x8x3_t __i; __builtin_neon_ci __o; } __bu = { __b }; + __builtin_neon_vst3_lanev8hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline int8x8x4_t __attribute__ ((__always_inline__)) +vld4_s8 (const int8_t * __a) +{ + union { int8x8x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4v8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline int16x4x4_t __attribute__ ((__always_inline__)) +vld4_s16 (const int16_t * __a) +{ + union { int16x4x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4v4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline int32x2x4_t __attribute__ ((__always_inline__)) +vld4_s32 (const int32_t * __a) +{ + union { int32x2x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4v2si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline float32x2x4_t __attribute__ ((__always_inline__)) +vld4_f32 (const float32_t * __a) +{ + union { float32x2x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4v2sf ((const __builtin_neon_sf *) __a); + return __rv.__i; +} + +__extension__ static __inline uint8x8x4_t __attribute__ ((__always_inline__)) +vld4_u8 (const uint8_t * __a) +{ + union { uint8x8x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4v8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint16x4x4_t __attribute__ ((__always_inline__)) +vld4_u16 (const uint16_t * __a) +{ + union { uint16x4x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4v4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint32x2x4_t __attribute__ ((__always_inline__)) +vld4_u32 (const uint32_t * __a) +{ + union { uint32x2x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4v2si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline poly8x8x4_t __attribute__ ((__always_inline__)) +vld4_p8 (const poly8_t * __a) +{ + union { poly8x8x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4v8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline poly16x4x4_t __attribute__ ((__always_inline__)) +vld4_p16 (const poly16_t * __a) +{ + union { poly16x4x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4v4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1x4_t __attribute__ ((__always_inline__)) +vld4_p64 (const poly64_t * __a) +{ + union { poly64x1x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4di ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +#endif +__extension__ static __inline int64x1x4_t __attribute__ ((__always_inline__)) +vld4_s64 (const int64_t * __a) +{ + union { int64x1x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4di ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +__extension__ static __inline uint64x1x4_t __attribute__ ((__always_inline__)) +vld4_u64 (const uint64_t * __a) +{ + union { uint64x1x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4di ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +__extension__ static __inline int8x16x4_t __attribute__ ((__always_inline__)) +vld4q_s8 (const int8_t * __a) +{ + union { int8x16x4_t __i; __builtin_neon_xi __o; } __rv; + __rv.__o = __builtin_neon_vld4v16qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline int16x8x4_t __attribute__ ((__always_inline__)) +vld4q_s16 (const int16_t * __a) +{ + union { int16x8x4_t __i; __builtin_neon_xi __o; } __rv; + __rv.__o = __builtin_neon_vld4v8hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline int32x4x4_t __attribute__ ((__always_inline__)) +vld4q_s32 (const int32_t * __a) +{ + union { int32x4x4_t __i; __builtin_neon_xi __o; } __rv; + __rv.__o = __builtin_neon_vld4v4si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline float32x4x4_t __attribute__ ((__always_inline__)) +vld4q_f32 (const float32_t * __a) +{ + union { float32x4x4_t __i; __builtin_neon_xi __o; } __rv; + __rv.__o = __builtin_neon_vld4v4sf ((const __builtin_neon_sf *) __a); + return __rv.__i; +} + +__extension__ static __inline uint8x16x4_t __attribute__ ((__always_inline__)) +vld4q_u8 (const uint8_t * __a) +{ + union { uint8x16x4_t __i; __builtin_neon_xi __o; } __rv; + __rv.__o = __builtin_neon_vld4v16qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint16x8x4_t __attribute__ ((__always_inline__)) +vld4q_u16 (const uint16_t * __a) +{ + union { uint16x8x4_t __i; __builtin_neon_xi __o; } __rv; + __rv.__o = __builtin_neon_vld4v8hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint32x4x4_t __attribute__ ((__always_inline__)) +vld4q_u32 (const uint32_t * __a) +{ + union { uint32x4x4_t __i; __builtin_neon_xi __o; } __rv; + __rv.__o = __builtin_neon_vld4v4si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline poly8x16x4_t __attribute__ ((__always_inline__)) +vld4q_p8 (const poly8_t * __a) +{ + union { poly8x16x4_t __i; __builtin_neon_xi __o; } __rv; + __rv.__o = __builtin_neon_vld4v16qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline poly16x8x4_t __attribute__ ((__always_inline__)) +vld4q_p16 (const poly16_t * __a) +{ + union { poly16x8x4_t __i; __builtin_neon_xi __o; } __rv; + __rv.__o = __builtin_neon_vld4v8hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline int8x8x4_t __attribute__ ((__always_inline__)) +vld4_lane_s8 (const int8_t * __a, int8x8x4_t __b, const int __c) +{ + union { int8x8x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + union { int8x8x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_lanev8qi ((const __builtin_neon_qi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline int16x4x4_t __attribute__ ((__always_inline__)) +vld4_lane_s16 (const int16_t * __a, int16x4x4_t __b, const int __c) +{ + union { int16x4x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + union { int16x4x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_lanev4hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline int32x2x4_t __attribute__ ((__always_inline__)) +vld4_lane_s32 (const int32_t * __a, int32x2x4_t __b, const int __c) +{ + union { int32x2x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + union { int32x2x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_lanev2si ((const __builtin_neon_si *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline float32x2x4_t __attribute__ ((__always_inline__)) +vld4_lane_f32 (const float32_t * __a, float32x2x4_t __b, const int __c) +{ + union { float32x2x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + union { float32x2x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_lanev2sf ((const __builtin_neon_sf *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline uint8x8x4_t __attribute__ ((__always_inline__)) +vld4_lane_u8 (const uint8_t * __a, uint8x8x4_t __b, const int __c) +{ + union { uint8x8x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + union { uint8x8x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_lanev8qi ((const __builtin_neon_qi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline uint16x4x4_t __attribute__ ((__always_inline__)) +vld4_lane_u16 (const uint16_t * __a, uint16x4x4_t __b, const int __c) +{ + union { uint16x4x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + union { uint16x4x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_lanev4hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline uint32x2x4_t __attribute__ ((__always_inline__)) +vld4_lane_u32 (const uint32_t * __a, uint32x2x4_t __b, const int __c) +{ + union { uint32x2x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + union { uint32x2x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_lanev2si ((const __builtin_neon_si *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline poly8x8x4_t __attribute__ ((__always_inline__)) +vld4_lane_p8 (const poly8_t * __a, poly8x8x4_t __b, const int __c) +{ + union { poly8x8x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + union { poly8x8x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_lanev8qi ((const __builtin_neon_qi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline poly16x4x4_t __attribute__ ((__always_inline__)) +vld4_lane_p16 (const poly16_t * __a, poly16x4x4_t __b, const int __c) +{ + union { poly16x4x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + union { poly16x4x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_lanev4hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline int16x8x4_t __attribute__ ((__always_inline__)) +vld4q_lane_s16 (const int16_t * __a, int16x8x4_t __b, const int __c) +{ + union { int16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + union { int16x8x4_t __i; __builtin_neon_xi __o; } __rv; + __rv.__o = __builtin_neon_vld4_lanev8hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline int32x4x4_t __attribute__ ((__always_inline__)) +vld4q_lane_s32 (const int32_t * __a, int32x4x4_t __b, const int __c) +{ + union { int32x4x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + union { int32x4x4_t __i; __builtin_neon_xi __o; } __rv; + __rv.__o = __builtin_neon_vld4_lanev4si ((const __builtin_neon_si *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline float32x4x4_t __attribute__ ((__always_inline__)) +vld4q_lane_f32 (const float32_t * __a, float32x4x4_t __b, const int __c) +{ + union { float32x4x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + union { float32x4x4_t __i; __builtin_neon_xi __o; } __rv; + __rv.__o = __builtin_neon_vld4_lanev4sf ((const __builtin_neon_sf *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline uint16x8x4_t __attribute__ ((__always_inline__)) +vld4q_lane_u16 (const uint16_t * __a, uint16x8x4_t __b, const int __c) +{ + union { uint16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + union { uint16x8x4_t __i; __builtin_neon_xi __o; } __rv; + __rv.__o = __builtin_neon_vld4_lanev8hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline uint32x4x4_t __attribute__ ((__always_inline__)) +vld4q_lane_u32 (const uint32_t * __a, uint32x4x4_t __b, const int __c) +{ + union { uint32x4x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + union { uint32x4x4_t __i; __builtin_neon_xi __o; } __rv; + __rv.__o = __builtin_neon_vld4_lanev4si ((const __builtin_neon_si *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline poly16x8x4_t __attribute__ ((__always_inline__)) +vld4q_lane_p16 (const poly16_t * __a, poly16x8x4_t __b, const int __c) +{ + union { poly16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + union { poly16x8x4_t __i; __builtin_neon_xi __o; } __rv; + __rv.__o = __builtin_neon_vld4_lanev8hi ((const __builtin_neon_hi *) __a, __bu.__o, __c); + return __rv.__i; +} + +__extension__ static __inline int8x8x4_t __attribute__ ((__always_inline__)) +vld4_dup_s8 (const int8_t * __a) +{ + union { int8x8x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_dupv8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline int16x4x4_t __attribute__ ((__always_inline__)) +vld4_dup_s16 (const int16_t * __a) +{ + union { int16x4x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_dupv4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline int32x2x4_t __attribute__ ((__always_inline__)) +vld4_dup_s32 (const int32_t * __a) +{ + union { int32x2x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_dupv2si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline float32x2x4_t __attribute__ ((__always_inline__)) +vld4_dup_f32 (const float32_t * __a) +{ + union { float32x2x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_dupv2sf ((const __builtin_neon_sf *) __a); + return __rv.__i; +} + +__extension__ static __inline uint8x8x4_t __attribute__ ((__always_inline__)) +vld4_dup_u8 (const uint8_t * __a) +{ + union { uint8x8x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_dupv8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint16x4x4_t __attribute__ ((__always_inline__)) +vld4_dup_u16 (const uint16_t * __a) +{ + union { uint16x4x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_dupv4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +__extension__ static __inline uint32x2x4_t __attribute__ ((__always_inline__)) +vld4_dup_u32 (const uint32_t * __a) +{ + union { uint32x2x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_dupv2si ((const __builtin_neon_si *) __a); + return __rv.__i; +} + +__extension__ static __inline poly8x8x4_t __attribute__ ((__always_inline__)) +vld4_dup_p8 (const poly8_t * __a) +{ + union { poly8x8x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_dupv8qi ((const __builtin_neon_qi *) __a); + return __rv.__i; +} + +__extension__ static __inline poly16x4x4_t __attribute__ ((__always_inline__)) +vld4_dup_p16 (const poly16_t * __a) +{ + union { poly16x4x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_dupv4hi ((const __builtin_neon_hi *) __a); + return __rv.__i; +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1x4_t __attribute__ ((__always_inline__)) +vld4_dup_p64 (const poly64_t * __a) +{ + union { poly64x1x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_dupdi ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +#endif +__extension__ static __inline int64x1x4_t __attribute__ ((__always_inline__)) +vld4_dup_s64 (const int64_t * __a) +{ + union { int64x1x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_dupdi ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +__extension__ static __inline uint64x1x4_t __attribute__ ((__always_inline__)) +vld4_dup_u64 (const uint64_t * __a) +{ + union { uint64x1x4_t __i; __builtin_neon_oi __o; } __rv; + __rv.__o = __builtin_neon_vld4_dupdi ((const __builtin_neon_di *) __a); + return __rv.__i; +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_s8 (int8_t * __a, int8x8x4_t __b) +{ + union { int8x8x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4v8qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_s16 (int16_t * __a, int16x4x4_t __b) +{ + union { int16x4x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4v4hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_s32 (int32_t * __a, int32x2x4_t __b) +{ + union { int32x2x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4v2si ((__builtin_neon_si *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_f32 (float32_t * __a, float32x2x4_t __b) +{ + union { float32x2x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4v2sf ((__builtin_neon_sf *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_u8 (uint8_t * __a, uint8x8x4_t __b) +{ + union { uint8x8x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4v8qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_u16 (uint16_t * __a, uint16x4x4_t __b) +{ + union { uint16x4x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4v4hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_u32 (uint32_t * __a, uint32x2x4_t __b) +{ + union { uint32x2x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4v2si ((__builtin_neon_si *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_p8 (poly8_t * __a, poly8x8x4_t __b) +{ + union { poly8x8x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4v8qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_p16 (poly16_t * __a, poly16x4x4_t __b) +{ + union { poly16x4x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4v4hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_p64 (poly64_t * __a, poly64x1x4_t __b) +{ + union { poly64x1x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4di ((__builtin_neon_di *) __a, __bu.__o); +} + +#endif +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_s64 (int64_t * __a, int64x1x4_t __b) +{ + union { int64x1x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4di ((__builtin_neon_di *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_u64 (uint64_t * __a, uint64x1x4_t __b) +{ + union { uint64x1x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4di ((__builtin_neon_di *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4q_s8 (int8_t * __a, int8x16x4_t __b) +{ + union { int8x16x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + __builtin_neon_vst4v16qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4q_s16 (int16_t * __a, int16x8x4_t __b) +{ + union { int16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + __builtin_neon_vst4v8hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4q_s32 (int32_t * __a, int32x4x4_t __b) +{ + union { int32x4x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + __builtin_neon_vst4v4si ((__builtin_neon_si *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4q_f32 (float32_t * __a, float32x4x4_t __b) +{ + union { float32x4x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + __builtin_neon_vst4v4sf ((__builtin_neon_sf *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4q_u8 (uint8_t * __a, uint8x16x4_t __b) +{ + union { uint8x16x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + __builtin_neon_vst4v16qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4q_u16 (uint16_t * __a, uint16x8x4_t __b) +{ + union { uint16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + __builtin_neon_vst4v8hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4q_u32 (uint32_t * __a, uint32x4x4_t __b) +{ + union { uint32x4x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + __builtin_neon_vst4v4si ((__builtin_neon_si *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4q_p8 (poly8_t * __a, poly8x16x4_t __b) +{ + union { poly8x16x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + __builtin_neon_vst4v16qi ((__builtin_neon_qi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4q_p16 (poly16_t * __a, poly16x8x4_t __b) +{ + union { poly16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + __builtin_neon_vst4v8hi ((__builtin_neon_hi *) __a, __bu.__o); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_lane_s8 (int8_t * __a, int8x8x4_t __b, const int __c) +{ + union { int8x8x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4_lanev8qi ((__builtin_neon_qi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_lane_s16 (int16_t * __a, int16x4x4_t __b, const int __c) +{ + union { int16x4x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4_lanev4hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_lane_s32 (int32_t * __a, int32x2x4_t __b, const int __c) +{ + union { int32x2x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4_lanev2si ((__builtin_neon_si *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_lane_f32 (float32_t * __a, float32x2x4_t __b, const int __c) +{ + union { float32x2x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4_lanev2sf ((__builtin_neon_sf *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_lane_u8 (uint8_t * __a, uint8x8x4_t __b, const int __c) +{ + union { uint8x8x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4_lanev8qi ((__builtin_neon_qi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_lane_u16 (uint16_t * __a, uint16x4x4_t __b, const int __c) +{ + union { uint16x4x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4_lanev4hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_lane_u32 (uint32_t * __a, uint32x2x4_t __b, const int __c) +{ + union { uint32x2x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4_lanev2si ((__builtin_neon_si *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_lane_p8 (poly8_t * __a, poly8x8x4_t __b, const int __c) +{ + union { poly8x8x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4_lanev8qi ((__builtin_neon_qi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4_lane_p16 (poly16_t * __a, poly16x4x4_t __b, const int __c) +{ + union { poly16x4x4_t __i; __builtin_neon_oi __o; } __bu = { __b }; + __builtin_neon_vst4_lanev4hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4q_lane_s16 (int16_t * __a, int16x8x4_t __b, const int __c) +{ + union { int16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + __builtin_neon_vst4_lanev8hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4q_lane_s32 (int32_t * __a, int32x4x4_t __b, const int __c) +{ + union { int32x4x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + __builtin_neon_vst4_lanev4si ((__builtin_neon_si *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4q_lane_f32 (float32_t * __a, float32x4x4_t __b, const int __c) +{ + union { float32x4x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + __builtin_neon_vst4_lanev4sf ((__builtin_neon_sf *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4q_lane_u16 (uint16_t * __a, uint16x8x4_t __b, const int __c) +{ + union { uint16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + __builtin_neon_vst4_lanev8hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4q_lane_u32 (uint32_t * __a, uint32x4x4_t __b, const int __c) +{ + union { uint32x4x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + __builtin_neon_vst4_lanev4si ((__builtin_neon_si *) __a, __bu.__o, __c); +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vst4q_lane_p16 (poly16_t * __a, poly16x8x4_t __b, const int __c) +{ + union { poly16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b }; + __builtin_neon_vst4_lanev8hi ((__builtin_neon_hi *) __a, __bu.__o, __c); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vand_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vandv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vand_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vandv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vand_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vandv2si (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vand_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vandv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vand_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vandv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vand_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vandv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vand_s64 (int64x1_t __a, int64x1_t __b) +{ + return (int64x1_t)__builtin_neon_vanddi (__a, __b, 1); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vand_u64 (uint64x1_t __a, uint64x1_t __b) +{ + return (uint64x1_t)__builtin_neon_vanddi ((int64x1_t) __a, (int64x1_t) __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vandq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vandv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vandq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vandv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vandq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vandv4si (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vandq_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int64x2_t)__builtin_neon_vandv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vandq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vandv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vandq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vandv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vandq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vandv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vandq_u64 (uint64x2_t __a, uint64x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vandv2di ((int64x2_t) __a, (int64x2_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vorr_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vorrv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vorr_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vorrv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vorr_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vorrv2si (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vorr_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vorrv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vorr_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vorrv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vorr_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vorrv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vorr_s64 (int64x1_t __a, int64x1_t __b) +{ + return (int64x1_t)__builtin_neon_vorrdi (__a, __b, 1); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vorr_u64 (uint64x1_t __a, uint64x1_t __b) +{ + return (uint64x1_t)__builtin_neon_vorrdi ((int64x1_t) __a, (int64x1_t) __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vorrq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vorrv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vorrq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vorrv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vorrq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vorrv4si (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vorrq_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int64x2_t)__builtin_neon_vorrv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vorrq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vorrv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vorrq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vorrv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vorrq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vorrv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vorrq_u64 (uint64x2_t __a, uint64x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vorrv2di ((int64x2_t) __a, (int64x2_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +veor_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_veorv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +veor_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_veorv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +veor_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_veorv2si (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +veor_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_veorv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +veor_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_veorv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +veor_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_veorv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +veor_s64 (int64x1_t __a, int64x1_t __b) +{ + return (int64x1_t)__builtin_neon_veordi (__a, __b, 1); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +veor_u64 (uint64x1_t __a, uint64x1_t __b) +{ + return (uint64x1_t)__builtin_neon_veordi ((int64x1_t) __a, (int64x1_t) __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +veorq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_veorv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +veorq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_veorv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +veorq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_veorv4si (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +veorq_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int64x2_t)__builtin_neon_veorv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +veorq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_veorv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +veorq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_veorv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +veorq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_veorv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +veorq_u64 (uint64x2_t __a, uint64x2_t __b) +{ + return (uint64x2_t)__builtin_neon_veorv2di ((int64x2_t) __a, (int64x2_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vbic_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vbicv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vbic_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vbicv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vbic_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vbicv2si (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vbic_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vbicv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vbic_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vbicv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vbic_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vbicv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vbic_s64 (int64x1_t __a, int64x1_t __b) +{ + return (int64x1_t)__builtin_neon_vbicdi (__a, __b, 1); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vbic_u64 (uint64x1_t __a, uint64x1_t __b) +{ + return (uint64x1_t)__builtin_neon_vbicdi ((int64x1_t) __a, (int64x1_t) __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vbicq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vbicv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vbicq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vbicv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vbicq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vbicv4si (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vbicq_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int64x2_t)__builtin_neon_vbicv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vbicq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vbicv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vbicq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vbicv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vbicq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vbicv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vbicq_u64 (uint64x2_t __a, uint64x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vbicv2di ((int64x2_t) __a, (int64x2_t) __b, 0); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vorn_s8 (int8x8_t __a, int8x8_t __b) +{ + return (int8x8_t)__builtin_neon_vornv8qi (__a, __b, 1); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vorn_s16 (int16x4_t __a, int16x4_t __b) +{ + return (int16x4_t)__builtin_neon_vornv4hi (__a, __b, 1); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vorn_s32 (int32x2_t __a, int32x2_t __b) +{ + return (int32x2_t)__builtin_neon_vornv2si (__a, __b, 1); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vorn_u8 (uint8x8_t __a, uint8x8_t __b) +{ + return (uint8x8_t)__builtin_neon_vornv8qi ((int8x8_t) __a, (int8x8_t) __b, 0); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vorn_u16 (uint16x4_t __a, uint16x4_t __b) +{ + return (uint16x4_t)__builtin_neon_vornv4hi ((int16x4_t) __a, (int16x4_t) __b, 0); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vorn_u32 (uint32x2_t __a, uint32x2_t __b) +{ + return (uint32x2_t)__builtin_neon_vornv2si ((int32x2_t) __a, (int32x2_t) __b, 0); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vorn_s64 (int64x1_t __a, int64x1_t __b) +{ + return (int64x1_t)__builtin_neon_vorndi (__a, __b, 1); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vorn_u64 (uint64x1_t __a, uint64x1_t __b) +{ + return (uint64x1_t)__builtin_neon_vorndi ((int64x1_t) __a, (int64x1_t) __b, 0); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vornq_s8 (int8x16_t __a, int8x16_t __b) +{ + return (int8x16_t)__builtin_neon_vornv16qi (__a, __b, 1); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vornq_s16 (int16x8_t __a, int16x8_t __b) +{ + return (int16x8_t)__builtin_neon_vornv8hi (__a, __b, 1); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vornq_s32 (int32x4_t __a, int32x4_t __b) +{ + return (int32x4_t)__builtin_neon_vornv4si (__a, __b, 1); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vornq_s64 (int64x2_t __a, int64x2_t __b) +{ + return (int64x2_t)__builtin_neon_vornv2di (__a, __b, 1); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vornq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + return (uint8x16_t)__builtin_neon_vornv16qi ((int8x16_t) __a, (int8x16_t) __b, 0); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vornq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + return (uint16x8_t)__builtin_neon_vornv8hi ((int16x8_t) __a, (int16x8_t) __b, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vornq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + return (uint32x4_t)__builtin_neon_vornv4si ((int32x4_t) __a, (int32x4_t) __b, 0); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vornq_u64 (uint64x2_t __a, uint64x2_t __b) +{ + return (uint64x2_t)__builtin_neon_vornv2di ((int64x2_t) __a, (int64x2_t) __b, 0); +} + + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vreinterpret_p8_p16 (poly16x4_t __a) +{ + return (poly8x8_t)__builtin_neon_vreinterpretv8qiv4hi ((int16x4_t) __a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vreinterpret_p8_f32 (float32x2_t __a) +{ + return (poly8x8_t)__builtin_neon_vreinterpretv8qiv2sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vreinterpret_p8_p64 (poly64x1_t __a) +{ + return (poly8x8_t)__builtin_neon_vreinterpretv8qidi (__a); +} + +#endif +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vreinterpret_p8_s64 (int64x1_t __a) +{ + return (poly8x8_t)__builtin_neon_vreinterpretv8qidi (__a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vreinterpret_p8_u64 (uint64x1_t __a) +{ + return (poly8x8_t)__builtin_neon_vreinterpretv8qidi ((int64x1_t) __a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vreinterpret_p8_s8 (int8x8_t __a) +{ + return (poly8x8_t)__builtin_neon_vreinterpretv8qiv8qi (__a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vreinterpret_p8_s16 (int16x4_t __a) +{ + return (poly8x8_t)__builtin_neon_vreinterpretv8qiv4hi (__a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vreinterpret_p8_s32 (int32x2_t __a) +{ + return (poly8x8_t)__builtin_neon_vreinterpretv8qiv2si (__a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vreinterpret_p8_u8 (uint8x8_t __a) +{ + return (poly8x8_t)__builtin_neon_vreinterpretv8qiv8qi ((int8x8_t) __a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vreinterpret_p8_u16 (uint16x4_t __a) +{ + return (poly8x8_t)__builtin_neon_vreinterpretv8qiv4hi ((int16x4_t) __a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vreinterpret_p8_u32 (uint32x2_t __a) +{ + return (poly8x8_t)__builtin_neon_vreinterpretv8qiv2si ((int32x2_t) __a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vreinterpret_p16_p8 (poly8x8_t __a) +{ + return (poly16x4_t)__builtin_neon_vreinterpretv4hiv8qi ((int8x8_t) __a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vreinterpret_p16_f32 (float32x2_t __a) +{ + return (poly16x4_t)__builtin_neon_vreinterpretv4hiv2sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vreinterpret_p16_p64 (poly64x1_t __a) +{ + return (poly16x4_t)__builtin_neon_vreinterpretv4hidi (__a); +} + +#endif +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vreinterpret_p16_s64 (int64x1_t __a) +{ + return (poly16x4_t)__builtin_neon_vreinterpretv4hidi (__a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vreinterpret_p16_u64 (uint64x1_t __a) +{ + return (poly16x4_t)__builtin_neon_vreinterpretv4hidi ((int64x1_t) __a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vreinterpret_p16_s8 (int8x8_t __a) +{ + return (poly16x4_t)__builtin_neon_vreinterpretv4hiv8qi (__a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vreinterpret_p16_s16 (int16x4_t __a) +{ + return (poly16x4_t)__builtin_neon_vreinterpretv4hiv4hi (__a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vreinterpret_p16_s32 (int32x2_t __a) +{ + return (poly16x4_t)__builtin_neon_vreinterpretv4hiv2si (__a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vreinterpret_p16_u8 (uint8x8_t __a) +{ + return (poly16x4_t)__builtin_neon_vreinterpretv4hiv8qi ((int8x8_t) __a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vreinterpret_p16_u16 (uint16x4_t __a) +{ + return (poly16x4_t)__builtin_neon_vreinterpretv4hiv4hi ((int16x4_t) __a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vreinterpret_p16_u32 (uint32x2_t __a) +{ + return (poly16x4_t)__builtin_neon_vreinterpretv4hiv2si ((int32x2_t) __a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vreinterpret_f32_p8 (poly8x8_t __a) +{ + return (float32x2_t)__builtin_neon_vreinterpretv2sfv8qi ((int8x8_t) __a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vreinterpret_f32_p16 (poly16x4_t __a) +{ + return (float32x2_t)__builtin_neon_vreinterpretv2sfv4hi ((int16x4_t) __a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vreinterpret_f32_p64 (poly64x1_t __a) +{ + return (float32x2_t)__builtin_neon_vreinterpretv2sfdi (__a); +} + +#endif +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vreinterpret_f32_s64 (int64x1_t __a) +{ + return (float32x2_t)__builtin_neon_vreinterpretv2sfdi (__a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vreinterpret_f32_u64 (uint64x1_t __a) +{ + return (float32x2_t)__builtin_neon_vreinterpretv2sfdi ((int64x1_t) __a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vreinterpret_f32_s8 (int8x8_t __a) +{ + return (float32x2_t)__builtin_neon_vreinterpretv2sfv8qi (__a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vreinterpret_f32_s16 (int16x4_t __a) +{ + return (float32x2_t)__builtin_neon_vreinterpretv2sfv4hi (__a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vreinterpret_f32_s32 (int32x2_t __a) +{ + return (float32x2_t)__builtin_neon_vreinterpretv2sfv2si (__a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vreinterpret_f32_u8 (uint8x8_t __a) +{ + return (float32x2_t)__builtin_neon_vreinterpretv2sfv8qi ((int8x8_t) __a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vreinterpret_f32_u16 (uint16x4_t __a) +{ + return (float32x2_t)__builtin_neon_vreinterpretv2sfv4hi ((int16x4_t) __a); +} + +__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) +vreinterpret_f32_u32 (uint32x2_t __a) +{ + return (float32x2_t)__builtin_neon_vreinterpretv2sfv2si ((int32x2_t) __a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vreinterpret_p64_p8 (poly8x8_t __a) +{ + return (poly64x1_t)__builtin_neon_vreinterpretdiv8qi ((int8x8_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vreinterpret_p64_p16 (poly16x4_t __a) +{ + return (poly64x1_t)__builtin_neon_vreinterpretdiv4hi ((int16x4_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vreinterpret_p64_f32 (float32x2_t __a) +{ + return (poly64x1_t)__builtin_neon_vreinterpretdiv2sf (__a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vreinterpret_p64_s64 (int64x1_t __a) +{ + return (poly64x1_t)__builtin_neon_vreinterpretdidi (__a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vreinterpret_p64_u64 (uint64x1_t __a) +{ + return (poly64x1_t)__builtin_neon_vreinterpretdidi ((int64x1_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vreinterpret_p64_s8 (int8x8_t __a) +{ + return (poly64x1_t)__builtin_neon_vreinterpretdiv8qi (__a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vreinterpret_p64_s16 (int16x4_t __a) +{ + return (poly64x1_t)__builtin_neon_vreinterpretdiv4hi (__a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vreinterpret_p64_s32 (int32x2_t __a) +{ + return (poly64x1_t)__builtin_neon_vreinterpretdiv2si (__a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vreinterpret_p64_u8 (uint8x8_t __a) +{ + return (poly64x1_t)__builtin_neon_vreinterpretdiv8qi ((int8x8_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vreinterpret_p64_u16 (uint16x4_t __a) +{ + return (poly64x1_t)__builtin_neon_vreinterpretdiv4hi ((int16x4_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x1_t __attribute__ ((__always_inline__)) +vreinterpret_p64_u32 (uint32x2_t __a) +{ + return (poly64x1_t)__builtin_neon_vreinterpretdiv2si ((int32x2_t) __a); +} + +#endif +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vreinterpret_s64_p8 (poly8x8_t __a) +{ + return (int64x1_t)__builtin_neon_vreinterpretdiv8qi ((int8x8_t) __a); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vreinterpret_s64_p16 (poly16x4_t __a) +{ + return (int64x1_t)__builtin_neon_vreinterpretdiv4hi ((int16x4_t) __a); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vreinterpret_s64_f32 (float32x2_t __a) +{ + return (int64x1_t)__builtin_neon_vreinterpretdiv2sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vreinterpret_s64_p64 (poly64x1_t __a) +{ + return (int64x1_t)__builtin_neon_vreinterpretdidi (__a); +} + +#endif +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vreinterpret_s64_u64 (uint64x1_t __a) +{ + return (int64x1_t)__builtin_neon_vreinterpretdidi ((int64x1_t) __a); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vreinterpret_s64_s8 (int8x8_t __a) +{ + return (int64x1_t)__builtin_neon_vreinterpretdiv8qi (__a); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vreinterpret_s64_s16 (int16x4_t __a) +{ + return (int64x1_t)__builtin_neon_vreinterpretdiv4hi (__a); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vreinterpret_s64_s32 (int32x2_t __a) +{ + return (int64x1_t)__builtin_neon_vreinterpretdiv2si (__a); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vreinterpret_s64_u8 (uint8x8_t __a) +{ + return (int64x1_t)__builtin_neon_vreinterpretdiv8qi ((int8x8_t) __a); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vreinterpret_s64_u16 (uint16x4_t __a) +{ + return (int64x1_t)__builtin_neon_vreinterpretdiv4hi ((int16x4_t) __a); +} + +__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) +vreinterpret_s64_u32 (uint32x2_t __a) +{ + return (int64x1_t)__builtin_neon_vreinterpretdiv2si ((int32x2_t) __a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vreinterpret_u64_p8 (poly8x8_t __a) +{ + return (uint64x1_t)__builtin_neon_vreinterpretdiv8qi ((int8x8_t) __a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vreinterpret_u64_p16 (poly16x4_t __a) +{ + return (uint64x1_t)__builtin_neon_vreinterpretdiv4hi ((int16x4_t) __a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vreinterpret_u64_f32 (float32x2_t __a) +{ + return (uint64x1_t)__builtin_neon_vreinterpretdiv2sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vreinterpret_u64_p64 (poly64x1_t __a) +{ + return (uint64x1_t)__builtin_neon_vreinterpretdidi (__a); +} + +#endif +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vreinterpret_u64_s64 (int64x1_t __a) +{ + return (uint64x1_t)__builtin_neon_vreinterpretdidi (__a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vreinterpret_u64_s8 (int8x8_t __a) +{ + return (uint64x1_t)__builtin_neon_vreinterpretdiv8qi (__a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vreinterpret_u64_s16 (int16x4_t __a) +{ + return (uint64x1_t)__builtin_neon_vreinterpretdiv4hi (__a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vreinterpret_u64_s32 (int32x2_t __a) +{ + return (uint64x1_t)__builtin_neon_vreinterpretdiv2si (__a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vreinterpret_u64_u8 (uint8x8_t __a) +{ + return (uint64x1_t)__builtin_neon_vreinterpretdiv8qi ((int8x8_t) __a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vreinterpret_u64_u16 (uint16x4_t __a) +{ + return (uint64x1_t)__builtin_neon_vreinterpretdiv4hi ((int16x4_t) __a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vreinterpret_u64_u32 (uint32x2_t __a) +{ + return (uint64x1_t)__builtin_neon_vreinterpretdiv2si ((int32x2_t) __a); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vreinterpret_s8_p8 (poly8x8_t __a) +{ + return (int8x8_t)__builtin_neon_vreinterpretv8qiv8qi ((int8x8_t) __a); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vreinterpret_s8_p16 (poly16x4_t __a) +{ + return (int8x8_t)__builtin_neon_vreinterpretv8qiv4hi ((int16x4_t) __a); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vreinterpret_s8_f32 (float32x2_t __a) +{ + return (int8x8_t)__builtin_neon_vreinterpretv8qiv2sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vreinterpret_s8_p64 (poly64x1_t __a) +{ + return (int8x8_t)__builtin_neon_vreinterpretv8qidi (__a); +} + +#endif +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vreinterpret_s8_s64 (int64x1_t __a) +{ + return (int8x8_t)__builtin_neon_vreinterpretv8qidi (__a); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vreinterpret_s8_u64 (uint64x1_t __a) +{ + return (int8x8_t)__builtin_neon_vreinterpretv8qidi ((int64x1_t) __a); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vreinterpret_s8_s16 (int16x4_t __a) +{ + return (int8x8_t)__builtin_neon_vreinterpretv8qiv4hi (__a); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vreinterpret_s8_s32 (int32x2_t __a) +{ + return (int8x8_t)__builtin_neon_vreinterpretv8qiv2si (__a); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vreinterpret_s8_u8 (uint8x8_t __a) +{ + return (int8x8_t)__builtin_neon_vreinterpretv8qiv8qi ((int8x8_t) __a); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vreinterpret_s8_u16 (uint16x4_t __a) +{ + return (int8x8_t)__builtin_neon_vreinterpretv8qiv4hi ((int16x4_t) __a); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vreinterpret_s8_u32 (uint32x2_t __a) +{ + return (int8x8_t)__builtin_neon_vreinterpretv8qiv2si ((int32x2_t) __a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vreinterpret_s16_p8 (poly8x8_t __a) +{ + return (int16x4_t)__builtin_neon_vreinterpretv4hiv8qi ((int8x8_t) __a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vreinterpret_s16_p16 (poly16x4_t __a) +{ + return (int16x4_t)__builtin_neon_vreinterpretv4hiv4hi ((int16x4_t) __a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vreinterpret_s16_f32 (float32x2_t __a) +{ + return (int16x4_t)__builtin_neon_vreinterpretv4hiv2sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vreinterpret_s16_p64 (poly64x1_t __a) +{ + return (int16x4_t)__builtin_neon_vreinterpretv4hidi (__a); +} + +#endif +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vreinterpret_s16_s64 (int64x1_t __a) +{ + return (int16x4_t)__builtin_neon_vreinterpretv4hidi (__a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vreinterpret_s16_u64 (uint64x1_t __a) +{ + return (int16x4_t)__builtin_neon_vreinterpretv4hidi ((int64x1_t) __a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vreinterpret_s16_s8 (int8x8_t __a) +{ + return (int16x4_t)__builtin_neon_vreinterpretv4hiv8qi (__a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vreinterpret_s16_s32 (int32x2_t __a) +{ + return (int16x4_t)__builtin_neon_vreinterpretv4hiv2si (__a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vreinterpret_s16_u8 (uint8x8_t __a) +{ + return (int16x4_t)__builtin_neon_vreinterpretv4hiv8qi ((int8x8_t) __a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vreinterpret_s16_u16 (uint16x4_t __a) +{ + return (int16x4_t)__builtin_neon_vreinterpretv4hiv4hi ((int16x4_t) __a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vreinterpret_s16_u32 (uint32x2_t __a) +{ + return (int16x4_t)__builtin_neon_vreinterpretv4hiv2si ((int32x2_t) __a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vreinterpret_s32_p8 (poly8x8_t __a) +{ + return (int32x2_t)__builtin_neon_vreinterpretv2siv8qi ((int8x8_t) __a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vreinterpret_s32_p16 (poly16x4_t __a) +{ + return (int32x2_t)__builtin_neon_vreinterpretv2siv4hi ((int16x4_t) __a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vreinterpret_s32_f32 (float32x2_t __a) +{ + return (int32x2_t)__builtin_neon_vreinterpretv2siv2sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vreinterpret_s32_p64 (poly64x1_t __a) +{ + return (int32x2_t)__builtin_neon_vreinterpretv2sidi (__a); +} + +#endif +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vreinterpret_s32_s64 (int64x1_t __a) +{ + return (int32x2_t)__builtin_neon_vreinterpretv2sidi (__a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vreinterpret_s32_u64 (uint64x1_t __a) +{ + return (int32x2_t)__builtin_neon_vreinterpretv2sidi ((int64x1_t) __a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vreinterpret_s32_s8 (int8x8_t __a) +{ + return (int32x2_t)__builtin_neon_vreinterpretv2siv8qi (__a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vreinterpret_s32_s16 (int16x4_t __a) +{ + return (int32x2_t)__builtin_neon_vreinterpretv2siv4hi (__a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vreinterpret_s32_u8 (uint8x8_t __a) +{ + return (int32x2_t)__builtin_neon_vreinterpretv2siv8qi ((int8x8_t) __a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vreinterpret_s32_u16 (uint16x4_t __a) +{ + return (int32x2_t)__builtin_neon_vreinterpretv2siv4hi ((int16x4_t) __a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vreinterpret_s32_u32 (uint32x2_t __a) +{ + return (int32x2_t)__builtin_neon_vreinterpretv2siv2si ((int32x2_t) __a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vreinterpret_u8_p8 (poly8x8_t __a) +{ + return (uint8x8_t)__builtin_neon_vreinterpretv8qiv8qi ((int8x8_t) __a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vreinterpret_u8_p16 (poly16x4_t __a) +{ + return (uint8x8_t)__builtin_neon_vreinterpretv8qiv4hi ((int16x4_t) __a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vreinterpret_u8_f32 (float32x2_t __a) +{ + return (uint8x8_t)__builtin_neon_vreinterpretv8qiv2sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vreinterpret_u8_p64 (poly64x1_t __a) +{ + return (uint8x8_t)__builtin_neon_vreinterpretv8qidi (__a); +} + +#endif +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vreinterpret_u8_s64 (int64x1_t __a) +{ + return (uint8x8_t)__builtin_neon_vreinterpretv8qidi (__a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vreinterpret_u8_u64 (uint64x1_t __a) +{ + return (uint8x8_t)__builtin_neon_vreinterpretv8qidi ((int64x1_t) __a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vreinterpret_u8_s8 (int8x8_t __a) +{ + return (uint8x8_t)__builtin_neon_vreinterpretv8qiv8qi (__a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vreinterpret_u8_s16 (int16x4_t __a) +{ + return (uint8x8_t)__builtin_neon_vreinterpretv8qiv4hi (__a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vreinterpret_u8_s32 (int32x2_t __a) +{ + return (uint8x8_t)__builtin_neon_vreinterpretv8qiv2si (__a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vreinterpret_u8_u16 (uint16x4_t __a) +{ + return (uint8x8_t)__builtin_neon_vreinterpretv8qiv4hi ((int16x4_t) __a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vreinterpret_u8_u32 (uint32x2_t __a) +{ + return (uint8x8_t)__builtin_neon_vreinterpretv8qiv2si ((int32x2_t) __a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vreinterpret_u16_p8 (poly8x8_t __a) +{ + return (uint16x4_t)__builtin_neon_vreinterpretv4hiv8qi ((int8x8_t) __a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vreinterpret_u16_p16 (poly16x4_t __a) +{ + return (uint16x4_t)__builtin_neon_vreinterpretv4hiv4hi ((int16x4_t) __a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vreinterpret_u16_f32 (float32x2_t __a) +{ + return (uint16x4_t)__builtin_neon_vreinterpretv4hiv2sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vreinterpret_u16_p64 (poly64x1_t __a) +{ + return (uint16x4_t)__builtin_neon_vreinterpretv4hidi (__a); +} + +#endif +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vreinterpret_u16_s64 (int64x1_t __a) +{ + return (uint16x4_t)__builtin_neon_vreinterpretv4hidi (__a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vreinterpret_u16_u64 (uint64x1_t __a) +{ + return (uint16x4_t)__builtin_neon_vreinterpretv4hidi ((int64x1_t) __a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vreinterpret_u16_s8 (int8x8_t __a) +{ + return (uint16x4_t)__builtin_neon_vreinterpretv4hiv8qi (__a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vreinterpret_u16_s16 (int16x4_t __a) +{ + return (uint16x4_t)__builtin_neon_vreinterpretv4hiv4hi (__a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vreinterpret_u16_s32 (int32x2_t __a) +{ + return (uint16x4_t)__builtin_neon_vreinterpretv4hiv2si (__a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vreinterpret_u16_u8 (uint8x8_t __a) +{ + return (uint16x4_t)__builtin_neon_vreinterpretv4hiv8qi ((int8x8_t) __a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vreinterpret_u16_u32 (uint32x2_t __a) +{ + return (uint16x4_t)__builtin_neon_vreinterpretv4hiv2si ((int32x2_t) __a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vreinterpret_u32_p8 (poly8x8_t __a) +{ + return (uint32x2_t)__builtin_neon_vreinterpretv2siv8qi ((int8x8_t) __a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vreinterpret_u32_p16 (poly16x4_t __a) +{ + return (uint32x2_t)__builtin_neon_vreinterpretv2siv4hi ((int16x4_t) __a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vreinterpret_u32_f32 (float32x2_t __a) +{ + return (uint32x2_t)__builtin_neon_vreinterpretv2siv2sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vreinterpret_u32_p64 (poly64x1_t __a) +{ + return (uint32x2_t)__builtin_neon_vreinterpretv2sidi (__a); +} + +#endif +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vreinterpret_u32_s64 (int64x1_t __a) +{ + return (uint32x2_t)__builtin_neon_vreinterpretv2sidi (__a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vreinterpret_u32_u64 (uint64x1_t __a) +{ + return (uint32x2_t)__builtin_neon_vreinterpretv2sidi ((int64x1_t) __a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vreinterpret_u32_s8 (int8x8_t __a) +{ + return (uint32x2_t)__builtin_neon_vreinterpretv2siv8qi (__a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vreinterpret_u32_s16 (int16x4_t __a) +{ + return (uint32x2_t)__builtin_neon_vreinterpretv2siv4hi (__a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vreinterpret_u32_s32 (int32x2_t __a) +{ + return (uint32x2_t)__builtin_neon_vreinterpretv2siv2si (__a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vreinterpret_u32_u8 (uint8x8_t __a) +{ + return (uint32x2_t)__builtin_neon_vreinterpretv2siv8qi ((int8x8_t) __a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vreinterpret_u32_u16 (uint16x4_t __a) +{ + return (uint32x2_t)__builtin_neon_vreinterpretv2siv4hi ((int16x4_t) __a); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_p8_p16 (poly16x8_t __a) +{ + return (poly8x16_t)__builtin_neon_vreinterpretv16qiv8hi ((int16x8_t) __a); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_p8_f32 (float32x4_t __a) +{ + return (poly8x16_t)__builtin_neon_vreinterpretv16qiv4sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_p8_p64 (poly64x2_t __a) +{ + return (poly8x16_t)__builtin_neon_vreinterpretv16qiv2di ((int64x2_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_p8_p128 (poly128_t __a) +{ + return (poly8x16_t)__builtin_neon_vreinterpretv16qiti ((__builtin_neon_ti) __a); +} + +#endif +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_p8_s64 (int64x2_t __a) +{ + return (poly8x16_t)__builtin_neon_vreinterpretv16qiv2di (__a); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_p8_u64 (uint64x2_t __a) +{ + return (poly8x16_t)__builtin_neon_vreinterpretv16qiv2di ((int64x2_t) __a); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_p8_s8 (int8x16_t __a) +{ + return (poly8x16_t)__builtin_neon_vreinterpretv16qiv16qi (__a); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_p8_s16 (int16x8_t __a) +{ + return (poly8x16_t)__builtin_neon_vreinterpretv16qiv8hi (__a); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_p8_s32 (int32x4_t __a) +{ + return (poly8x16_t)__builtin_neon_vreinterpretv16qiv4si (__a); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_p8_u8 (uint8x16_t __a) +{ + return (poly8x16_t)__builtin_neon_vreinterpretv16qiv16qi ((int8x16_t) __a); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_p8_u16 (uint16x8_t __a) +{ + return (poly8x16_t)__builtin_neon_vreinterpretv16qiv8hi ((int16x8_t) __a); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_p8_u32 (uint32x4_t __a) +{ + return (poly8x16_t)__builtin_neon_vreinterpretv16qiv4si ((int32x4_t) __a); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_p16_p8 (poly8x16_t __a) +{ + return (poly16x8_t)__builtin_neon_vreinterpretv8hiv16qi ((int8x16_t) __a); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_p16_f32 (float32x4_t __a) +{ + return (poly16x8_t)__builtin_neon_vreinterpretv8hiv4sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_p16_p64 (poly64x2_t __a) +{ + return (poly16x8_t)__builtin_neon_vreinterpretv8hiv2di ((int64x2_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_p16_p128 (poly128_t __a) +{ + return (poly16x8_t)__builtin_neon_vreinterpretv8hiti ((__builtin_neon_ti) __a); +} + +#endif +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_p16_s64 (int64x2_t __a) +{ + return (poly16x8_t)__builtin_neon_vreinterpretv8hiv2di (__a); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_p16_u64 (uint64x2_t __a) +{ + return (poly16x8_t)__builtin_neon_vreinterpretv8hiv2di ((int64x2_t) __a); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_p16_s8 (int8x16_t __a) +{ + return (poly16x8_t)__builtin_neon_vreinterpretv8hiv16qi (__a); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_p16_s16 (int16x8_t __a) +{ + return (poly16x8_t)__builtin_neon_vreinterpretv8hiv8hi (__a); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_p16_s32 (int32x4_t __a) +{ + return (poly16x8_t)__builtin_neon_vreinterpretv8hiv4si (__a); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_p16_u8 (uint8x16_t __a) +{ + return (poly16x8_t)__builtin_neon_vreinterpretv8hiv16qi ((int8x16_t) __a); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_p16_u16 (uint16x8_t __a) +{ + return (poly16x8_t)__builtin_neon_vreinterpretv8hiv8hi ((int16x8_t) __a); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_p16_u32 (uint32x4_t __a) +{ + return (poly16x8_t)__builtin_neon_vreinterpretv8hiv4si ((int32x4_t) __a); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_f32_p8 (poly8x16_t __a) +{ + return (float32x4_t)__builtin_neon_vreinterpretv4sfv16qi ((int8x16_t) __a); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_f32_p16 (poly16x8_t __a) +{ + return (float32x4_t)__builtin_neon_vreinterpretv4sfv8hi ((int16x8_t) __a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_f32_p64 (poly64x2_t __a) +{ + return (float32x4_t)__builtin_neon_vreinterpretv4sfv2di ((int64x2_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_f32_p128 (poly128_t __a) +{ + return (float32x4_t)__builtin_neon_vreinterpretv4sfti ((__builtin_neon_ti) __a); +} + +#endif +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_f32_s64 (int64x2_t __a) +{ + return (float32x4_t)__builtin_neon_vreinterpretv4sfv2di (__a); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_f32_u64 (uint64x2_t __a) +{ + return (float32x4_t)__builtin_neon_vreinterpretv4sfv2di ((int64x2_t) __a); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_f32_s8 (int8x16_t __a) +{ + return (float32x4_t)__builtin_neon_vreinterpretv4sfv16qi (__a); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_f32_s16 (int16x8_t __a) +{ + return (float32x4_t)__builtin_neon_vreinterpretv4sfv8hi (__a); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_f32_s32 (int32x4_t __a) +{ + return (float32x4_t)__builtin_neon_vreinterpretv4sfv4si (__a); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_f32_u8 (uint8x16_t __a) +{ + return (float32x4_t)__builtin_neon_vreinterpretv4sfv16qi ((int8x16_t) __a); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_f32_u16 (uint16x8_t __a) +{ + return (float32x4_t)__builtin_neon_vreinterpretv4sfv8hi ((int16x8_t) __a); +} + +__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_f32_u32 (uint32x4_t __a) +{ + return (float32x4_t)__builtin_neon_vreinterpretv4sfv4si ((int32x4_t) __a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_p64_p8 (poly8x16_t __a) +{ + return (poly64x2_t)__builtin_neon_vreinterpretv2div16qi ((int8x16_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_p64_p16 (poly16x8_t __a) +{ + return (poly64x2_t)__builtin_neon_vreinterpretv2div8hi ((int16x8_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_p64_f32 (float32x4_t __a) +{ + return (poly64x2_t)__builtin_neon_vreinterpretv2div4sf (__a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_p64_p128 (poly128_t __a) +{ + return (poly64x2_t)__builtin_neon_vreinterpretv2diti ((__builtin_neon_ti) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_p64_s64 (int64x2_t __a) +{ + return (poly64x2_t)__builtin_neon_vreinterpretv2div2di (__a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_p64_u64 (uint64x2_t __a) +{ + return (poly64x2_t)__builtin_neon_vreinterpretv2div2di ((int64x2_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_p64_s8 (int8x16_t __a) +{ + return (poly64x2_t)__builtin_neon_vreinterpretv2div16qi (__a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_p64_s16 (int16x8_t __a) +{ + return (poly64x2_t)__builtin_neon_vreinterpretv2div8hi (__a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_p64_s32 (int32x4_t __a) +{ + return (poly64x2_t)__builtin_neon_vreinterpretv2div4si (__a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_p64_u8 (uint8x16_t __a) +{ + return (poly64x2_t)__builtin_neon_vreinterpretv2div16qi ((int8x16_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_p64_u16 (uint16x8_t __a) +{ + return (poly64x2_t)__builtin_neon_vreinterpretv2div8hi ((int16x8_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_p64_u32 (uint32x4_t __a) +{ + return (poly64x2_t)__builtin_neon_vreinterpretv2div4si ((int32x4_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vreinterpretq_p128_p8 (poly8x16_t __a) +{ + return (poly128_t)__builtin_neon_vreinterprettiv16qi ((int8x16_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vreinterpretq_p128_p16 (poly16x8_t __a) +{ + return (poly128_t)__builtin_neon_vreinterprettiv8hi ((int16x8_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vreinterpretq_p128_f32 (float32x4_t __a) +{ + return (poly128_t)__builtin_neon_vreinterprettiv4sf (__a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vreinterpretq_p128_p64 (poly64x2_t __a) +{ + return (poly128_t)__builtin_neon_vreinterprettiv2di ((int64x2_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vreinterpretq_p128_s64 (int64x2_t __a) +{ + return (poly128_t)__builtin_neon_vreinterprettiv2di (__a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vreinterpretq_p128_u64 (uint64x2_t __a) +{ + return (poly128_t)__builtin_neon_vreinterprettiv2di ((int64x2_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vreinterpretq_p128_s8 (int8x16_t __a) +{ + return (poly128_t)__builtin_neon_vreinterprettiv16qi (__a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vreinterpretq_p128_s16 (int16x8_t __a) +{ + return (poly128_t)__builtin_neon_vreinterprettiv8hi (__a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vreinterpretq_p128_s32 (int32x4_t __a) +{ + return (poly128_t)__builtin_neon_vreinterprettiv4si (__a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vreinterpretq_p128_u8 (uint8x16_t __a) +{ + return (poly128_t)__builtin_neon_vreinterprettiv16qi ((int8x16_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vreinterpretq_p128_u16 (uint16x8_t __a) +{ + return (poly128_t)__builtin_neon_vreinterprettiv8hi ((int16x8_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vreinterpretq_p128_u32 (uint32x4_t __a) +{ + return (poly128_t)__builtin_neon_vreinterprettiv4si ((int32x4_t) __a); +} + +#endif +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_s64_p8 (poly8x16_t __a) +{ + return (int64x2_t)__builtin_neon_vreinterpretv2div16qi ((int8x16_t) __a); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_s64_p16 (poly16x8_t __a) +{ + return (int64x2_t)__builtin_neon_vreinterpretv2div8hi ((int16x8_t) __a); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_s64_f32 (float32x4_t __a) +{ + return (int64x2_t)__builtin_neon_vreinterpretv2div4sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_s64_p64 (poly64x2_t __a) +{ + return (int64x2_t)__builtin_neon_vreinterpretv2div2di ((int64x2_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_s64_p128 (poly128_t __a) +{ + return (int64x2_t)__builtin_neon_vreinterpretv2diti ((__builtin_neon_ti) __a); +} + +#endif +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_s64_u64 (uint64x2_t __a) +{ + return (int64x2_t)__builtin_neon_vreinterpretv2div2di ((int64x2_t) __a); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_s64_s8 (int8x16_t __a) +{ + return (int64x2_t)__builtin_neon_vreinterpretv2div16qi (__a); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_s64_s16 (int16x8_t __a) +{ + return (int64x2_t)__builtin_neon_vreinterpretv2div8hi (__a); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_s64_s32 (int32x4_t __a) +{ + return (int64x2_t)__builtin_neon_vreinterpretv2div4si (__a); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_s64_u8 (uint8x16_t __a) +{ + return (int64x2_t)__builtin_neon_vreinterpretv2div16qi ((int8x16_t) __a); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_s64_u16 (uint16x8_t __a) +{ + return (int64x2_t)__builtin_neon_vreinterpretv2div8hi ((int16x8_t) __a); +} + +__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_s64_u32 (uint32x4_t __a) +{ + return (int64x2_t)__builtin_neon_vreinterpretv2div4si ((int32x4_t) __a); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_u64_p8 (poly8x16_t __a) +{ + return (uint64x2_t)__builtin_neon_vreinterpretv2div16qi ((int8x16_t) __a); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_u64_p16 (poly16x8_t __a) +{ + return (uint64x2_t)__builtin_neon_vreinterpretv2div8hi ((int16x8_t) __a); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_u64_f32 (float32x4_t __a) +{ + return (uint64x2_t)__builtin_neon_vreinterpretv2div4sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_u64_p64 (poly64x2_t __a) +{ + return (uint64x2_t)__builtin_neon_vreinterpretv2div2di ((int64x2_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_u64_p128 (poly128_t __a) +{ + return (uint64x2_t)__builtin_neon_vreinterpretv2diti ((__builtin_neon_ti) __a); +} + +#endif +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_u64_s64 (int64x2_t __a) +{ + return (uint64x2_t)__builtin_neon_vreinterpretv2div2di (__a); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_u64_s8 (int8x16_t __a) +{ + return (uint64x2_t)__builtin_neon_vreinterpretv2div16qi (__a); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_u64_s16 (int16x8_t __a) +{ + return (uint64x2_t)__builtin_neon_vreinterpretv2div8hi (__a); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_u64_s32 (int32x4_t __a) +{ + return (uint64x2_t)__builtin_neon_vreinterpretv2div4si (__a); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_u64_u8 (uint8x16_t __a) +{ + return (uint64x2_t)__builtin_neon_vreinterpretv2div16qi ((int8x16_t) __a); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_u64_u16 (uint16x8_t __a) +{ + return (uint64x2_t)__builtin_neon_vreinterpretv2div8hi ((int16x8_t) __a); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_u64_u32 (uint32x4_t __a) +{ + return (uint64x2_t)__builtin_neon_vreinterpretv2div4si ((int32x4_t) __a); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_s8_p8 (poly8x16_t __a) +{ + return (int8x16_t)__builtin_neon_vreinterpretv16qiv16qi ((int8x16_t) __a); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_s8_p16 (poly16x8_t __a) +{ + return (int8x16_t)__builtin_neon_vreinterpretv16qiv8hi ((int16x8_t) __a); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_s8_f32 (float32x4_t __a) +{ + return (int8x16_t)__builtin_neon_vreinterpretv16qiv4sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_s8_p64 (poly64x2_t __a) +{ + return (int8x16_t)__builtin_neon_vreinterpretv16qiv2di ((int64x2_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_s8_p128 (poly128_t __a) +{ + return (int8x16_t)__builtin_neon_vreinterpretv16qiti ((__builtin_neon_ti) __a); +} + +#endif +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_s8_s64 (int64x2_t __a) +{ + return (int8x16_t)__builtin_neon_vreinterpretv16qiv2di (__a); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_s8_u64 (uint64x2_t __a) +{ + return (int8x16_t)__builtin_neon_vreinterpretv16qiv2di ((int64x2_t) __a); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_s8_s16 (int16x8_t __a) +{ + return (int8x16_t)__builtin_neon_vreinterpretv16qiv8hi (__a); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_s8_s32 (int32x4_t __a) +{ + return (int8x16_t)__builtin_neon_vreinterpretv16qiv4si (__a); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_s8_u8 (uint8x16_t __a) +{ + return (int8x16_t)__builtin_neon_vreinterpretv16qiv16qi ((int8x16_t) __a); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_s8_u16 (uint16x8_t __a) +{ + return (int8x16_t)__builtin_neon_vreinterpretv16qiv8hi ((int16x8_t) __a); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_s8_u32 (uint32x4_t __a) +{ + return (int8x16_t)__builtin_neon_vreinterpretv16qiv4si ((int32x4_t) __a); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_s16_p8 (poly8x16_t __a) +{ + return (int16x8_t)__builtin_neon_vreinterpretv8hiv16qi ((int8x16_t) __a); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_s16_p16 (poly16x8_t __a) +{ + return (int16x8_t)__builtin_neon_vreinterpretv8hiv8hi ((int16x8_t) __a); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_s16_f32 (float32x4_t __a) +{ + return (int16x8_t)__builtin_neon_vreinterpretv8hiv4sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_s16_p64 (poly64x2_t __a) +{ + return (int16x8_t)__builtin_neon_vreinterpretv8hiv2di ((int64x2_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_s16_p128 (poly128_t __a) +{ + return (int16x8_t)__builtin_neon_vreinterpretv8hiti ((__builtin_neon_ti) __a); +} + +#endif +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_s16_s64 (int64x2_t __a) +{ + return (int16x8_t)__builtin_neon_vreinterpretv8hiv2di (__a); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_s16_u64 (uint64x2_t __a) +{ + return (int16x8_t)__builtin_neon_vreinterpretv8hiv2di ((int64x2_t) __a); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_s16_s8 (int8x16_t __a) +{ + return (int16x8_t)__builtin_neon_vreinterpretv8hiv16qi (__a); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_s16_s32 (int32x4_t __a) +{ + return (int16x8_t)__builtin_neon_vreinterpretv8hiv4si (__a); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_s16_u8 (uint8x16_t __a) +{ + return (int16x8_t)__builtin_neon_vreinterpretv8hiv16qi ((int8x16_t) __a); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_s16_u16 (uint16x8_t __a) +{ + return (int16x8_t)__builtin_neon_vreinterpretv8hiv8hi ((int16x8_t) __a); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_s16_u32 (uint32x4_t __a) +{ + return (int16x8_t)__builtin_neon_vreinterpretv8hiv4si ((int32x4_t) __a); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_s32_p8 (poly8x16_t __a) +{ + return (int32x4_t)__builtin_neon_vreinterpretv4siv16qi ((int8x16_t) __a); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_s32_p16 (poly16x8_t __a) +{ + return (int32x4_t)__builtin_neon_vreinterpretv4siv8hi ((int16x8_t) __a); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_s32_f32 (float32x4_t __a) +{ + return (int32x4_t)__builtin_neon_vreinterpretv4siv4sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_s32_p64 (poly64x2_t __a) +{ + return (int32x4_t)__builtin_neon_vreinterpretv4siv2di ((int64x2_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_s32_p128 (poly128_t __a) +{ + return (int32x4_t)__builtin_neon_vreinterpretv4siti ((__builtin_neon_ti) __a); +} + +#endif +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_s32_s64 (int64x2_t __a) +{ + return (int32x4_t)__builtin_neon_vreinterpretv4siv2di (__a); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_s32_u64 (uint64x2_t __a) +{ + return (int32x4_t)__builtin_neon_vreinterpretv4siv2di ((int64x2_t) __a); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_s32_s8 (int8x16_t __a) +{ + return (int32x4_t)__builtin_neon_vreinterpretv4siv16qi (__a); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_s32_s16 (int16x8_t __a) +{ + return (int32x4_t)__builtin_neon_vreinterpretv4siv8hi (__a); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_s32_u8 (uint8x16_t __a) +{ + return (int32x4_t)__builtin_neon_vreinterpretv4siv16qi ((int8x16_t) __a); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_s32_u16 (uint16x8_t __a) +{ + return (int32x4_t)__builtin_neon_vreinterpretv4siv8hi ((int16x8_t) __a); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_s32_u32 (uint32x4_t __a) +{ + return (int32x4_t)__builtin_neon_vreinterpretv4siv4si ((int32x4_t) __a); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_u8_p8 (poly8x16_t __a) +{ + return (uint8x16_t)__builtin_neon_vreinterpretv16qiv16qi ((int8x16_t) __a); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_u8_p16 (poly16x8_t __a) +{ + return (uint8x16_t)__builtin_neon_vreinterpretv16qiv8hi ((int16x8_t) __a); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_u8_f32 (float32x4_t __a) +{ + return (uint8x16_t)__builtin_neon_vreinterpretv16qiv4sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_u8_p64 (poly64x2_t __a) +{ + return (uint8x16_t)__builtin_neon_vreinterpretv16qiv2di ((int64x2_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_u8_p128 (poly128_t __a) +{ + return (uint8x16_t)__builtin_neon_vreinterpretv16qiti ((__builtin_neon_ti) __a); +} + +#endif +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_u8_s64 (int64x2_t __a) +{ + return (uint8x16_t)__builtin_neon_vreinterpretv16qiv2di (__a); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_u8_u64 (uint64x2_t __a) +{ + return (uint8x16_t)__builtin_neon_vreinterpretv16qiv2di ((int64x2_t) __a); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_u8_s8 (int8x16_t __a) +{ + return (uint8x16_t)__builtin_neon_vreinterpretv16qiv16qi (__a); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_u8_s16 (int16x8_t __a) +{ + return (uint8x16_t)__builtin_neon_vreinterpretv16qiv8hi (__a); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_u8_s32 (int32x4_t __a) +{ + return (uint8x16_t)__builtin_neon_vreinterpretv16qiv4si (__a); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_u8_u16 (uint16x8_t __a) +{ + return (uint8x16_t)__builtin_neon_vreinterpretv16qiv8hi ((int16x8_t) __a); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_u8_u32 (uint32x4_t __a) +{ + return (uint8x16_t)__builtin_neon_vreinterpretv16qiv4si ((int32x4_t) __a); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_u16_p8 (poly8x16_t __a) +{ + return (uint16x8_t)__builtin_neon_vreinterpretv8hiv16qi ((int8x16_t) __a); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_u16_p16 (poly16x8_t __a) +{ + return (uint16x8_t)__builtin_neon_vreinterpretv8hiv8hi ((int16x8_t) __a); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_u16_f32 (float32x4_t __a) +{ + return (uint16x8_t)__builtin_neon_vreinterpretv8hiv4sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_u16_p64 (poly64x2_t __a) +{ + return (uint16x8_t)__builtin_neon_vreinterpretv8hiv2di ((int64x2_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_u16_p128 (poly128_t __a) +{ + return (uint16x8_t)__builtin_neon_vreinterpretv8hiti ((__builtin_neon_ti) __a); +} + +#endif +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_u16_s64 (int64x2_t __a) +{ + return (uint16x8_t)__builtin_neon_vreinterpretv8hiv2di (__a); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_u16_u64 (uint64x2_t __a) +{ + return (uint16x8_t)__builtin_neon_vreinterpretv8hiv2di ((int64x2_t) __a); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_u16_s8 (int8x16_t __a) +{ + return (uint16x8_t)__builtin_neon_vreinterpretv8hiv16qi (__a); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_u16_s16 (int16x8_t __a) +{ + return (uint16x8_t)__builtin_neon_vreinterpretv8hiv8hi (__a); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_u16_s32 (int32x4_t __a) +{ + return (uint16x8_t)__builtin_neon_vreinterpretv8hiv4si (__a); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_u16_u8 (uint8x16_t __a) +{ + return (uint16x8_t)__builtin_neon_vreinterpretv8hiv16qi ((int8x16_t) __a); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_u16_u32 (uint32x4_t __a) +{ + return (uint16x8_t)__builtin_neon_vreinterpretv8hiv4si ((int32x4_t) __a); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_u32_p8 (poly8x16_t __a) +{ + return (uint32x4_t)__builtin_neon_vreinterpretv4siv16qi ((int8x16_t) __a); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_u32_p16 (poly16x8_t __a) +{ + return (uint32x4_t)__builtin_neon_vreinterpretv4siv8hi ((int16x8_t) __a); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_u32_f32 (float32x4_t __a) +{ + return (uint32x4_t)__builtin_neon_vreinterpretv4siv4sf (__a); +} + +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_u32_p64 (poly64x2_t __a) +{ + return (uint32x4_t)__builtin_neon_vreinterpretv4siv2di ((int64x2_t) __a); +} + +#endif +#ifdef __ARM_FEATURE_CRYPTO +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_u32_p128 (poly128_t __a) +{ + return (uint32x4_t)__builtin_neon_vreinterpretv4siti ((__builtin_neon_ti) __a); +} + +#endif +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_u32_s64 (int64x2_t __a) +{ + return (uint32x4_t)__builtin_neon_vreinterpretv4siv2di (__a); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_u32_u64 (uint64x2_t __a) +{ + return (uint32x4_t)__builtin_neon_vreinterpretv4siv2di ((int64x2_t) __a); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_u32_s8 (int8x16_t __a) +{ + return (uint32x4_t)__builtin_neon_vreinterpretv4siv16qi (__a); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_u32_s16 (int16x8_t __a) +{ + return (uint32x4_t)__builtin_neon_vreinterpretv4siv8hi (__a); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_u32_s32 (int32x4_t __a) +{ + return (uint32x4_t)__builtin_neon_vreinterpretv4siv4si (__a); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_u32_u8 (uint8x16_t __a) +{ + return (uint32x4_t)__builtin_neon_vreinterpretv4siv16qi ((int8x16_t) __a); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_u32_u16 (uint16x8_t __a) +{ + return (uint32x4_t)__builtin_neon_vreinterpretv4siv8hi ((int16x8_t) __a); +} + + +#ifdef __ARM_FEATURE_CRYPTO + +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vldrq_p128 (poly128_t const * __ptr) +{ +#ifdef __ARM_BIG_ENDIAN + poly64_t* __ptmp = (poly64_t*) __ptr; + poly64_t __d0 = vld1_p64 (__ptmp); + poly64_t __d1 = vld1_p64 (__ptmp + 1); + return vreinterpretq_p128_p64 (vcombine_p64 (__d1, __d0)); +#else + return vreinterpretq_p128_p64 (vld1q_p64 ((poly64_t*) __ptr)); +#endif +} + +__extension__ static __inline void __attribute__ ((__always_inline__)) +vstrq_p128 (poly128_t * __ptr, poly128_t __val) +{ +#ifdef __ARM_BIG_ENDIAN + poly64x2_t __tmp = vreinterpretq_p64_p128 (__val); + poly64_t __d0 = vget_high_p64 (__tmp); + poly64_t __d1 = vget_low_p64 (__tmp); + vst1q_p64 ((poly64_t*) __ptr, vcombine_p64 (__d0, __d1)); +#else + vst1q_p64 ((poly64_t*) __ptr, vreinterpretq_p64_p128 (__val)); +#endif +} + +/* The vceq_p64 intrinsic does not map to a single instruction. + Instead we emulate it by performing a 32-bit variant of the vceq + and applying a pairwise min reduction to the result. + vceq_u32 will produce two 32-bit halves, each of which will contain either + all ones or all zeros depending on whether the corresponding 32-bit + halves of the poly64_t were equal. The whole poly64_t values are equal + if and only if both halves are equal, i.e. vceq_u32 returns all ones. + If the result is all zeroes for any half then the whole result is zeroes. + This is what the pairwise min reduction achieves. */ + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vceq_p64 (poly64x1_t __a, poly64x1_t __b) +{ + uint32x2_t __t_a = vreinterpret_u32_p64 (__a); + uint32x2_t __t_b = vreinterpret_u32_p64 (__b); + uint32x2_t __c = vceq_u32 (__t_a, __t_b); + uint32x2_t __m = vpmin_u32 (__c, __c); + return vreinterpret_u64_u32 (__m); +} + +/* The vtst_p64 intrinsic does not map to a single instruction. + We emulate it in way similar to vceq_p64 above but here we do + a reduction with max since if any two corresponding bits + in the two poly64_t's match, then the whole result must be all ones. */ + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vtst_p64 (poly64x1_t __a, poly64x1_t __b) +{ + uint32x2_t __t_a = vreinterpret_u32_p64 (__a); + uint32x2_t __t_b = vreinterpret_u32_p64 (__b); + uint32x2_t __c = vtst_u32 (__t_a, __t_b); + uint32x2_t __m = vpmax_u32 (__c, __c); + return vreinterpret_u64_u32 (__m); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vaeseq_u8 (uint8x16_t __data, uint8x16_t __key) +{ + return __builtin_arm_crypto_aese (__data, __key); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vaesdq_u8 (uint8x16_t __data, uint8x16_t __key) +{ + return __builtin_arm_crypto_aesd (__data, __key); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vaesmcq_u8 (uint8x16_t __data) +{ + return __builtin_arm_crypto_aesmc (__data); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vaesimcq_u8 (uint8x16_t __data) +{ + return __builtin_arm_crypto_aesimc (__data); +} + +__extension__ static __inline uint32_t __attribute__ ((__always_inline__)) +vsha1h_u32 (uint32_t __hash_e) +{ + uint32x4_t __t = vdupq_n_u32 (0); + __t = vsetq_lane_u32 (__hash_e, __t, 0); + __t = __builtin_arm_crypto_sha1h (__t); + return vgetq_lane_u32 (__t, 0); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsha1cq_u32 (uint32x4_t __hash_abcd, uint32_t __hash_e, uint32x4_t __wk) +{ + uint32x4_t __t = vdupq_n_u32 (0); + __t = vsetq_lane_u32 (__hash_e, __t, 0); + return __builtin_arm_crypto_sha1c (__hash_abcd, __t, __wk); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsha1pq_u32 (uint32x4_t __hash_abcd, uint32_t __hash_e, uint32x4_t __wk) +{ + uint32x4_t __t = vdupq_n_u32 (0); + __t = vsetq_lane_u32 (__hash_e, __t, 0); + return __builtin_arm_crypto_sha1p (__hash_abcd, __t, __wk); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsha1mq_u32 (uint32x4_t __hash_abcd, uint32_t __hash_e, uint32x4_t __wk) +{ + uint32x4_t __t = vdupq_n_u32 (0); + __t = vsetq_lane_u32 (__hash_e, __t, 0); + return __builtin_arm_crypto_sha1m (__hash_abcd, __t, __wk); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsha1su0q_u32 (uint32x4_t __w0_3, uint32x4_t __w4_7, uint32x4_t __w8_11) +{ + return __builtin_arm_crypto_sha1su0 (__w0_3, __w4_7, __w8_11); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsha1su1q_u32 (uint32x4_t __tw0_3, uint32x4_t __w12_15) +{ + return __builtin_arm_crypto_sha1su1 (__tw0_3, __w12_15); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsha256hq_u32 (uint32x4_t __hash_abcd, uint32x4_t __hash_efgh, uint32x4_t __wk) +{ + return __builtin_arm_crypto_sha256h (__hash_abcd, __hash_efgh, __wk); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsha256h2q_u32 (uint32x4_t __hash_abcd, uint32x4_t __hash_efgh, uint32x4_t __wk) +{ + return __builtin_arm_crypto_sha256h2 (__hash_abcd, __hash_efgh, __wk); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsha256su0q_u32 (uint32x4_t __w0_3, uint32x4_t __w4_7) +{ + return __builtin_arm_crypto_sha256su0 (__w0_3, __w4_7); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vsha256su1q_u32 (uint32x4_t __tw0_3, uint32x4_t __w8_11, uint32x4_t __w12_15) +{ + return __builtin_arm_crypto_sha256su1 (__tw0_3, __w8_11, __w12_15); +} + +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vmull_p64 (poly64_t __a, poly64_t __b) +{ + return (poly128_t) __builtin_arm_crypto_vmullp64 ((uint64_t) __a, (uint64_t) __b); +} + +__extension__ static __inline poly128_t __attribute__ ((__always_inline__)) +vmull_high_p64 (poly64x2_t __a, poly64x2_t __b) +{ + poly64_t __t1 = vget_high_p64 (__a); + poly64_t __t2 = vget_high_p64 (__b); + + return (poly128_t) __builtin_arm_crypto_vmullp64 ((uint64_t) __t1, (uint64_t) __t2); +} + +#endif +#ifdef __cplusplus +} +#endif +#endif +#endif diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/float.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/float.h new file mode 100644 index 0000000..a8e05bf --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/float.h @@ -0,0 +1,277 @@ +/* Copyright (C) 2002-2014 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 3, or (at your option) +any later version. + +GCC is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + +/* + * ISO C Standard: 5.2.4.2.2 Characteristics of floating types <float.h> + */ + +#ifndef _FLOAT_H___ +#define _FLOAT_H___ + +/* Radix of exponent representation, b. */ +#undef FLT_RADIX +#define FLT_RADIX __FLT_RADIX__ + +/* Number of base-FLT_RADIX digits in the significand, p. */ +#undef FLT_MANT_DIG +#undef DBL_MANT_DIG +#undef LDBL_MANT_DIG +#define FLT_MANT_DIG __FLT_MANT_DIG__ +#define DBL_MANT_DIG __DBL_MANT_DIG__ +#define LDBL_MANT_DIG __LDBL_MANT_DIG__ + +/* Number of decimal digits, q, such that any floating-point number with q + decimal digits can be rounded into a floating-point number with p radix b + digits and back again without change to the q decimal digits, + + p * log10(b) if b is a power of 10 + floor((p - 1) * log10(b)) otherwise +*/ +#undef FLT_DIG +#undef DBL_DIG +#undef LDBL_DIG +#define FLT_DIG __FLT_DIG__ +#define DBL_DIG __DBL_DIG__ +#define LDBL_DIG __LDBL_DIG__ + +/* Minimum int x such that FLT_RADIX**(x-1) is a normalized float, emin */ +#undef FLT_MIN_EXP +#undef DBL_MIN_EXP +#undef LDBL_MIN_EXP +#define FLT_MIN_EXP __FLT_MIN_EXP__ +#define DBL_MIN_EXP __DBL_MIN_EXP__ +#define LDBL_MIN_EXP __LDBL_MIN_EXP__ + +/* Minimum negative integer such that 10 raised to that power is in the + range of normalized floating-point numbers, + + ceil(log10(b) * (emin - 1)) +*/ +#undef FLT_MIN_10_EXP +#undef DBL_MIN_10_EXP +#undef LDBL_MIN_10_EXP +#define FLT_MIN_10_EXP __FLT_MIN_10_EXP__ +#define DBL_MIN_10_EXP __DBL_MIN_10_EXP__ +#define LDBL_MIN_10_EXP __LDBL_MIN_10_EXP__ + +/* Maximum int x such that FLT_RADIX**(x-1) is a representable float, emax. */ +#undef FLT_MAX_EXP +#undef DBL_MAX_EXP +#undef LDBL_MAX_EXP +#define FLT_MAX_EXP __FLT_MAX_EXP__ +#define DBL_MAX_EXP __DBL_MAX_EXP__ +#define LDBL_MAX_EXP __LDBL_MAX_EXP__ + +/* Maximum integer such that 10 raised to that power is in the range of + representable finite floating-point numbers, + + floor(log10((1 - b**-p) * b**emax)) +*/ +#undef FLT_MAX_10_EXP +#undef DBL_MAX_10_EXP +#undef LDBL_MAX_10_EXP +#define FLT_MAX_10_EXP __FLT_MAX_10_EXP__ +#define DBL_MAX_10_EXP __DBL_MAX_10_EXP__ +#define LDBL_MAX_10_EXP __LDBL_MAX_10_EXP__ + +/* Maximum representable finite floating-point number, + + (1 - b**-p) * b**emax +*/ +#undef FLT_MAX +#undef DBL_MAX +#undef LDBL_MAX +#define FLT_MAX __FLT_MAX__ +#define DBL_MAX __DBL_MAX__ +#define LDBL_MAX __LDBL_MAX__ + +/* The difference between 1 and the least value greater than 1 that is + representable in the given floating point type, b**1-p. */ +#undef FLT_EPSILON +#undef DBL_EPSILON +#undef LDBL_EPSILON +#define FLT_EPSILON __FLT_EPSILON__ +#define DBL_EPSILON __DBL_EPSILON__ +#define LDBL_EPSILON __LDBL_EPSILON__ + +/* Minimum normalized positive floating-point number, b**(emin - 1). */ +#undef FLT_MIN +#undef DBL_MIN +#undef LDBL_MIN +#define FLT_MIN __FLT_MIN__ +#define DBL_MIN __DBL_MIN__ +#define LDBL_MIN __LDBL_MIN__ + +/* Addition rounds to 0: zero, 1: nearest, 2: +inf, 3: -inf, -1: unknown. */ +/* ??? This is supposed to change with calls to fesetround in <fenv.h>. */ +#undef FLT_ROUNDS +#define FLT_ROUNDS 1 + +#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L +/* The floating-point expression evaluation method. + -1 indeterminate + 0 evaluate all operations and constants just to the range and + precision of the type + 1 evaluate operations and constants of type float and double + to the range and precision of the double type, evaluate + long double operations and constants to the range and + precision of the long double type + 2 evaluate all operations and constants to the range and + precision of the long double type + + ??? This ought to change with the setting of the fp control word; + the value provided by the compiler assumes the widest setting. */ +#undef FLT_EVAL_METHOD +#define FLT_EVAL_METHOD __FLT_EVAL_METHOD__ + +/* Number of decimal digits, n, such that any floating-point number in the + widest supported floating type with pmax radix b digits can be rounded + to a floating-point number with n decimal digits and back again without + change to the value, + + pmax * log10(b) if b is a power of 10 + ceil(1 + pmax * log10(b)) otherwise +*/ +#undef DECIMAL_DIG +#define DECIMAL_DIG __DECIMAL_DIG__ + +#endif /* C99 */ + +#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 201112L +/* Versions of DECIMAL_DIG for each floating-point type. */ +#undef FLT_DECIMAL_DIG +#undef DBL_DECIMAL_DIG +#undef LDBL_DECIMAL_DIG +#define FLT_DECIMAL_DIG __FLT_DECIMAL_DIG__ +#define DBL_DECIMAL_DIG __DBL_DECIMAL_DIG__ +#define LDBL_DECIMAL_DIG __DECIMAL_DIG__ + +/* Whether types support subnormal numbers. */ +#undef FLT_HAS_SUBNORM +#undef DBL_HAS_SUBNORM +#undef LDBL_HAS_SUBNORM +#define FLT_HAS_SUBNORM __FLT_HAS_DENORM__ +#define DBL_HAS_SUBNORM __DBL_HAS_DENORM__ +#define LDBL_HAS_SUBNORM __LDBL_HAS_DENORM__ + +/* Minimum positive values, including subnormals. */ +#undef FLT_TRUE_MIN +#undef DBL_TRUE_MIN +#undef LDBL_TRUE_MIN +#if __FLT_HAS_DENORM__ +#define FLT_TRUE_MIN __FLT_DENORM_MIN__ +#else +#define FLT_TRUE_MIN __FLT_MIN__ +#endif +#if __DBL_HAS_DENORM__ +#define DBL_TRUE_MIN __DBL_DENORM_MIN__ +#else +#define DBL_TRUE_MIN __DBL_MIN__ +#endif +#if __LDBL_HAS_DENORM__ +#define LDBL_TRUE_MIN __LDBL_DENORM_MIN__ +#else +#define LDBL_TRUE_MIN __LDBL_MIN__ +#endif + +#endif /* C11 */ + +#ifdef __STDC_WANT_DEC_FP__ +/* Draft Technical Report 24732, extension for decimal floating-point + arithmetic: Characteristic of decimal floating types <float.h>. */ + +/* Number of base-FLT_RADIX digits in the significand, p. */ +#undef DEC32_MANT_DIG +#undef DEC64_MANT_DIG +#undef DEC128_MANT_DIG +#define DEC32_MANT_DIG __DEC32_MANT_DIG__ +#define DEC64_MANT_DIG __DEC64_MANT_DIG__ +#define DEC128_MANT_DIG __DEC128_MANT_DIG__ + +/* Minimum exponent. */ +#undef DEC32_MIN_EXP +#undef DEC64_MIN_EXP +#undef DEC128_MIN_EXP +#define DEC32_MIN_EXP __DEC32_MIN_EXP__ +#define DEC64_MIN_EXP __DEC64_MIN_EXP__ +#define DEC128_MIN_EXP __DEC128_MIN_EXP__ + +/* Maximum exponent. */ +#undef DEC32_MAX_EXP +#undef DEC64_MAX_EXP +#undef DEC128_MAX_EXP +#define DEC32_MAX_EXP __DEC32_MAX_EXP__ +#define DEC64_MAX_EXP __DEC64_MAX_EXP__ +#define DEC128_MAX_EXP __DEC128_MAX_EXP__ + +/* Maximum representable finite decimal floating-point number + (there are 6, 15, and 33 9s after the decimal points respectively). */ +#undef DEC32_MAX +#undef DEC64_MAX +#undef DEC128_MAX +#define DEC32_MAX __DEC32_MAX__ +#define DEC64_MAX __DEC64_MAX__ +#define DEC128_MAX __DEC128_MAX__ + +/* The difference between 1 and the least value greater than 1 that is + representable in the given floating point type. */ +#undef DEC32_EPSILON +#undef DEC64_EPSILON +#undef DEC128_EPSILON +#define DEC32_EPSILON __DEC32_EPSILON__ +#define DEC64_EPSILON __DEC64_EPSILON__ +#define DEC128_EPSILON __DEC128_EPSILON__ + +/* Minimum normalized positive floating-point number. */ +#undef DEC32_MIN +#undef DEC64_MIN +#undef DEC128_MIN +#define DEC32_MIN __DEC32_MIN__ +#define DEC64_MIN __DEC64_MIN__ +#define DEC128_MIN __DEC128_MIN__ + +/* Minimum subnormal positive floating-point number. */ +#undef DEC32_SUBNORMAL_MIN +#undef DEC64_SUBNORMAL_MIN +#undef DEC128_SUBNORMAL_MIN +#define DEC32_SUBNORMAL_MIN __DEC32_SUBNORMAL_MIN__ +#define DEC64_SUBNORMAL_MIN __DEC64_SUBNORMAL_MIN__ +#define DEC128_SUBNORMAL_MIN __DEC128_SUBNORMAL_MIN__ + +/* The floating-point expression evaluation method. + -1 indeterminate + 0 evaluate all operations and constants just to the range and + precision of the type + 1 evaluate operations and constants of type _Decimal32 + and _Decimal64 to the range and precision of the _Decimal64 + type, evaluate _Decimal128 operations and constants to the + range and precision of the _Decimal128 type; + 2 evaluate all operations and constants to the range and + precision of the _Decimal128 type. */ + +#undef DEC_EVAL_METHOD +#define DEC_EVAL_METHOD __DEC_EVAL_METHOD__ + +#endif /* __STDC_WANT_DEC_FP__ */ + +#endif /* _FLOAT_H___ */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/iso646.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/iso646.h new file mode 100644 index 0000000..89bc8f4 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/iso646.h @@ -0,0 +1,45 @@ +/* Copyright (C) 1997-2014 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 3, or (at your option) +any later version. + +GCC is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + +/* + * ISO C Standard: 7.9 Alternative spellings <iso646.h> + */ + +#ifndef _ISO646_H +#define _ISO646_H + +#ifndef __cplusplus +#define and && +#define and_eq &= +#define bitand & +#define bitor | +#define compl ~ +#define not ! +#define not_eq != +#define or || +#define or_eq |= +#define xor ^ +#define xor_eq ^= +#endif + +#endif diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/mmintrin.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/mmintrin.h new file mode 100644 index 0000000..b906fac --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/mmintrin.h @@ -0,0 +1,1836 @@ +/* Copyright (C) 2002-2014 Free Software Foundation, Inc. + + This file is part of GCC. + + GCC is free software; you can redistribute it and/or modify it + under the terms of the GNU General Public License as published + by the Free Software Foundation; either version 3, or (at your + option) any later version. + + GCC is distributed in the hope that it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY + or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public + License for more details. + + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see + <http://www.gnu.org/licenses/>. */ + +#ifndef _MMINTRIN_H_INCLUDED +#define _MMINTRIN_H_INCLUDED + +#ifndef __IWMMXT__ +#error mmintrin.h included without enabling WMMX/WMMX2 instructions (e.g. -march=iwmmxt or -march=iwmmxt2) +#endif + + +#if defined __cplusplus +extern "C" { +/* Intrinsics use C name-mangling. */ +#endif /* __cplusplus */ + +/* The data type intended for user use. */ +typedef unsigned long long __m64, __int64; + +/* Internal data types for implementing the intrinsics. */ +typedef int __v2si __attribute__ ((vector_size (8))); +typedef short __v4hi __attribute__ ((vector_size (8))); +typedef signed char __v8qi __attribute__ ((vector_size (8))); + +/* Provided for source compatibility with MMX. */ +extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__)) +_mm_empty (void) +{ +} + +/* "Convert" __m64 and __int64 into each other. */ +static __inline __m64 +_mm_cvtsi64_m64 (__int64 __i) +{ + return __i; +} + +static __inline __int64 +_mm_cvtm64_si64 (__m64 __i) +{ + return __i; +} + +static __inline int +_mm_cvtsi64_si32 (__int64 __i) +{ + return __i; +} + +static __inline __int64 +_mm_cvtsi32_si64 (int __i) +{ + return (__i & 0xffffffff); +} + +/* Pack the four 16-bit values from M1 into the lower four 8-bit values of + the result, and the four 16-bit values from M2 into the upper four 8-bit + values of the result, all with signed saturation. */ +static __inline __m64 +_mm_packs_pi16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wpackhss ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Pack the two 32-bit values from M1 in to the lower two 16-bit values of + the result, and the two 32-bit values from M2 into the upper two 16-bit + values of the result, all with signed saturation. */ +static __inline __m64 +_mm_packs_pi32 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wpackwss ((__v2si)__m1, (__v2si)__m2); +} + +/* Copy the 64-bit value from M1 into the lower 32-bits of the result, and + the 64-bit value from M2 into the upper 32-bits of the result, all with + signed saturation for values that do not fit exactly into 32-bits. */ +static __inline __m64 +_mm_packs_pi64 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wpackdss ((long long)__m1, (long long)__m2); +} + +/* Pack the four 16-bit values from M1 into the lower four 8-bit values of + the result, and the four 16-bit values from M2 into the upper four 8-bit + values of the result, all with unsigned saturation. */ +static __inline __m64 +_mm_packs_pu16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wpackhus ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Pack the two 32-bit values from M1 into the lower two 16-bit values of + the result, and the two 32-bit values from M2 into the upper two 16-bit + values of the result, all with unsigned saturation. */ +static __inline __m64 +_mm_packs_pu32 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wpackwus ((__v2si)__m1, (__v2si)__m2); +} + +/* Copy the 64-bit value from M1 into the lower 32-bits of the result, and + the 64-bit value from M2 into the upper 32-bits of the result, all with + unsigned saturation for values that do not fit exactly into 32-bits. */ +static __inline __m64 +_mm_packs_pu64 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wpackdus ((long long)__m1, (long long)__m2); +} + +/* Interleave the four 8-bit values from the high half of M1 with the four + 8-bit values from the high half of M2. */ +static __inline __m64 +_mm_unpackhi_pi8 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wunpckihb ((__v8qi)__m1, (__v8qi)__m2); +} + +/* Interleave the two 16-bit values from the high half of M1 with the two + 16-bit values from the high half of M2. */ +static __inline __m64 +_mm_unpackhi_pi16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wunpckihh ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Interleave the 32-bit value from the high half of M1 with the 32-bit + value from the high half of M2. */ +static __inline __m64 +_mm_unpackhi_pi32 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wunpckihw ((__v2si)__m1, (__v2si)__m2); +} + +/* Interleave the four 8-bit values from the low half of M1 with the four + 8-bit values from the low half of M2. */ +static __inline __m64 +_mm_unpacklo_pi8 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wunpckilb ((__v8qi)__m1, (__v8qi)__m2); +} + +/* Interleave the two 16-bit values from the low half of M1 with the two + 16-bit values from the low half of M2. */ +static __inline __m64 +_mm_unpacklo_pi16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wunpckilh ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Interleave the 32-bit value from the low half of M1 with the 32-bit + value from the low half of M2. */ +static __inline __m64 +_mm_unpacklo_pi32 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wunpckilw ((__v2si)__m1, (__v2si)__m2); +} + +/* Take the four 8-bit values from the low half of M1, sign extend them, + and return the result as a vector of four 16-bit quantities. */ +static __inline __m64 +_mm_unpackel_pi8 (__m64 __m1) +{ + return (__m64) __builtin_arm_wunpckelsb ((__v8qi)__m1); +} + +/* Take the two 16-bit values from the low half of M1, sign extend them, + and return the result as a vector of two 32-bit quantities. */ +static __inline __m64 +_mm_unpackel_pi16 (__m64 __m1) +{ + return (__m64) __builtin_arm_wunpckelsh ((__v4hi)__m1); +} + +/* Take the 32-bit value from the low half of M1, and return it sign extended + to 64 bits. */ +static __inline __m64 +_mm_unpackel_pi32 (__m64 __m1) +{ + return (__m64) __builtin_arm_wunpckelsw ((__v2si)__m1); +} + +/* Take the four 8-bit values from the high half of M1, sign extend them, + and return the result as a vector of four 16-bit quantities. */ +static __inline __m64 +_mm_unpackeh_pi8 (__m64 __m1) +{ + return (__m64) __builtin_arm_wunpckehsb ((__v8qi)__m1); +} + +/* Take the two 16-bit values from the high half of M1, sign extend them, + and return the result as a vector of two 32-bit quantities. */ +static __inline __m64 +_mm_unpackeh_pi16 (__m64 __m1) +{ + return (__m64) __builtin_arm_wunpckehsh ((__v4hi)__m1); +} + +/* Take the 32-bit value from the high half of M1, and return it sign extended + to 64 bits. */ +static __inline __m64 +_mm_unpackeh_pi32 (__m64 __m1) +{ + return (__m64) __builtin_arm_wunpckehsw ((__v2si)__m1); +} + +/* Take the four 8-bit values from the low half of M1, zero extend them, + and return the result as a vector of four 16-bit quantities. */ +static __inline __m64 +_mm_unpackel_pu8 (__m64 __m1) +{ + return (__m64) __builtin_arm_wunpckelub ((__v8qi)__m1); +} + +/* Take the two 16-bit values from the low half of M1, zero extend them, + and return the result as a vector of two 32-bit quantities. */ +static __inline __m64 +_mm_unpackel_pu16 (__m64 __m1) +{ + return (__m64) __builtin_arm_wunpckeluh ((__v4hi)__m1); +} + +/* Take the 32-bit value from the low half of M1, and return it zero extended + to 64 bits. */ +static __inline __m64 +_mm_unpackel_pu32 (__m64 __m1) +{ + return (__m64) __builtin_arm_wunpckeluw ((__v2si)__m1); +} + +/* Take the four 8-bit values from the high half of M1, zero extend them, + and return the result as a vector of four 16-bit quantities. */ +static __inline __m64 +_mm_unpackeh_pu8 (__m64 __m1) +{ + return (__m64) __builtin_arm_wunpckehub ((__v8qi)__m1); +} + +/* Take the two 16-bit values from the high half of M1, zero extend them, + and return the result as a vector of two 32-bit quantities. */ +static __inline __m64 +_mm_unpackeh_pu16 (__m64 __m1) +{ + return (__m64) __builtin_arm_wunpckehuh ((__v4hi)__m1); +} + +/* Take the 32-bit value from the high half of M1, and return it zero extended + to 64 bits. */ +static __inline __m64 +_mm_unpackeh_pu32 (__m64 __m1) +{ + return (__m64) __builtin_arm_wunpckehuw ((__v2si)__m1); +} + +/* Add the 8-bit values in M1 to the 8-bit values in M2. */ +static __inline __m64 +_mm_add_pi8 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_waddb ((__v8qi)__m1, (__v8qi)__m2); +} + +/* Add the 16-bit values in M1 to the 16-bit values in M2. */ +static __inline __m64 +_mm_add_pi16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_waddh ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Add the 32-bit values in M1 to the 32-bit values in M2. */ +static __inline __m64 +_mm_add_pi32 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_waddw ((__v2si)__m1, (__v2si)__m2); +} + +/* Add the 8-bit values in M1 to the 8-bit values in M2 using signed + saturated arithmetic. */ +static __inline __m64 +_mm_adds_pi8 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_waddbss ((__v8qi)__m1, (__v8qi)__m2); +} + +/* Add the 16-bit values in M1 to the 16-bit values in M2 using signed + saturated arithmetic. */ +static __inline __m64 +_mm_adds_pi16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_waddhss ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Add the 32-bit values in M1 to the 32-bit values in M2 using signed + saturated arithmetic. */ +static __inline __m64 +_mm_adds_pi32 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_waddwss ((__v2si)__m1, (__v2si)__m2); +} + +/* Add the 8-bit values in M1 to the 8-bit values in M2 using unsigned + saturated arithmetic. */ +static __inline __m64 +_mm_adds_pu8 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_waddbus ((__v8qi)__m1, (__v8qi)__m2); +} + +/* Add the 16-bit values in M1 to the 16-bit values in M2 using unsigned + saturated arithmetic. */ +static __inline __m64 +_mm_adds_pu16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_waddhus ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Add the 32-bit values in M1 to the 32-bit values in M2 using unsigned + saturated arithmetic. */ +static __inline __m64 +_mm_adds_pu32 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_waddwus ((__v2si)__m1, (__v2si)__m2); +} + +/* Subtract the 8-bit values in M2 from the 8-bit values in M1. */ +static __inline __m64 +_mm_sub_pi8 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wsubb ((__v8qi)__m1, (__v8qi)__m2); +} + +/* Subtract the 16-bit values in M2 from the 16-bit values in M1. */ +static __inline __m64 +_mm_sub_pi16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wsubh ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Subtract the 32-bit values in M2 from the 32-bit values in M1. */ +static __inline __m64 +_mm_sub_pi32 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wsubw ((__v2si)__m1, (__v2si)__m2); +} + +/* Subtract the 8-bit values in M2 from the 8-bit values in M1 using signed + saturating arithmetic. */ +static __inline __m64 +_mm_subs_pi8 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wsubbss ((__v8qi)__m1, (__v8qi)__m2); +} + +/* Subtract the 16-bit values in M2 from the 16-bit values in M1 using + signed saturating arithmetic. */ +static __inline __m64 +_mm_subs_pi16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wsubhss ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Subtract the 32-bit values in M2 from the 32-bit values in M1 using + signed saturating arithmetic. */ +static __inline __m64 +_mm_subs_pi32 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wsubwss ((__v2si)__m1, (__v2si)__m2); +} + +/* Subtract the 8-bit values in M2 from the 8-bit values in M1 using + unsigned saturating arithmetic. */ +static __inline __m64 +_mm_subs_pu8 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wsubbus ((__v8qi)__m1, (__v8qi)__m2); +} + +/* Subtract the 16-bit values in M2 from the 16-bit values in M1 using + unsigned saturating arithmetic. */ +static __inline __m64 +_mm_subs_pu16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wsubhus ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Subtract the 32-bit values in M2 from the 32-bit values in M1 using + unsigned saturating arithmetic. */ +static __inline __m64 +_mm_subs_pu32 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wsubwus ((__v2si)__m1, (__v2si)__m2); +} + +/* Multiply four 16-bit values in M1 by four 16-bit values in M2 producing + four 32-bit intermediate results, which are then summed by pairs to + produce two 32-bit results. */ +static __inline __m64 +_mm_madd_pi16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wmadds ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Multiply four 16-bit values in M1 by four 16-bit values in M2 producing + four 32-bit intermediate results, which are then summed by pairs to + produce two 32-bit results. */ +static __inline __m64 +_mm_madd_pu16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wmaddu ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Multiply four signed 16-bit values in M1 by four signed 16-bit values in + M2 and produce the high 16 bits of the 32-bit results. */ +static __inline __m64 +_mm_mulhi_pi16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wmulsm ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Multiply four signed 16-bit values in M1 by four signed 16-bit values in + M2 and produce the high 16 bits of the 32-bit results. */ +static __inline __m64 +_mm_mulhi_pu16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wmulum ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Multiply four 16-bit values in M1 by four 16-bit values in M2 and produce + the low 16 bits of the results. */ +static __inline __m64 +_mm_mullo_pi16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wmulul ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Shift four 16-bit values in M left by COUNT. */ +static __inline __m64 +_mm_sll_pi16 (__m64 __m, __m64 __count) +{ + return (__m64) __builtin_arm_wsllh ((__v4hi)__m, __count); +} + +static __inline __m64 +_mm_slli_pi16 (__m64 __m, int __count) +{ + return (__m64) __builtin_arm_wsllhi ((__v4hi)__m, __count); +} + +/* Shift two 32-bit values in M left by COUNT. */ +static __inline __m64 +_mm_sll_pi32 (__m64 __m, __m64 __count) +{ + return (__m64) __builtin_arm_wsllw ((__v2si)__m, __count); +} + +static __inline __m64 +_mm_slli_pi32 (__m64 __m, int __count) +{ + return (__m64) __builtin_arm_wsllwi ((__v2si)__m, __count); +} + +/* Shift the 64-bit value in M left by COUNT. */ +static __inline __m64 +_mm_sll_si64 (__m64 __m, __m64 __count) +{ + return (__m64) __builtin_arm_wslld (__m, __count); +} + +static __inline __m64 +_mm_slli_si64 (__m64 __m, int __count) +{ + return (__m64) __builtin_arm_wslldi (__m, __count); +} + +/* Shift four 16-bit values in M right by COUNT; shift in the sign bit. */ +static __inline __m64 +_mm_sra_pi16 (__m64 __m, __m64 __count) +{ + return (__m64) __builtin_arm_wsrah ((__v4hi)__m, __count); +} + +static __inline __m64 +_mm_srai_pi16 (__m64 __m, int __count) +{ + return (__m64) __builtin_arm_wsrahi ((__v4hi)__m, __count); +} + +/* Shift two 32-bit values in M right by COUNT; shift in the sign bit. */ +static __inline __m64 +_mm_sra_pi32 (__m64 __m, __m64 __count) +{ + return (__m64) __builtin_arm_wsraw ((__v2si)__m, __count); +} + +static __inline __m64 +_mm_srai_pi32 (__m64 __m, int __count) +{ + return (__m64) __builtin_arm_wsrawi ((__v2si)__m, __count); +} + +/* Shift the 64-bit value in M right by COUNT; shift in the sign bit. */ +static __inline __m64 +_mm_sra_si64 (__m64 __m, __m64 __count) +{ + return (__m64) __builtin_arm_wsrad (__m, __count); +} + +static __inline __m64 +_mm_srai_si64 (__m64 __m, int __count) +{ + return (__m64) __builtin_arm_wsradi (__m, __count); +} + +/* Shift four 16-bit values in M right by COUNT; shift in zeros. */ +static __inline __m64 +_mm_srl_pi16 (__m64 __m, __m64 __count) +{ + return (__m64) __builtin_arm_wsrlh ((__v4hi)__m, __count); +} + +static __inline __m64 +_mm_srli_pi16 (__m64 __m, int __count) +{ + return (__m64) __builtin_arm_wsrlhi ((__v4hi)__m, __count); +} + +/* Shift two 32-bit values in M right by COUNT; shift in zeros. */ +static __inline __m64 +_mm_srl_pi32 (__m64 __m, __m64 __count) +{ + return (__m64) __builtin_arm_wsrlw ((__v2si)__m, __count); +} + +static __inline __m64 +_mm_srli_pi32 (__m64 __m, int __count) +{ + return (__m64) __builtin_arm_wsrlwi ((__v2si)__m, __count); +} + +/* Shift the 64-bit value in M left by COUNT; shift in zeros. */ +static __inline __m64 +_mm_srl_si64 (__m64 __m, __m64 __count) +{ + return (__m64) __builtin_arm_wsrld (__m, __count); +} + +static __inline __m64 +_mm_srli_si64 (__m64 __m, int __count) +{ + return (__m64) __builtin_arm_wsrldi (__m, __count); +} + +/* Rotate four 16-bit values in M right by COUNT. */ +static __inline __m64 +_mm_ror_pi16 (__m64 __m, __m64 __count) +{ + return (__m64) __builtin_arm_wrorh ((__v4hi)__m, __count); +} + +static __inline __m64 +_mm_rori_pi16 (__m64 __m, int __count) +{ + return (__m64) __builtin_arm_wrorhi ((__v4hi)__m, __count); +} + +/* Rotate two 32-bit values in M right by COUNT. */ +static __inline __m64 +_mm_ror_pi32 (__m64 __m, __m64 __count) +{ + return (__m64) __builtin_arm_wrorw ((__v2si)__m, __count); +} + +static __inline __m64 +_mm_rori_pi32 (__m64 __m, int __count) +{ + return (__m64) __builtin_arm_wrorwi ((__v2si)__m, __count); +} + +/* Rotate two 64-bit values in M right by COUNT. */ +static __inline __m64 +_mm_ror_si64 (__m64 __m, __m64 __count) +{ + return (__m64) __builtin_arm_wrord (__m, __count); +} + +static __inline __m64 +_mm_rori_si64 (__m64 __m, int __count) +{ + return (__m64) __builtin_arm_wrordi (__m, __count); +} + +/* Bit-wise AND the 64-bit values in M1 and M2. */ +static __inline __m64 +_mm_and_si64 (__m64 __m1, __m64 __m2) +{ + return __builtin_arm_wand (__m1, __m2); +} + +/* Bit-wise complement the 64-bit value in M1 and bit-wise AND it with the + 64-bit value in M2. */ +static __inline __m64 +_mm_andnot_si64 (__m64 __m1, __m64 __m2) +{ + return __builtin_arm_wandn (__m2, __m1); +} + +/* Bit-wise inclusive OR the 64-bit values in M1 and M2. */ +static __inline __m64 +_mm_or_si64 (__m64 __m1, __m64 __m2) +{ + return __builtin_arm_wor (__m1, __m2); +} + +/* Bit-wise exclusive OR the 64-bit values in M1 and M2. */ +static __inline __m64 +_mm_xor_si64 (__m64 __m1, __m64 __m2) +{ + return __builtin_arm_wxor (__m1, __m2); +} + +/* Compare eight 8-bit values. The result of the comparison is 0xFF if the + test is true and zero if false. */ +static __inline __m64 +_mm_cmpeq_pi8 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wcmpeqb ((__v8qi)__m1, (__v8qi)__m2); +} + +static __inline __m64 +_mm_cmpgt_pi8 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wcmpgtsb ((__v8qi)__m1, (__v8qi)__m2); +} + +static __inline __m64 +_mm_cmpgt_pu8 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wcmpgtub ((__v8qi)__m1, (__v8qi)__m2); +} + +/* Compare four 16-bit values. The result of the comparison is 0xFFFF if + the test is true and zero if false. */ +static __inline __m64 +_mm_cmpeq_pi16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wcmpeqh ((__v4hi)__m1, (__v4hi)__m2); +} + +static __inline __m64 +_mm_cmpgt_pi16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wcmpgtsh ((__v4hi)__m1, (__v4hi)__m2); +} + +static __inline __m64 +_mm_cmpgt_pu16 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wcmpgtuh ((__v4hi)__m1, (__v4hi)__m2); +} + +/* Compare two 32-bit values. The result of the comparison is 0xFFFFFFFF if + the test is true and zero if false. */ +static __inline __m64 +_mm_cmpeq_pi32 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wcmpeqw ((__v2si)__m1, (__v2si)__m2); +} + +static __inline __m64 +_mm_cmpgt_pi32 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wcmpgtsw ((__v2si)__m1, (__v2si)__m2); +} + +static __inline __m64 +_mm_cmpgt_pu32 (__m64 __m1, __m64 __m2) +{ + return (__m64) __builtin_arm_wcmpgtuw ((__v2si)__m1, (__v2si)__m2); +} + +/* Element-wise multiplication of unsigned 16-bit values __B and __C, followed + by accumulate across all elements and __A. */ +static __inline __m64 +_mm_mac_pu16 (__m64 __A, __m64 __B, __m64 __C) +{ + return __builtin_arm_wmacu (__A, (__v4hi)__B, (__v4hi)__C); +} + +/* Element-wise multiplication of signed 16-bit values __B and __C, followed + by accumulate across all elements and __A. */ +static __inline __m64 +_mm_mac_pi16 (__m64 __A, __m64 __B, __m64 __C) +{ + return __builtin_arm_wmacs (__A, (__v4hi)__B, (__v4hi)__C); +} + +/* Element-wise multiplication of unsigned 16-bit values __B and __C, followed + by accumulate across all elements. */ +static __inline __m64 +_mm_macz_pu16 (__m64 __A, __m64 __B) +{ + return __builtin_arm_wmacuz ((__v4hi)__A, (__v4hi)__B); +} + +/* Element-wise multiplication of signed 16-bit values __B and __C, followed + by accumulate across all elements. */ +static __inline __m64 +_mm_macz_pi16 (__m64 __A, __m64 __B) +{ + return __builtin_arm_wmacsz ((__v4hi)__A, (__v4hi)__B); +} + +/* Accumulate across all unsigned 8-bit values in __A. */ +static __inline __m64 +_mm_acc_pu8 (__m64 __A) +{ + return __builtin_arm_waccb ((__v8qi)__A); +} + +/* Accumulate across all unsigned 16-bit values in __A. */ +static __inline __m64 +_mm_acc_pu16 (__m64 __A) +{ + return __builtin_arm_wacch ((__v4hi)__A); +} + +/* Accumulate across all unsigned 32-bit values in __A. */ +static __inline __m64 +_mm_acc_pu32 (__m64 __A) +{ + return __builtin_arm_waccw ((__v2si)__A); +} + +static __inline __m64 +_mm_mia_si64 (__m64 __A, int __B, int __C) +{ + return __builtin_arm_tmia (__A, __B, __C); +} + +static __inline __m64 +_mm_miaph_si64 (__m64 __A, int __B, int __C) +{ + return __builtin_arm_tmiaph (__A, __B, __C); +} + +static __inline __m64 +_mm_miabb_si64 (__m64 __A, int __B, int __C) +{ + return __builtin_arm_tmiabb (__A, __B, __C); +} + +static __inline __m64 +_mm_miabt_si64 (__m64 __A, int __B, int __C) +{ + return __builtin_arm_tmiabt (__A, __B, __C); +} + +static __inline __m64 +_mm_miatb_si64 (__m64 __A, int __B, int __C) +{ + return __builtin_arm_tmiatb (__A, __B, __C); +} + +static __inline __m64 +_mm_miatt_si64 (__m64 __A, int __B, int __C) +{ + return __builtin_arm_tmiatt (__A, __B, __C); +} + +/* Extract one of the elements of A and sign extend. The selector N must + be immediate. */ +#define _mm_extract_pi8(A, N) __builtin_arm_textrmsb ((__v8qi)(A), (N)) +#define _mm_extract_pi16(A, N) __builtin_arm_textrmsh ((__v4hi)(A), (N)) +#define _mm_extract_pi32(A, N) __builtin_arm_textrmsw ((__v2si)(A), (N)) + +/* Extract one of the elements of A and zero extend. The selector N must + be immediate. */ +#define _mm_extract_pu8(A, N) __builtin_arm_textrmub ((__v8qi)(A), (N)) +#define _mm_extract_pu16(A, N) __builtin_arm_textrmuh ((__v4hi)(A), (N)) +#define _mm_extract_pu32(A, N) __builtin_arm_textrmuw ((__v2si)(A), (N)) + +/* Inserts word D into one of the elements of A. The selector N must be + immediate. */ +#define _mm_insert_pi8(A, D, N) \ + ((__m64) __builtin_arm_tinsrb ((__v8qi)(A), (D), (N))) +#define _mm_insert_pi16(A, D, N) \ + ((__m64) __builtin_arm_tinsrh ((__v4hi)(A), (D), (N))) +#define _mm_insert_pi32(A, D, N) \ + ((__m64) __builtin_arm_tinsrw ((__v2si)(A), (D), (N))) + +/* Compute the element-wise maximum of signed 8-bit values. */ +static __inline __m64 +_mm_max_pi8 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wmaxsb ((__v8qi)__A, (__v8qi)__B); +} + +/* Compute the element-wise maximum of signed 16-bit values. */ +static __inline __m64 +_mm_max_pi16 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wmaxsh ((__v4hi)__A, (__v4hi)__B); +} + +/* Compute the element-wise maximum of signed 32-bit values. */ +static __inline __m64 +_mm_max_pi32 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wmaxsw ((__v2si)__A, (__v2si)__B); +} + +/* Compute the element-wise maximum of unsigned 8-bit values. */ +static __inline __m64 +_mm_max_pu8 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wmaxub ((__v8qi)__A, (__v8qi)__B); +} + +/* Compute the element-wise maximum of unsigned 16-bit values. */ +static __inline __m64 +_mm_max_pu16 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wmaxuh ((__v4hi)__A, (__v4hi)__B); +} + +/* Compute the element-wise maximum of unsigned 32-bit values. */ +static __inline __m64 +_mm_max_pu32 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wmaxuw ((__v2si)__A, (__v2si)__B); +} + +/* Compute the element-wise minimum of signed 16-bit values. */ +static __inline __m64 +_mm_min_pi8 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wminsb ((__v8qi)__A, (__v8qi)__B); +} + +/* Compute the element-wise minimum of signed 16-bit values. */ +static __inline __m64 +_mm_min_pi16 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wminsh ((__v4hi)__A, (__v4hi)__B); +} + +/* Compute the element-wise minimum of signed 32-bit values. */ +static __inline __m64 +_mm_min_pi32 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wminsw ((__v2si)__A, (__v2si)__B); +} + +/* Compute the element-wise minimum of unsigned 16-bit values. */ +static __inline __m64 +_mm_min_pu8 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wminub ((__v8qi)__A, (__v8qi)__B); +} + +/* Compute the element-wise minimum of unsigned 16-bit values. */ +static __inline __m64 +_mm_min_pu16 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wminuh ((__v4hi)__A, (__v4hi)__B); +} + +/* Compute the element-wise minimum of unsigned 32-bit values. */ +static __inline __m64 +_mm_min_pu32 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wminuw ((__v2si)__A, (__v2si)__B); +} + +/* Create an 8-bit mask of the signs of 8-bit values. */ +static __inline int +_mm_movemask_pi8 (__m64 __A) +{ + return __builtin_arm_tmovmskb ((__v8qi)__A); +} + +/* Create an 8-bit mask of the signs of 16-bit values. */ +static __inline int +_mm_movemask_pi16 (__m64 __A) +{ + return __builtin_arm_tmovmskh ((__v4hi)__A); +} + +/* Create an 8-bit mask of the signs of 32-bit values. */ +static __inline int +_mm_movemask_pi32 (__m64 __A) +{ + return __builtin_arm_tmovmskw ((__v2si)__A); +} + +/* Return a combination of the four 16-bit values in A. The selector + must be an immediate. */ +#define _mm_shuffle_pi16(A, N) \ + ((__m64) __builtin_arm_wshufh ((__v4hi)(A), (N))) + + +/* Compute the rounded averages of the unsigned 8-bit values in A and B. */ +static __inline __m64 +_mm_avg_pu8 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wavg2br ((__v8qi)__A, (__v8qi)__B); +} + +/* Compute the rounded averages of the unsigned 16-bit values in A and B. */ +static __inline __m64 +_mm_avg_pu16 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wavg2hr ((__v4hi)__A, (__v4hi)__B); +} + +/* Compute the averages of the unsigned 8-bit values in A and B. */ +static __inline __m64 +_mm_avg2_pu8 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wavg2b ((__v8qi)__A, (__v8qi)__B); +} + +/* Compute the averages of the unsigned 16-bit values in A and B. */ +static __inline __m64 +_mm_avg2_pu16 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wavg2h ((__v4hi)__A, (__v4hi)__B); +} + +/* Compute the sum of the absolute differences of the unsigned 8-bit + values in A and B. Return the value in the lower 16-bit word; the + upper words are cleared. */ +static __inline __m64 +_mm_sad_pu8 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wsadbz ((__v8qi)__A, (__v8qi)__B); +} + +static __inline __m64 +_mm_sada_pu8 (__m64 __A, __m64 __B, __m64 __C) +{ + return (__m64) __builtin_arm_wsadb ((__v2si)__A, (__v8qi)__B, (__v8qi)__C); +} + +/* Compute the sum of the absolute differences of the unsigned 16-bit + values in A and B. Return the value in the lower 32-bit word; the + upper words are cleared. */ +static __inline __m64 +_mm_sad_pu16 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wsadhz ((__v4hi)__A, (__v4hi)__B); +} + +static __inline __m64 +_mm_sada_pu16 (__m64 __A, __m64 __B, __m64 __C) +{ + return (__m64) __builtin_arm_wsadh ((__v2si)__A, (__v4hi)__B, (__v4hi)__C); +} + + +/* Compute the sum of the absolute differences of the unsigned 8-bit + values in A and B. Return the value in the lower 16-bit word; the + upper words are cleared. */ +static __inline __m64 +_mm_sadz_pu8 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wsadbz ((__v8qi)__A, (__v8qi)__B); +} + +/* Compute the sum of the absolute differences of the unsigned 16-bit + values in A and B. Return the value in the lower 32-bit word; the + upper words are cleared. */ +static __inline __m64 +_mm_sadz_pu16 (__m64 __A, __m64 __B) +{ + return (__m64) __builtin_arm_wsadhz ((__v4hi)__A, (__v4hi)__B); +} + +#define _mm_align_si64(__A,__B, N) \ + (__m64) __builtin_arm_walign ((__v8qi) (__A),(__v8qi) (__B), (N)) + +/* Creates a 64-bit zero. */ +static __inline __m64 +_mm_setzero_si64 (void) +{ + return __builtin_arm_wzero (); +} + +/* Set and Get arbitrary iWMMXt Control registers. + Note only registers 0-3 and 8-11 are currently defined, + the rest are reserved. */ + +static __inline void +_mm_setwcx (const int __value, const int __regno) +{ + switch (__regno) + { + case 0: + __asm __volatile ("tmcr wcid, %0" :: "r"(__value)); + break; + case 1: + __asm __volatile ("tmcr wcon, %0" :: "r"(__value)); + break; + case 2: + __asm __volatile ("tmcr wcssf, %0" :: "r"(__value)); + break; + case 3: + __asm __volatile ("tmcr wcasf, %0" :: "r"(__value)); + break; + case 8: + __builtin_arm_setwcgr0 (__value); + break; + case 9: + __builtin_arm_setwcgr1 (__value); + break; + case 10: + __builtin_arm_setwcgr2 (__value); + break; + case 11: + __builtin_arm_setwcgr3 (__value); + break; + default: + break; + } +} + +static __inline int +_mm_getwcx (const int __regno) +{ + int __value; + switch (__regno) + { + case 0: + __asm __volatile ("tmrc %0, wcid" : "=r"(__value)); + break; + case 1: + __asm __volatile ("tmrc %0, wcon" : "=r"(__value)); + break; + case 2: + __asm __volatile ("tmrc %0, wcssf" : "=r"(__value)); + break; + case 3: + __asm __volatile ("tmrc %0, wcasf" : "=r"(__value)); + break; + case 8: + return __builtin_arm_getwcgr0 (); + case 9: + return __builtin_arm_getwcgr1 (); + case 10: + return __builtin_arm_getwcgr2 (); + case 11: + return __builtin_arm_getwcgr3 (); + default: + break; + } + return __value; +} + +/* Creates a vector of two 32-bit values; I0 is least significant. */ +static __inline __m64 +_mm_set_pi32 (int __i1, int __i0) +{ + union + { + __m64 __q; + struct + { + unsigned int __i0; + unsigned int __i1; + } __s; + } __u; + + __u.__s.__i0 = __i0; + __u.__s.__i1 = __i1; + + return __u.__q; +} + +/* Creates a vector of four 16-bit values; W0 is least significant. */ +static __inline __m64 +_mm_set_pi16 (short __w3, short __w2, short __w1, short __w0) +{ + unsigned int __i1 = (unsigned short) __w3 << 16 | (unsigned short) __w2; + unsigned int __i0 = (unsigned short) __w1 << 16 | (unsigned short) __w0; + + return _mm_set_pi32 (__i1, __i0); +} + +/* Creates a vector of eight 8-bit values; B0 is least significant. */ +static __inline __m64 +_mm_set_pi8 (char __b7, char __b6, char __b5, char __b4, + char __b3, char __b2, char __b1, char __b0) +{ + unsigned int __i1, __i0; + + __i1 = (unsigned char)__b7; + __i1 = __i1 << 8 | (unsigned char)__b6; + __i1 = __i1 << 8 | (unsigned char)__b5; + __i1 = __i1 << 8 | (unsigned char)__b4; + + __i0 = (unsigned char)__b3; + __i0 = __i0 << 8 | (unsigned char)__b2; + __i0 = __i0 << 8 | (unsigned char)__b1; + __i0 = __i0 << 8 | (unsigned char)__b0; + + return _mm_set_pi32 (__i1, __i0); +} + +/* Similar, but with the arguments in reverse order. */ +static __inline __m64 +_mm_setr_pi32 (int __i0, int __i1) +{ + return _mm_set_pi32 (__i1, __i0); +} + +static __inline __m64 +_mm_setr_pi16 (short __w0, short __w1, short __w2, short __w3) +{ + return _mm_set_pi16 (__w3, __w2, __w1, __w0); +} + +static __inline __m64 +_mm_setr_pi8 (char __b0, char __b1, char __b2, char __b3, + char __b4, char __b5, char __b6, char __b7) +{ + return _mm_set_pi8 (__b7, __b6, __b5, __b4, __b3, __b2, __b1, __b0); +} + +/* Creates a vector of two 32-bit values, both elements containing I. */ +static __inline __m64 +_mm_set1_pi32 (int __i) +{ + return _mm_set_pi32 (__i, __i); +} + +/* Creates a vector of four 16-bit values, all elements containing W. */ +static __inline __m64 +_mm_set1_pi16 (short __w) +{ + unsigned int __i = (unsigned short)__w << 16 | (unsigned short)__w; + return _mm_set1_pi32 (__i); +} + +/* Creates a vector of four 16-bit values, all elements containing B. */ +static __inline __m64 +_mm_set1_pi8 (char __b) +{ + unsigned int __w = (unsigned char)__b << 8 | (unsigned char)__b; + unsigned int __i = __w << 16 | __w; + return _mm_set1_pi32 (__i); +} + +#ifdef __IWMMXT2__ +static __inline __m64 +_mm_abs_pi8 (__m64 m1) +{ + return (__m64) __builtin_arm_wabsb ((__v8qi)m1); +} + +static __inline __m64 +_mm_abs_pi16 (__m64 m1) +{ + return (__m64) __builtin_arm_wabsh ((__v4hi)m1); + +} + +static __inline __m64 +_mm_abs_pi32 (__m64 m1) +{ + return (__m64) __builtin_arm_wabsw ((__v2si)m1); + +} + +static __inline __m64 +_mm_addsubhx_pi16 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_waddsubhx ((__v4hi)a, (__v4hi)b); +} + +static __inline __m64 +_mm_absdiff_pu8 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wabsdiffb ((__v8qi)a, (__v8qi)b); +} + +static __inline __m64 +_mm_absdiff_pu16 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wabsdiffh ((__v4hi)a, (__v4hi)b); +} + +static __inline __m64 +_mm_absdiff_pu32 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wabsdiffw ((__v2si)a, (__v2si)b); +} + +static __inline __m64 +_mm_addc_pu16 (__m64 a, __m64 b) +{ + __m64 result; + __asm__ __volatile__ ("waddhc %0, %1, %2" : "=y" (result) : "y" (a), "y" (b)); + return result; +} + +static __inline __m64 +_mm_addc_pu32 (__m64 a, __m64 b) +{ + __m64 result; + __asm__ __volatile__ ("waddwc %0, %1, %2" : "=y" (result) : "y" (a), "y" (b)); + return result; +} + +static __inline __m64 +_mm_avg4_pu8 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wavg4 ((__v8qi)a, (__v8qi)b); +} + +static __inline __m64 +_mm_avg4r_pu8 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wavg4r ((__v8qi)a, (__v8qi)b); +} + +static __inline __m64 +_mm_maddx_pi16 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wmaddsx ((__v4hi)a, (__v4hi)b); +} + +static __inline __m64 +_mm_maddx_pu16 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wmaddux ((__v4hi)a, (__v4hi)b); +} + +static __inline __m64 +_mm_msub_pi16 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wmaddsn ((__v4hi)a, (__v4hi)b); +} + +static __inline __m64 +_mm_msub_pu16 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wmaddun ((__v4hi)a, (__v4hi)b); +} + +static __inline __m64 +_mm_mulhi_pi32 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wmulwsm ((__v2si)a, (__v2si)b); +} + +static __inline __m64 +_mm_mulhi_pu32 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wmulwum ((__v2si)a, (__v2si)b); +} + +static __inline __m64 +_mm_mulhir_pi16 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wmulsmr ((__v4hi)a, (__v4hi)b); +} + +static __inline __m64 +_mm_mulhir_pi32 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wmulwsmr ((__v2si)a, (__v2si)b); +} + +static __inline __m64 +_mm_mulhir_pu16 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wmulumr ((__v4hi)a, (__v4hi)b); +} + +static __inline __m64 +_mm_mulhir_pu32 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wmulwumr ((__v2si)a, (__v2si)b); +} + +static __inline __m64 +_mm_mullo_pi32 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wmulwl ((__v2si)a, (__v2si)b); +} + +static __inline __m64 +_mm_qmulm_pi16 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wqmulm ((__v4hi)a, (__v4hi)b); +} + +static __inline __m64 +_mm_qmulm_pi32 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wqmulwm ((__v2si)a, (__v2si)b); +} + +static __inline __m64 +_mm_qmulmr_pi16 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wqmulmr ((__v4hi)a, (__v4hi)b); +} + +static __inline __m64 +_mm_qmulmr_pi32 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wqmulwmr ((__v2si)a, (__v2si)b); +} + +static __inline __m64 +_mm_subaddhx_pi16 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_wsubaddhx ((__v4hi)a, (__v4hi)b); +} + +static __inline __m64 +_mm_addbhusl_pu8 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_waddbhusl ((__v4hi)a, (__v8qi)b); +} + +static __inline __m64 +_mm_addbhusm_pu8 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_waddbhusm ((__v4hi)a, (__v8qi)b); +} + +#define _mm_qmiabb_pi32(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wqmiabb ((__v2si)_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_qmiabbn_pi32(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wqmiabbn ((__v2si)_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_qmiabt_pi32(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wqmiabt ((__v2si)_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_qmiabtn_pi32(acc, m1, m2) \ + ({\ + __m64 _acc=acc;\ + __m64 _m1=m1;\ + __m64 _m2=m2;\ + _acc = (__m64) __builtin_arm_wqmiabtn ((__v2si)_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_qmiatb_pi32(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wqmiatb ((__v2si)_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_qmiatbn_pi32(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wqmiatbn ((__v2si)_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_qmiatt_pi32(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wqmiatt ((__v2si)_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_qmiattn_pi32(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wqmiattn ((__v2si)_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_wmiabb_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiabb (_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_wmiabbn_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiabbn (_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_wmiabt_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiabt (_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_wmiabtn_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiabtn (_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_wmiatb_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiatb (_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_wmiatbn_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiatbn (_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_wmiatt_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiatt (_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_wmiattn_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiattn (_acc, (__v4hi)_m1, (__v4hi)_m2);\ + _acc;\ + }) + +#define _mm_wmiawbb_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiawbb (_acc, (__v2si)_m1, (__v2si)_m2);\ + _acc;\ + }) + +#define _mm_wmiawbbn_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiawbbn (_acc, (__v2si)_m1, (__v2si)_m2);\ + _acc;\ + }) + +#define _mm_wmiawbt_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiawbt (_acc, (__v2si)_m1, (__v2si)_m2);\ + _acc;\ + }) + +#define _mm_wmiawbtn_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiawbtn (_acc, (__v2si)_m1, (__v2si)_m2);\ + _acc;\ + }) + +#define _mm_wmiawtb_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiawtb (_acc, (__v2si)_m1, (__v2si)_m2);\ + _acc;\ + }) + +#define _mm_wmiawtbn_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiawtbn (_acc, (__v2si)_m1, (__v2si)_m2);\ + _acc;\ + }) + +#define _mm_wmiawtt_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiawtt (_acc, (__v2si)_m1, (__v2si)_m2);\ + _acc;\ + }) + +#define _mm_wmiawttn_si64(acc, m1, m2) \ + ({\ + __m64 _acc = acc;\ + __m64 _m1 = m1;\ + __m64 _m2 = m2;\ + _acc = (__m64) __builtin_arm_wmiawttn (_acc, (__v2si)_m1, (__v2si)_m2);\ + _acc;\ + }) + +/* The third arguments should be an immediate. */ +#define _mm_merge_si64(a, b, n) \ + ({\ + __m64 result;\ + result = (__m64) __builtin_arm_wmerge ((__m64) (a), (__m64) (b), (n));\ + result;\ + }) +#endif /* __IWMMXT2__ */ + +static __inline __m64 +_mm_alignr0_si64 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_walignr0 ((__v8qi) a, (__v8qi) b); +} + +static __inline __m64 +_mm_alignr1_si64 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_walignr1 ((__v8qi) a, (__v8qi) b); +} + +static __inline __m64 +_mm_alignr2_si64 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_walignr2 ((__v8qi) a, (__v8qi) b); +} + +static __inline __m64 +_mm_alignr3_si64 (__m64 a, __m64 b) +{ + return (__m64) __builtin_arm_walignr3 ((__v8qi) a, (__v8qi) b); +} + +static __inline void +_mm_tandcb () +{ + __asm __volatile ("tandcb r15"); +} + +static __inline void +_mm_tandch () +{ + __asm __volatile ("tandch r15"); +} + +static __inline void +_mm_tandcw () +{ + __asm __volatile ("tandcw r15"); +} + +#define _mm_textrcb(n) \ + ({\ + __asm__ __volatile__ (\ + "textrcb r15, %0" : : "i" (n));\ + }) + +#define _mm_textrch(n) \ + ({\ + __asm__ __volatile__ (\ + "textrch r15, %0" : : "i" (n));\ + }) + +#define _mm_textrcw(n) \ + ({\ + __asm__ __volatile__ (\ + "textrcw r15, %0" : : "i" (n));\ + }) + +static __inline void +_mm_torcb () +{ + __asm __volatile ("torcb r15"); +} + +static __inline void +_mm_torch () +{ + __asm __volatile ("torch r15"); +} + +static __inline void +_mm_torcw () +{ + __asm __volatile ("torcw r15"); +} + +#ifdef __IWMMXT2__ +static __inline void +_mm_torvscb () +{ + __asm __volatile ("torvscb r15"); +} + +static __inline void +_mm_torvsch () +{ + __asm __volatile ("torvsch r15"); +} + +static __inline void +_mm_torvscw () +{ + __asm __volatile ("torvscw r15"); +} +#endif /* __IWMMXT2__ */ + +static __inline __m64 +_mm_tbcst_pi8 (int value) +{ + return (__m64) __builtin_arm_tbcstb ((signed char) value); +} + +static __inline __m64 +_mm_tbcst_pi16 (int value) +{ + return (__m64) __builtin_arm_tbcsth ((short) value); +} + +static __inline __m64 +_mm_tbcst_pi32 (int value) +{ + return (__m64) __builtin_arm_tbcstw (value); +} + +#define _m_empty _mm_empty +#define _m_packsswb _mm_packs_pi16 +#define _m_packssdw _mm_packs_pi32 +#define _m_packuswb _mm_packs_pu16 +#define _m_packusdw _mm_packs_pu32 +#define _m_packssqd _mm_packs_pi64 +#define _m_packusqd _mm_packs_pu64 +#define _mm_packs_si64 _mm_packs_pi64 +#define _mm_packs_su64 _mm_packs_pu64 +#define _m_punpckhbw _mm_unpackhi_pi8 +#define _m_punpckhwd _mm_unpackhi_pi16 +#define _m_punpckhdq _mm_unpackhi_pi32 +#define _m_punpcklbw _mm_unpacklo_pi8 +#define _m_punpcklwd _mm_unpacklo_pi16 +#define _m_punpckldq _mm_unpacklo_pi32 +#define _m_punpckehsbw _mm_unpackeh_pi8 +#define _m_punpckehswd _mm_unpackeh_pi16 +#define _m_punpckehsdq _mm_unpackeh_pi32 +#define _m_punpckehubw _mm_unpackeh_pu8 +#define _m_punpckehuwd _mm_unpackeh_pu16 +#define _m_punpckehudq _mm_unpackeh_pu32 +#define _m_punpckelsbw _mm_unpackel_pi8 +#define _m_punpckelswd _mm_unpackel_pi16 +#define _m_punpckelsdq _mm_unpackel_pi32 +#define _m_punpckelubw _mm_unpackel_pu8 +#define _m_punpckeluwd _mm_unpackel_pu16 +#define _m_punpckeludq _mm_unpackel_pu32 +#define _m_paddb _mm_add_pi8 +#define _m_paddw _mm_add_pi16 +#define _m_paddd _mm_add_pi32 +#define _m_paddsb _mm_adds_pi8 +#define _m_paddsw _mm_adds_pi16 +#define _m_paddsd _mm_adds_pi32 +#define _m_paddusb _mm_adds_pu8 +#define _m_paddusw _mm_adds_pu16 +#define _m_paddusd _mm_adds_pu32 +#define _m_psubb _mm_sub_pi8 +#define _m_psubw _mm_sub_pi16 +#define _m_psubd _mm_sub_pi32 +#define _m_psubsb _mm_subs_pi8 +#define _m_psubsw _mm_subs_pi16 +#define _m_psubuw _mm_subs_pi32 +#define _m_psubusb _mm_subs_pu8 +#define _m_psubusw _mm_subs_pu16 +#define _m_psubusd _mm_subs_pu32 +#define _m_pmaddwd _mm_madd_pi16 +#define _m_pmadduwd _mm_madd_pu16 +#define _m_pmulhw _mm_mulhi_pi16 +#define _m_pmulhuw _mm_mulhi_pu16 +#define _m_pmullw _mm_mullo_pi16 +#define _m_pmacsw _mm_mac_pi16 +#define _m_pmacuw _mm_mac_pu16 +#define _m_pmacszw _mm_macz_pi16 +#define _m_pmacuzw _mm_macz_pu16 +#define _m_paccb _mm_acc_pu8 +#define _m_paccw _mm_acc_pu16 +#define _m_paccd _mm_acc_pu32 +#define _m_pmia _mm_mia_si64 +#define _m_pmiaph _mm_miaph_si64 +#define _m_pmiabb _mm_miabb_si64 +#define _m_pmiabt _mm_miabt_si64 +#define _m_pmiatb _mm_miatb_si64 +#define _m_pmiatt _mm_miatt_si64 +#define _m_psllw _mm_sll_pi16 +#define _m_psllwi _mm_slli_pi16 +#define _m_pslld _mm_sll_pi32 +#define _m_pslldi _mm_slli_pi32 +#define _m_psllq _mm_sll_si64 +#define _m_psllqi _mm_slli_si64 +#define _m_psraw _mm_sra_pi16 +#define _m_psrawi _mm_srai_pi16 +#define _m_psrad _mm_sra_pi32 +#define _m_psradi _mm_srai_pi32 +#define _m_psraq _mm_sra_si64 +#define _m_psraqi _mm_srai_si64 +#define _m_psrlw _mm_srl_pi16 +#define _m_psrlwi _mm_srli_pi16 +#define _m_psrld _mm_srl_pi32 +#define _m_psrldi _mm_srli_pi32 +#define _m_psrlq _mm_srl_si64 +#define _m_psrlqi _mm_srli_si64 +#define _m_prorw _mm_ror_pi16 +#define _m_prorwi _mm_rori_pi16 +#define _m_prord _mm_ror_pi32 +#define _m_prordi _mm_rori_pi32 +#define _m_prorq _mm_ror_si64 +#define _m_prorqi _mm_rori_si64 +#define _m_pand _mm_and_si64 +#define _m_pandn _mm_andnot_si64 +#define _m_por _mm_or_si64 +#define _m_pxor _mm_xor_si64 +#define _m_pcmpeqb _mm_cmpeq_pi8 +#define _m_pcmpeqw _mm_cmpeq_pi16 +#define _m_pcmpeqd _mm_cmpeq_pi32 +#define _m_pcmpgtb _mm_cmpgt_pi8 +#define _m_pcmpgtub _mm_cmpgt_pu8 +#define _m_pcmpgtw _mm_cmpgt_pi16 +#define _m_pcmpgtuw _mm_cmpgt_pu16 +#define _m_pcmpgtd _mm_cmpgt_pi32 +#define _m_pcmpgtud _mm_cmpgt_pu32 +#define _m_pextrb _mm_extract_pi8 +#define _m_pextrw _mm_extract_pi16 +#define _m_pextrd _mm_extract_pi32 +#define _m_pextrub _mm_extract_pu8 +#define _m_pextruw _mm_extract_pu16 +#define _m_pextrud _mm_extract_pu32 +#define _m_pinsrb _mm_insert_pi8 +#define _m_pinsrw _mm_insert_pi16 +#define _m_pinsrd _mm_insert_pi32 +#define _m_pmaxsb _mm_max_pi8 +#define _m_pmaxsw _mm_max_pi16 +#define _m_pmaxsd _mm_max_pi32 +#define _m_pmaxub _mm_max_pu8 +#define _m_pmaxuw _mm_max_pu16 +#define _m_pmaxud _mm_max_pu32 +#define _m_pminsb _mm_min_pi8 +#define _m_pminsw _mm_min_pi16 +#define _m_pminsd _mm_min_pi32 +#define _m_pminub _mm_min_pu8 +#define _m_pminuw _mm_min_pu16 +#define _m_pminud _mm_min_pu32 +#define _m_pmovmskb _mm_movemask_pi8 +#define _m_pmovmskw _mm_movemask_pi16 +#define _m_pmovmskd _mm_movemask_pi32 +#define _m_pshufw _mm_shuffle_pi16 +#define _m_pavgb _mm_avg_pu8 +#define _m_pavgw _mm_avg_pu16 +#define _m_pavg2b _mm_avg2_pu8 +#define _m_pavg2w _mm_avg2_pu16 +#define _m_psadbw _mm_sad_pu8 +#define _m_psadwd _mm_sad_pu16 +#define _m_psadzbw _mm_sadz_pu8 +#define _m_psadzwd _mm_sadz_pu16 +#define _m_paligniq _mm_align_si64 +#define _m_cvt_si2pi _mm_cvtsi64_m64 +#define _m_cvt_pi2si _mm_cvtm64_si64 +#define _m_from_int _mm_cvtsi32_si64 +#define _m_to_int _mm_cvtsi64_si32 + +#if defined __cplusplus +}; /* End "C" */ +#endif /* __cplusplus */ + +#endif /* _MMINTRIN_H_INCLUDED */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/omp.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/omp.h new file mode 100644 index 0000000..b1824b5 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/omp.h @@ -0,0 +1,127 @@ +/* Copyright (C) 2005-2014 Free Software Foundation, Inc. + Contributed by Richard Henderson <rth@redhat.com>. + + This file is part of the GNU OpenMP Library (libgomp). + + Libgomp is free software; you can redistribute it and/or modify it + under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 3, or (at your option) + any later version. + + Libgomp is distributed in the hope that it will be useful, but WITHOUT ANY + WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS + FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see + <http://www.gnu.org/licenses/>. */ + +#ifndef _OMP_H +#define _OMP_H 1 + +#ifndef _LIBGOMP_OMP_LOCK_DEFINED +#define _LIBGOMP_OMP_LOCK_DEFINED 1 +/* These two structures get edited by the libgomp build process to + reflect the shape of the two types. Their internals are private + to the library. */ + +typedef struct +{ + unsigned char _x[4] + __attribute__((__aligned__(4))); +} omp_lock_t; + +typedef struct +{ + unsigned char _x[12] + __attribute__((__aligned__(4))); +} omp_nest_lock_t; +#endif + +typedef enum omp_sched_t +{ + omp_sched_static = 1, + omp_sched_dynamic = 2, + omp_sched_guided = 3, + omp_sched_auto = 4 +} omp_sched_t; + +typedef enum omp_proc_bind_t +{ + omp_proc_bind_false = 0, + omp_proc_bind_true = 1, + omp_proc_bind_master = 2, + omp_proc_bind_close = 3, + omp_proc_bind_spread = 4 +} omp_proc_bind_t; + +#ifdef __cplusplus +extern "C" { +# define __GOMP_NOTHROW throw () +#else +# define __GOMP_NOTHROW __attribute__((__nothrow__)) +#endif + +extern void omp_set_num_threads (int) __GOMP_NOTHROW; +extern int omp_get_num_threads (void) __GOMP_NOTHROW; +extern int omp_get_max_threads (void) __GOMP_NOTHROW; +extern int omp_get_thread_num (void) __GOMP_NOTHROW; +extern int omp_get_num_procs (void) __GOMP_NOTHROW; + +extern int omp_in_parallel (void) __GOMP_NOTHROW; + +extern void omp_set_dynamic (int) __GOMP_NOTHROW; +extern int omp_get_dynamic (void) __GOMP_NOTHROW; + +extern void omp_set_nested (int) __GOMP_NOTHROW; +extern int omp_get_nested (void) __GOMP_NOTHROW; + +extern void omp_init_lock (omp_lock_t *) __GOMP_NOTHROW; +extern void omp_destroy_lock (omp_lock_t *) __GOMP_NOTHROW; +extern void omp_set_lock (omp_lock_t *) __GOMP_NOTHROW; +extern void omp_unset_lock (omp_lock_t *) __GOMP_NOTHROW; +extern int omp_test_lock (omp_lock_t *) __GOMP_NOTHROW; + +extern void omp_init_nest_lock (omp_nest_lock_t *) __GOMP_NOTHROW; +extern void omp_destroy_nest_lock (omp_nest_lock_t *) __GOMP_NOTHROW; +extern void omp_set_nest_lock (omp_nest_lock_t *) __GOMP_NOTHROW; +extern void omp_unset_nest_lock (omp_nest_lock_t *) __GOMP_NOTHROW; +extern int omp_test_nest_lock (omp_nest_lock_t *) __GOMP_NOTHROW; + +extern double omp_get_wtime (void) __GOMP_NOTHROW; +extern double omp_get_wtick (void) __GOMP_NOTHROW; + +extern void omp_set_schedule (omp_sched_t, int) __GOMP_NOTHROW; +extern void omp_get_schedule (omp_sched_t *, int *) __GOMP_NOTHROW; +extern int omp_get_thread_limit (void) __GOMP_NOTHROW; +extern void omp_set_max_active_levels (int) __GOMP_NOTHROW; +extern int omp_get_max_active_levels (void) __GOMP_NOTHROW; +extern int omp_get_level (void) __GOMP_NOTHROW; +extern int omp_get_ancestor_thread_num (int) __GOMP_NOTHROW; +extern int omp_get_team_size (int) __GOMP_NOTHROW; +extern int omp_get_active_level (void) __GOMP_NOTHROW; + +extern int omp_in_final (void) __GOMP_NOTHROW; + +extern int omp_get_cancellation (void) __GOMP_NOTHROW; +extern omp_proc_bind_t omp_get_proc_bind (void) __GOMP_NOTHROW; + +extern void omp_set_default_device (int) __GOMP_NOTHROW; +extern int omp_get_default_device (void) __GOMP_NOTHROW; +extern int omp_get_num_devices (void) __GOMP_NOTHROW; +extern int omp_get_num_teams (void) __GOMP_NOTHROW; +extern int omp_get_team_num (void) __GOMP_NOTHROW; + +extern int omp_is_initial_device (void) __GOMP_NOTHROW; + +#ifdef __cplusplus +} +#endif + +#endif /* _OMP_H */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdalign.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdalign.h new file mode 100644 index 0000000..ee2d81f --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdalign.h @@ -0,0 +1,39 @@ +/* Copyright (C) 2011-2014 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 3, or (at your option) +any later version. + +GCC is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + +/* ISO C1X: 7.15 Alignment <stdalign.h>. */ + +#ifndef _STDALIGN_H +#define _STDALIGN_H + +#ifndef __cplusplus + +#define alignas _Alignas +#define alignof _Alignof + +#define __alignas_is_defined 1 +#define __alignof_is_defined 1 + +#endif + +#endif /* stdalign.h */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdarg.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdarg.h new file mode 100644 index 0000000..1d4418b --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdarg.h @@ -0,0 +1,126 @@ +/* Copyright (C) 1989-2014 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 3, or (at your option) +any later version. + +GCC is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + +/* + * ISO C Standard: 7.15 Variable arguments <stdarg.h> + */ + +#ifndef _STDARG_H +#ifndef _ANSI_STDARG_H_ +#ifndef __need___va_list +#define _STDARG_H +#define _ANSI_STDARG_H_ +#endif /* not __need___va_list */ +#undef __need___va_list + +/* Define __gnuc_va_list. */ + +#ifndef __GNUC_VA_LIST +#define __GNUC_VA_LIST +typedef __builtin_va_list __gnuc_va_list; +#endif + +/* Define the standard macros for the user, + if this invocation was from the user program. */ +#ifdef _STDARG_H + +#define va_start(v,l) __builtin_va_start(v,l) +#define va_end(v) __builtin_va_end(v) +#define va_arg(v,l) __builtin_va_arg(v,l) +#if !defined(__STRICT_ANSI__) || __STDC_VERSION__ + 0 >= 199900L || defined(__GXX_EXPERIMENTAL_CXX0X__) +#define va_copy(d,s) __builtin_va_copy(d,s) +#endif +#define __va_copy(d,s) __builtin_va_copy(d,s) + +/* Define va_list, if desired, from __gnuc_va_list. */ +/* We deliberately do not define va_list when called from + stdio.h, because ANSI C says that stdio.h is not supposed to define + va_list. stdio.h needs to have access to that data type, + but must not use that name. It should use the name __gnuc_va_list, + which is safe because it is reserved for the implementation. */ + +#ifdef _BSD_VA_LIST +#undef _BSD_VA_LIST +#endif + +#if defined(__svr4__) || (defined(_SCO_DS) && !defined(__VA_LIST)) +/* SVR4.2 uses _VA_LIST for an internal alias for va_list, + so we must avoid testing it and setting it here. + SVR4 uses _VA_LIST as a flag in stdarg.h, but we should + have no conflict with that. */ +#ifndef _VA_LIST_ +#define _VA_LIST_ +#ifdef __i860__ +#ifndef _VA_LIST +#define _VA_LIST va_list +#endif +#endif /* __i860__ */ +typedef __gnuc_va_list va_list; +#ifdef _SCO_DS +#define __VA_LIST +#endif +#endif /* _VA_LIST_ */ +#else /* not __svr4__ || _SCO_DS */ + +/* The macro _VA_LIST_ is the same thing used by this file in Ultrix. + But on BSD NET2 we must not test or define or undef it. + (Note that the comments in NET 2's ansi.h + are incorrect for _VA_LIST_--see stdio.h!) */ +#if !defined (_VA_LIST_) || defined (__BSD_NET2__) || defined (____386BSD____) || defined (__bsdi__) || defined (__sequent__) || defined (__FreeBSD__) || defined(WINNT) +/* The macro _VA_LIST_DEFINED is used in Windows NT 3.5 */ +#ifndef _VA_LIST_DEFINED +/* The macro _VA_LIST is used in SCO Unix 3.2. */ +#ifndef _VA_LIST +/* The macro _VA_LIST_T_H is used in the Bull dpx2 */ +#ifndef _VA_LIST_T_H +/* The macro __va_list__ is used by BeOS. */ +#ifndef __va_list__ +typedef __gnuc_va_list va_list; +#endif /* not __va_list__ */ +#endif /* not _VA_LIST_T_H */ +#endif /* not _VA_LIST */ +#endif /* not _VA_LIST_DEFINED */ +#if !(defined (__BSD_NET2__) || defined (____386BSD____) || defined (__bsdi__) || defined (__sequent__) || defined (__FreeBSD__)) +#define _VA_LIST_ +#endif +#ifndef _VA_LIST +#define _VA_LIST +#endif +#ifndef _VA_LIST_DEFINED +#define _VA_LIST_DEFINED +#endif +#ifndef _VA_LIST_T_H +#define _VA_LIST_T_H +#endif +#ifndef __va_list__ +#define __va_list__ +#endif + +#endif /* not _VA_LIST_, except on certain systems */ + +#endif /* not __svr4__ */ + +#endif /* _STDARG_H */ + +#endif /* not _ANSI_STDARG_H_ */ +#endif /* not _STDARG_H */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdatomic.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdatomic.h new file mode 100644 index 0000000..108259b --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdatomic.h @@ -0,0 +1,252 @@ +/* Copyright (C) 2013-2014 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 3, or (at your option) +any later version. + +GCC is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + +/* ISO C11 Standard: 7.17 Atomics <stdatomic.h>. */ + +#ifndef _STDATOMIC_H +#define _STDATOMIC_H + +typedef enum + { + memory_order_relaxed = __ATOMIC_RELAXED, + memory_order_consume = __ATOMIC_CONSUME, + memory_order_acquire = __ATOMIC_ACQUIRE, + memory_order_release = __ATOMIC_RELEASE, + memory_order_acq_rel = __ATOMIC_ACQ_REL, + memory_order_seq_cst = __ATOMIC_SEQ_CST + } memory_order; + + +typedef _Atomic _Bool atomic_bool; +typedef _Atomic char atomic_char; +typedef _Atomic signed char atomic_schar; +typedef _Atomic unsigned char atomic_uchar; +typedef _Atomic short atomic_short; +typedef _Atomic unsigned short atomic_ushort; +typedef _Atomic int atomic_int; +typedef _Atomic unsigned int atomic_uint; +typedef _Atomic long atomic_long; +typedef _Atomic unsigned long atomic_ulong; +typedef _Atomic long long atomic_llong; +typedef _Atomic unsigned long long atomic_ullong; +typedef _Atomic __CHAR16_TYPE__ atomic_char16_t; +typedef _Atomic __CHAR32_TYPE__ atomic_char32_t; +typedef _Atomic __WCHAR_TYPE__ atomic_wchar_t; +typedef _Atomic __INT_LEAST8_TYPE__ atomic_int_least8_t; +typedef _Atomic __UINT_LEAST8_TYPE__ atomic_uint_least8_t; +typedef _Atomic __INT_LEAST16_TYPE__ atomic_int_least16_t; +typedef _Atomic __UINT_LEAST16_TYPE__ atomic_uint_least16_t; +typedef _Atomic __INT_LEAST32_TYPE__ atomic_int_least32_t; +typedef _Atomic __UINT_LEAST32_TYPE__ atomic_uint_least32_t; +typedef _Atomic __INT_LEAST64_TYPE__ atomic_int_least64_t; +typedef _Atomic __UINT_LEAST64_TYPE__ atomic_uint_least64_t; +typedef _Atomic __INT_FAST8_TYPE__ atomic_int_fast8_t; +typedef _Atomic __UINT_FAST8_TYPE__ atomic_uint_fast8_t; +typedef _Atomic __INT_FAST16_TYPE__ atomic_int_fast16_t; +typedef _Atomic __UINT_FAST16_TYPE__ atomic_uint_fast16_t; +typedef _Atomic __INT_FAST32_TYPE__ atomic_int_fast32_t; +typedef _Atomic __UINT_FAST32_TYPE__ atomic_uint_fast32_t; +typedef _Atomic __INT_FAST64_TYPE__ atomic_int_fast64_t; +typedef _Atomic __UINT_FAST64_TYPE__ atomic_uint_fast64_t; +typedef _Atomic __INTPTR_TYPE__ atomic_intptr_t; +typedef _Atomic __UINTPTR_TYPE__ atomic_uintptr_t; +typedef _Atomic __SIZE_TYPE__ atomic_size_t; +typedef _Atomic __PTRDIFF_TYPE__ atomic_ptrdiff_t; +typedef _Atomic __INTMAX_TYPE__ atomic_intmax_t; +typedef _Atomic __UINTMAX_TYPE__ atomic_uintmax_t; + + +#define ATOMIC_VAR_INIT(VALUE) (VALUE) +#define atomic_init(PTR, VAL) \ + do \ + { \ + *(PTR) = (VAL); \ + } \ + while (0) + +#define kill_dependency(Y) \ + __extension__ \ + ({ \ + __auto_type __kill_dependency_tmp = (Y); \ + __kill_dependency_tmp; \ + }) + +#define atomic_thread_fence(MO) __atomic_thread_fence (MO) +#define atomic_signal_fence(MO) __atomic_signal_fence (MO) +#define atomic_is_lock_free(OBJ) __atomic_is_lock_free (sizeof (*(OBJ)), (OBJ)) + +#define __atomic_type_lock_free(T) \ + (__atomic_always_lock_free (sizeof (T), (void *) 0) \ + ? 2 \ + : (__atomic_is_lock_free (sizeof (T), (void *) 0) ? 1 : 0)) +#define ATOMIC_BOOL_LOCK_FREE \ + __atomic_type_lock_free (atomic_bool) +#define ATOMIC_CHAR_LOCK_FREE \ + __atomic_type_lock_free (atomic_char) +#define ATOMIC_CHAR16_T_LOCK_FREE \ + __atomic_type_lock_free (atomic_char16_t) +#define ATOMIC_CHAR32_T_LOCK_FREE \ + __atomic_type_lock_free (atomic_char32_t) +#define ATOMIC_WCHAR_T_LOCK_FREE \ + __atomic_type_lock_free (atomic_wchar_t) +#define ATOMIC_SHORT_LOCK_FREE \ + __atomic_type_lock_free (atomic_short) +#define ATOMIC_INT_LOCK_FREE \ + __atomic_type_lock_free (atomic_int) +#define ATOMIC_LONG_LOCK_FREE \ + __atomic_type_lock_free (atomic_long) +#define ATOMIC_LLONG_LOCK_FREE \ + __atomic_type_lock_free (atomic_llong) +#define ATOMIC_POINTER_LOCK_FREE \ + __atomic_type_lock_free (void * _Atomic) + + +/* Note that these macros require __typeof__ and __auto_type to remove + _Atomic qualifiers (and const qualifiers, if those are valid on + macro operands). + + Also note that the header file uses the generic form of __atomic + builtins, which requires the address to be taken of the value + parameter, and then we pass that value on. This allows the macros + to work for any type, and the compiler is smart enough to convert + these to lock-free _N variants if possible, and throw away the + temps. */ + +#define atomic_store_explicit(PTR, VAL, MO) \ + __extension__ \ + ({ \ + __auto_type __atomic_store_ptr = (PTR); \ + __typeof__ (*__atomic_store_ptr) __atomic_store_tmp = (VAL); \ + __atomic_store (__atomic_store_ptr, &__atomic_store_tmp, (MO)); \ + }) + +#define atomic_store(PTR, VAL) \ + atomic_store_explicit (PTR, VAL, __ATOMIC_SEQ_CST) + + +#define atomic_load_explicit(PTR, MO) \ + __extension__ \ + ({ \ + __auto_type __atomic_load_ptr = (PTR); \ + __typeof__ (*__atomic_load_ptr) __atomic_load_tmp; \ + __atomic_load (__atomic_load_ptr, &__atomic_load_tmp, (MO)); \ + __atomic_load_tmp; \ + }) + +#define atomic_load(PTR) atomic_load_explicit (PTR, __ATOMIC_SEQ_CST) + + +#define atomic_exchange_explicit(PTR, VAL, MO) \ + __extension__ \ + ({ \ + __auto_type __atomic_exchange_ptr = (PTR); \ + __typeof__ (*__atomic_exchange_ptr) __atomic_exchange_val = (VAL); \ + __typeof__ (*__atomic_exchange_ptr) __atomic_exchange_tmp; \ + __atomic_exchange (__atomic_exchange_ptr, &__atomic_exchange_val, \ + &__atomic_exchange_tmp, (MO)); \ + __atomic_exchange_tmp; \ + }) + +#define atomic_exchange(PTR, VAL) \ + atomic_exchange_explicit (PTR, VAL, __ATOMIC_SEQ_CST) + + +#define atomic_compare_exchange_strong_explicit(PTR, VAL, DES, SUC, FAIL) \ + __extension__ \ + ({ \ + __auto_type __atomic_compare_exchange_ptr = (PTR); \ + __typeof__ (*__atomic_compare_exchange_ptr) __atomic_compare_exchange_tmp \ + = (DES); \ + __atomic_compare_exchange (__atomic_compare_exchange_ptr, (VAL), \ + &__atomic_compare_exchange_tmp, 0, \ + (SUC), (FAIL)); \ + }) + +#define atomic_compare_exchange_strong(PTR, VAL, DES) \ + atomic_compare_exchange_strong_explicit (PTR, VAL, DES, __ATOMIC_SEQ_CST, \ + __ATOMIC_SEQ_CST) + +#define atomic_compare_exchange_weak_explicit(PTR, VAL, DES, SUC, FAIL) \ + __extension__ \ + ({ \ + __auto_type __atomic_compare_exchange_ptr = (PTR); \ + __typeof__ (*__atomic_compare_exchange_ptr) __atomic_compare_exchange_tmp \ + = (DES); \ + __atomic_compare_exchange (__atomic_compare_exchange_ptr, (VAL), \ + &__atomic_compare_exchange_tmp, 1, \ + (SUC), (FAIL)); \ + }) + +#define atomic_compare_exchange_weak(PTR, VAL, DES) \ + atomic_compare_exchange_weak_explicit (PTR, VAL, DES, __ATOMIC_SEQ_CST, \ + __ATOMIC_SEQ_CST) + + + +#define atomic_fetch_add(PTR, VAL) __atomic_fetch_add ((PTR), (VAL), \ + __ATOMIC_SEQ_CST) +#define atomic_fetch_add_explicit(PTR, VAL, MO) \ + __atomic_fetch_add ((PTR), (VAL), (MO)) + +#define atomic_fetch_sub(PTR, VAL) __atomic_fetch_sub ((PTR), (VAL), \ + __ATOMIC_SEQ_CST) +#define atomic_fetch_sub_explicit(PTR, VAL, MO) \ + __atomic_fetch_sub ((PTR), (VAL), (MO)) + +#define atomic_fetch_or(PTR, VAL) __atomic_fetch_or ((PTR), (VAL), \ + __ATOMIC_SEQ_CST) +#define atomic_fetch_or_explicit(PTR, VAL, MO) \ + __atomic_fetch_or ((PTR), (VAL), (MO)) + +#define atomic_fetch_xor(PTR, VAL) __atomic_fetch_xor ((PTR), (VAL), \ + __ATOMIC_SEQ_CST) +#define atomic_fetch_xor_explicit(PTR, VAL, MO) \ + __atomic_fetch_xor ((PTR), (VAL), (MO)) + +#define atomic_fetch_and(PTR, VAL) __atomic_fetch_and ((PTR), (VAL), \ + __ATOMIC_SEQ_CST) +#define atomic_fetch_and_explicit(PTR, VAL, MO) \ + __atomic_fetch_and ((PTR), (VAL), (MO)) + + +typedef _Atomic struct +{ +#if __GCC_ATOMIC_TEST_AND_SET_TRUEVAL == 1 + _Bool __val; +#else + unsigned char __val; +#endif +} atomic_flag; + +#define ATOMIC_FLAG_INIT { 0 } + + +#define atomic_flag_test_and_set(PTR) \ + __atomic_test_and_set ((PTR), __ATOMIC_SEQ_CST) +#define atomic_flag_test_and_set_explicit(PTR, MO) \ + __atomic_test_and_set ((PTR), (MO)) + +#define atomic_flag_clear(PTR) __atomic_clear ((PTR), __ATOMIC_SEQ_CST) +#define atomic_flag_clear_explicit(PTR, MO) __atomic_clear ((PTR), (MO)) + +#endif /* _STDATOMIC_H */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdbool.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdbool.h new file mode 100644 index 0000000..f4e802f --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdbool.h @@ -0,0 +1,50 @@ +/* Copyright (C) 1998-2014 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 3, or (at your option) +any later version. + +GCC is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + +/* + * ISO C Standard: 7.16 Boolean type and values <stdbool.h> + */ + +#ifndef _STDBOOL_H +#define _STDBOOL_H + +#ifndef __cplusplus + +#define bool _Bool +#define true 1 +#define false 0 + +#else /* __cplusplus */ + +/* Supporting <stdbool.h> in C++ is a GCC extension. */ +#define _Bool bool +#define bool bool +#define false false +#define true true + +#endif /* __cplusplus */ + +/* Signal that all the definitions are present. */ +#define __bool_true_false_are_defined 1 + +#endif /* stdbool.h */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stddef.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stddef.h new file mode 100644 index 0000000..cfa8df3 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stddef.h @@ -0,0 +1,439 @@ +/* Copyright (C) 1989-2014 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 3, or (at your option) +any later version. + +GCC is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + +/* + * ISO C Standard: 7.17 Common definitions <stddef.h> + */ +#if (!defined(_STDDEF_H) && !defined(_STDDEF_H_) && !defined(_ANSI_STDDEF_H) \ + && !defined(__STDDEF_H__)) \ + || defined(__need_wchar_t) || defined(__need_size_t) \ + || defined(__need_ptrdiff_t) || defined(__need_NULL) \ + || defined(__need_wint_t) + +/* Any one of these symbols __need_* means that GNU libc + wants us just to define one data type. So don't define + the symbols that indicate this file's entire job has been done. */ +#if (!defined(__need_wchar_t) && !defined(__need_size_t) \ + && !defined(__need_ptrdiff_t) && !defined(__need_NULL) \ + && !defined(__need_wint_t)) +#define _STDDEF_H +#define _STDDEF_H_ +/* snaroff@next.com says the NeXT needs this. */ +#define _ANSI_STDDEF_H +#endif + +#ifndef __sys_stdtypes_h +/* This avoids lossage on SunOS but only if stdtypes.h comes first. + There's no way to win with the other order! Sun lossage. */ + +/* On 4.3bsd-net2, make sure ansi.h is included, so we have + one less case to deal with in the following. */ +#if defined (__BSD_NET2__) || defined (____386BSD____) || (defined (__FreeBSD__) && (__FreeBSD__ < 5)) || defined(__NetBSD__) +#include <machine/ansi.h> +#endif +/* On FreeBSD 5, machine/ansi.h does not exist anymore... */ +#if defined (__FreeBSD__) && (__FreeBSD__ >= 5) +#include <sys/_types.h> +#endif + +/* In 4.3bsd-net2, machine/ansi.h defines these symbols, which are + defined if the corresponding type is *not* defined. + FreeBSD-2.1 defines _MACHINE_ANSI_H_ instead of _ANSI_H_. + NetBSD defines _I386_ANSI_H_ and _X86_64_ANSI_H_ instead of _ANSI_H_ */ +#if defined(_ANSI_H_) || defined(_MACHINE_ANSI_H_) || defined(_X86_64_ANSI_H_) || defined(_I386_ANSI_H_) +#if !defined(_SIZE_T_) && !defined(_BSD_SIZE_T_) +#define _SIZE_T +#endif +#if !defined(_PTRDIFF_T_) && !defined(_BSD_PTRDIFF_T_) +#define _PTRDIFF_T +#endif +/* On BSD/386 1.1, at least, machine/ansi.h defines _BSD_WCHAR_T_ + instead of _WCHAR_T_. */ +#if !defined(_WCHAR_T_) && !defined(_BSD_WCHAR_T_) +#ifndef _BSD_WCHAR_T_ +#define _WCHAR_T +#endif +#endif +/* Undef _FOO_T_ if we are supposed to define foo_t. */ +#if defined (__need_ptrdiff_t) || defined (_STDDEF_H_) +#undef _PTRDIFF_T_ +#undef _BSD_PTRDIFF_T_ +#endif +#if defined (__need_size_t) || defined (_STDDEF_H_) +#undef _SIZE_T_ +#undef _BSD_SIZE_T_ +#endif +#if defined (__need_wchar_t) || defined (_STDDEF_H_) +#undef _WCHAR_T_ +#undef _BSD_WCHAR_T_ +#endif +#endif /* defined(_ANSI_H_) || defined(_MACHINE_ANSI_H_) || defined(_X86_64_ANSI_H_) || defined(_I386_ANSI_H_) */ + +/* Sequent's header files use _PTRDIFF_T_ in some conflicting way. + Just ignore it. */ +#if defined (__sequent__) && defined (_PTRDIFF_T_) +#undef _PTRDIFF_T_ +#endif + +/* On VxWorks, <type/vxTypesBase.h> may have defined macros like + _TYPE_size_t which will typedef size_t. fixincludes patched the + vxTypesBase.h so that this macro is only defined if _GCC_SIZE_T is + not defined, and so that defining this macro defines _GCC_SIZE_T. + If we find that the macros are still defined at this point, we must + invoke them so that the type is defined as expected. */ +#if defined (_TYPE_ptrdiff_t) && (defined (__need_ptrdiff_t) || defined (_STDDEF_H_)) +_TYPE_ptrdiff_t; +#undef _TYPE_ptrdiff_t +#endif +#if defined (_TYPE_size_t) && (defined (__need_size_t) || defined (_STDDEF_H_)) +_TYPE_size_t; +#undef _TYPE_size_t +#endif +#if defined (_TYPE_wchar_t) && (defined (__need_wchar_t) || defined (_STDDEF_H_)) +_TYPE_wchar_t; +#undef _TYPE_wchar_t +#endif + +/* In case nobody has defined these types, but we aren't running under + GCC 2.00, make sure that __PTRDIFF_TYPE__, __SIZE_TYPE__, and + __WCHAR_TYPE__ have reasonable values. This can happen if the + parts of GCC is compiled by an older compiler, that actually + include gstddef.h, such as collect2. */ + +/* Signed type of difference of two pointers. */ + +/* Define this type if we are doing the whole job, + or if we want this type in particular. */ +#if defined (_STDDEF_H) || defined (__need_ptrdiff_t) +#ifndef _PTRDIFF_T /* in case <sys/types.h> has defined it. */ +#ifndef _T_PTRDIFF_ +#ifndef _T_PTRDIFF +#ifndef __PTRDIFF_T +#ifndef _PTRDIFF_T_ +#ifndef _BSD_PTRDIFF_T_ +#ifndef ___int_ptrdiff_t_h +#ifndef _GCC_PTRDIFF_T +#define _PTRDIFF_T +#define _T_PTRDIFF_ +#define _T_PTRDIFF +#define __PTRDIFF_T +#define _PTRDIFF_T_ +#define _BSD_PTRDIFF_T_ +#define ___int_ptrdiff_t_h +#define _GCC_PTRDIFF_T +#ifndef __PTRDIFF_TYPE__ +#define __PTRDIFF_TYPE__ long int +#endif +typedef __PTRDIFF_TYPE__ ptrdiff_t; +#endif /* _GCC_PTRDIFF_T */ +#endif /* ___int_ptrdiff_t_h */ +#endif /* _BSD_PTRDIFF_T_ */ +#endif /* _PTRDIFF_T_ */ +#endif /* __PTRDIFF_T */ +#endif /* _T_PTRDIFF */ +#endif /* _T_PTRDIFF_ */ +#endif /* _PTRDIFF_T */ + +/* If this symbol has done its job, get rid of it. */ +#undef __need_ptrdiff_t + +#endif /* _STDDEF_H or __need_ptrdiff_t. */ + +/* Unsigned type of `sizeof' something. */ + +/* Define this type if we are doing the whole job, + or if we want this type in particular. */ +#if defined (_STDDEF_H) || defined (__need_size_t) +#ifndef __size_t__ /* BeOS */ +#ifndef __SIZE_T__ /* Cray Unicos/Mk */ +#ifndef _SIZE_T /* in case <sys/types.h> has defined it. */ +#ifndef _SYS_SIZE_T_H +#ifndef _T_SIZE_ +#ifndef _T_SIZE +#ifndef __SIZE_T +#ifndef _SIZE_T_ +#ifndef _BSD_SIZE_T_ +#ifndef _SIZE_T_DEFINED_ +#ifndef _SIZE_T_DEFINED +#ifndef _BSD_SIZE_T_DEFINED_ /* Darwin */ +#ifndef _SIZE_T_DECLARED /* FreeBSD 5 */ +#ifndef ___int_size_t_h +#ifndef _GCC_SIZE_T +#ifndef _SIZET_ +#ifndef __size_t +#define __size_t__ /* BeOS */ +#define __SIZE_T__ /* Cray Unicos/Mk */ +#define _SIZE_T +#define _SYS_SIZE_T_H +#define _T_SIZE_ +#define _T_SIZE +#define __SIZE_T +#define _SIZE_T_ +#define _BSD_SIZE_T_ +#define _SIZE_T_DEFINED_ +#define _SIZE_T_DEFINED +#define _BSD_SIZE_T_DEFINED_ /* Darwin */ +#define _SIZE_T_DECLARED /* FreeBSD 5 */ +#define ___int_size_t_h +#define _GCC_SIZE_T +#define _SIZET_ +#if (defined (__FreeBSD__) && (__FreeBSD__ >= 5)) \ + || defined(__FreeBSD_kernel__) +/* __size_t is a typedef on FreeBSD 5, must not trash it. */ +#elif defined (__VMS__) +/* __size_t is also a typedef on VMS. */ +#else +#define __size_t +#endif +#ifndef __SIZE_TYPE__ +#define __SIZE_TYPE__ long unsigned int +#endif +#if !(defined (__GNUG__) && defined (size_t)) +typedef __SIZE_TYPE__ size_t; +#ifdef __BEOS__ +typedef long ssize_t; +#endif /* __BEOS__ */ +#endif /* !(defined (__GNUG__) && defined (size_t)) */ +#endif /* __size_t */ +#endif /* _SIZET_ */ +#endif /* _GCC_SIZE_T */ +#endif /* ___int_size_t_h */ +#endif /* _SIZE_T_DECLARED */ +#endif /* _BSD_SIZE_T_DEFINED_ */ +#endif /* _SIZE_T_DEFINED */ +#endif /* _SIZE_T_DEFINED_ */ +#endif /* _BSD_SIZE_T_ */ +#endif /* _SIZE_T_ */ +#endif /* __SIZE_T */ +#endif /* _T_SIZE */ +#endif /* _T_SIZE_ */ +#endif /* _SYS_SIZE_T_H */ +#endif /* _SIZE_T */ +#endif /* __SIZE_T__ */ +#endif /* __size_t__ */ +#undef __need_size_t +#endif /* _STDDEF_H or __need_size_t. */ + + +/* Wide character type. + Locale-writers should change this as necessary to + be big enough to hold unique values not between 0 and 127, + and not (wchar_t) -1, for each defined multibyte character. */ + +/* Define this type if we are doing the whole job, + or if we want this type in particular. */ +#if defined (_STDDEF_H) || defined (__need_wchar_t) +#ifndef __wchar_t__ /* BeOS */ +#ifndef __WCHAR_T__ /* Cray Unicos/Mk */ +#ifndef _WCHAR_T +#ifndef _T_WCHAR_ +#ifndef _T_WCHAR +#ifndef __WCHAR_T +#ifndef _WCHAR_T_ +#ifndef _BSD_WCHAR_T_ +#ifndef _BSD_WCHAR_T_DEFINED_ /* Darwin */ +#ifndef _BSD_RUNE_T_DEFINED_ /* Darwin */ +#ifndef _WCHAR_T_DECLARED /* FreeBSD 5 */ +#ifndef _WCHAR_T_DEFINED_ +#ifndef _WCHAR_T_DEFINED +#ifndef _WCHAR_T_H +#ifndef ___int_wchar_t_h +#ifndef __INT_WCHAR_T_H +#ifndef _GCC_WCHAR_T +#define __wchar_t__ /* BeOS */ +#define __WCHAR_T__ /* Cray Unicos/Mk */ +#define _WCHAR_T +#define _T_WCHAR_ +#define _T_WCHAR +#define __WCHAR_T +#define _WCHAR_T_ +#define _BSD_WCHAR_T_ +#define _WCHAR_T_DEFINED_ +#define _WCHAR_T_DEFINED +#define _WCHAR_T_H +#define ___int_wchar_t_h +#define __INT_WCHAR_T_H +#define _GCC_WCHAR_T +#define _WCHAR_T_DECLARED + +/* On BSD/386 1.1, at least, machine/ansi.h defines _BSD_WCHAR_T_ + instead of _WCHAR_T_, and _BSD_RUNE_T_ (which, unlike the other + symbols in the _FOO_T_ family, stays defined even after its + corresponding type is defined). If we define wchar_t, then we + must undef _WCHAR_T_; for BSD/386 1.1 (and perhaps others), if + we undef _WCHAR_T_, then we must also define rune_t, since + headers like runetype.h assume that if machine/ansi.h is included, + and _BSD_WCHAR_T_ is not defined, then rune_t is available. + machine/ansi.h says, "Note that _WCHAR_T_ and _RUNE_T_ must be of + the same type." */ +#ifdef _BSD_WCHAR_T_ +#undef _BSD_WCHAR_T_ +#ifdef _BSD_RUNE_T_ +#if !defined (_ANSI_SOURCE) && !defined (_POSIX_SOURCE) +typedef _BSD_RUNE_T_ rune_t; +#define _BSD_WCHAR_T_DEFINED_ +#define _BSD_RUNE_T_DEFINED_ /* Darwin */ +#if defined (__FreeBSD__) && (__FreeBSD__ < 5) +/* Why is this file so hard to maintain properly? In contrast to + the comment above regarding BSD/386 1.1, on FreeBSD for as long + as the symbol has existed, _BSD_RUNE_T_ must not stay defined or + redundant typedefs will occur when stdlib.h is included after this file. */ +#undef _BSD_RUNE_T_ +#endif +#endif +#endif +#endif +/* FreeBSD 5 can't be handled well using "traditional" logic above + since it no longer defines _BSD_RUNE_T_ yet still desires to export + rune_t in some cases... */ +#if defined (__FreeBSD__) && (__FreeBSD__ >= 5) +#if !defined (_ANSI_SOURCE) && !defined (_POSIX_SOURCE) +#if __BSD_VISIBLE +#ifndef _RUNE_T_DECLARED +typedef __rune_t rune_t; +#define _RUNE_T_DECLARED +#endif +#endif +#endif +#endif + +#ifndef __WCHAR_TYPE__ +#define __WCHAR_TYPE__ int +#endif +#ifndef __cplusplus +typedef __WCHAR_TYPE__ wchar_t; +#endif +#endif +#endif +#endif +#endif +#endif +#endif +#endif /* _WCHAR_T_DECLARED */ +#endif /* _BSD_RUNE_T_DEFINED_ */ +#endif +#endif +#endif +#endif +#endif +#endif +#endif +#endif /* __WCHAR_T__ */ +#endif /* __wchar_t__ */ +#undef __need_wchar_t +#endif /* _STDDEF_H or __need_wchar_t. */ + +#if defined (__need_wint_t) +#ifndef _WINT_T +#define _WINT_T + +#ifndef __WINT_TYPE__ +#define __WINT_TYPE__ unsigned int +#endif +typedef __WINT_TYPE__ wint_t; +#endif +#undef __need_wint_t +#endif + +/* In 4.3bsd-net2, leave these undefined to indicate that size_t, etc. + are already defined. */ +/* BSD/OS 3.1 and FreeBSD [23].x require the MACHINE_ANSI_H check here. */ +/* NetBSD 5 requires the I386_ANSI_H and X86_64_ANSI_H checks here. */ +#if defined(_ANSI_H_) || defined(_MACHINE_ANSI_H_) || defined(_X86_64_ANSI_H_) || defined(_I386_ANSI_H_) +/* The references to _GCC_PTRDIFF_T_, _GCC_SIZE_T_, and _GCC_WCHAR_T_ + are probably typos and should be removed before 2.8 is released. */ +#ifdef _GCC_PTRDIFF_T_ +#undef _PTRDIFF_T_ +#undef _BSD_PTRDIFF_T_ +#endif +#ifdef _GCC_SIZE_T_ +#undef _SIZE_T_ +#undef _BSD_SIZE_T_ +#endif +#ifdef _GCC_WCHAR_T_ +#undef _WCHAR_T_ +#undef _BSD_WCHAR_T_ +#endif +/* The following ones are the real ones. */ +#ifdef _GCC_PTRDIFF_T +#undef _PTRDIFF_T_ +#undef _BSD_PTRDIFF_T_ +#endif +#ifdef _GCC_SIZE_T +#undef _SIZE_T_ +#undef _BSD_SIZE_T_ +#endif +#ifdef _GCC_WCHAR_T +#undef _WCHAR_T_ +#undef _BSD_WCHAR_T_ +#endif +#endif /* _ANSI_H_ || _MACHINE_ANSI_H_ || _X86_64_ANSI_H_ || _I386_ANSI_H_ */ + +#endif /* __sys_stdtypes_h */ + +/* A null pointer constant. */ + +#if defined (_STDDEF_H) || defined (__need_NULL) +#undef NULL /* in case <stdio.h> has defined it. */ +#ifdef __GNUG__ +#define NULL __null +#else /* G++ */ +#ifndef __cplusplus +#define NULL ((void *)0) +#else /* C++ */ +#define NULL 0 +#endif /* C++ */ +#endif /* G++ */ +#endif /* NULL not defined and <stddef.h> or need NULL. */ +#undef __need_NULL + +#ifdef _STDDEF_H + +/* Offset of member MEMBER in a struct of type TYPE. */ +#define offsetof(TYPE, MEMBER) __builtin_offsetof (TYPE, MEMBER) + +#if (defined (__STDC_VERSION__) && __STDC_VERSION__ >= 201112L) \ + || (defined(__cplusplus) && __cplusplus >= 201103L) +#ifndef _GCC_MAX_ALIGN_T +#define _GCC_MAX_ALIGN_T +/* Type whose alignment is supported in every context and is at least + as great as that of any standard type not using alignment + specifiers. */ +typedef struct { + long long __max_align_ll __attribute__((__aligned__(__alignof__(long long)))); + long double __max_align_ld __attribute__((__aligned__(__alignof__(long double)))); +} max_align_t; +#endif +#endif /* C11 or C++11. */ + +#if defined(__cplusplus) && __cplusplus >= 201103L +#ifndef _GXX_NULLPTR_T +#define _GXX_NULLPTR_T + typedef decltype(nullptr) nullptr_t; +#endif +#endif /* C++11. */ + +#endif /* _STDDEF_H was defined this time */ + +#endif /* !_STDDEF_H && !_STDDEF_H_ && !_ANSI_STDDEF_H && !__STDDEF_H__ + || __need_XXX was not defined before */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdfix.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdfix.h new file mode 100644 index 0000000..93e759a --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdfix.h @@ -0,0 +1,204 @@ +/* Copyright (C) 2007-2014 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 3, or (at your option) +any later version. + +GCC is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + +/* ISO/IEC JTC1 SC22 WG14 N1169 + * Date: 2006-04-04 + * ISO/IEC TR 18037 + * Programming languages - C - Extensions to support embedded processors + */ + +#ifndef _STDFIX_H +#define _STDFIX_H + +/* 7.18a.1 Introduction. */ + +#undef fract +#undef accum +#undef sat +#define fract _Fract +#define accum _Accum +#define sat _Sat + +/* 7.18a.3 Precision macros. */ + +#undef SFRACT_FBIT +#undef SFRACT_MIN +#undef SFRACT_MAX +#undef SFRACT_EPSILON +#define SFRACT_FBIT __SFRACT_FBIT__ +#define SFRACT_MIN __SFRACT_MIN__ +#define SFRACT_MAX __SFRACT_MAX__ +#define SFRACT_EPSILON __SFRACT_EPSILON__ + +#undef USFRACT_FBIT +#undef USFRACT_MIN +#undef USFRACT_MAX +#undef USFRACT_EPSILON +#define USFRACT_FBIT __USFRACT_FBIT__ +#define USFRACT_MIN __USFRACT_MIN__ /* GCC extension. */ +#define USFRACT_MAX __USFRACT_MAX__ +#define USFRACT_EPSILON __USFRACT_EPSILON__ + +#undef FRACT_FBIT +#undef FRACT_MIN +#undef FRACT_MAX +#undef FRACT_EPSILON +#define FRACT_FBIT __FRACT_FBIT__ +#define FRACT_MIN __FRACT_MIN__ +#define FRACT_MAX __FRACT_MAX__ +#define FRACT_EPSILON __FRACT_EPSILON__ + +#undef UFRACT_FBIT +#undef UFRACT_MIN +#undef UFRACT_MAX +#undef UFRACT_EPSILON +#define UFRACT_FBIT __UFRACT_FBIT__ +#define UFRACT_MIN __UFRACT_MIN__ /* GCC extension. */ +#define UFRACT_MAX __UFRACT_MAX__ +#define UFRACT_EPSILON __UFRACT_EPSILON__ + +#undef LFRACT_FBIT +#undef LFRACT_MIN +#undef LFRACT_MAX +#undef LFRACT_EPSILON +#define LFRACT_FBIT __LFRACT_FBIT__ +#define LFRACT_MIN __LFRACT_MIN__ +#define LFRACT_MAX __LFRACT_MAX__ +#define LFRACT_EPSILON __LFRACT_EPSILON__ + +#undef ULFRACT_FBIT +#undef ULFRACT_MIN +#undef ULFRACT_MAX +#undef ULFRACT_EPSILON +#define ULFRACT_FBIT __ULFRACT_FBIT__ +#define ULFRACT_MIN __ULFRACT_MIN__ /* GCC extension. */ +#define ULFRACT_MAX __ULFRACT_MAX__ +#define ULFRACT_EPSILON __ULFRACT_EPSILON__ + +#undef LLFRACT_FBIT +#undef LLFRACT_MIN +#undef LLFRACT_MAX +#undef LLFRACT_EPSILON +#define LLFRACT_FBIT __LLFRACT_FBIT__ /* GCC extension. */ +#define LLFRACT_MIN __LLFRACT_MIN__ /* GCC extension. */ +#define LLFRACT_MAX __LLFRACT_MAX__ /* GCC extension. */ +#define LLFRACT_EPSILON __LLFRACT_EPSILON__ /* GCC extension. */ + +#undef ULLFRACT_FBIT +#undef ULLFRACT_MIN +#undef ULLFRACT_MAX +#undef ULLFRACT_EPSILON +#define ULLFRACT_FBIT __ULLFRACT_FBIT__ /* GCC extension. */ +#define ULLFRACT_MIN __ULLFRACT_MIN__ /* GCC extension. */ +#define ULLFRACT_MAX __ULLFRACT_MAX__ /* GCC extension. */ +#define ULLFRACT_EPSILON __ULLFRACT_EPSILON__ /* GCC extension. */ + +#undef SACCUM_FBIT +#undef SACCUM_IBIT +#undef SACCUM_MIN +#undef SACCUM_MAX +#undef SACCUM_EPSILON +#define SACCUM_FBIT __SACCUM_FBIT__ +#define SACCUM_IBIT __SACCUM_IBIT__ +#define SACCUM_MIN __SACCUM_MIN__ +#define SACCUM_MAX __SACCUM_MAX__ +#define SACCUM_EPSILON __SACCUM_EPSILON__ + +#undef USACCUM_FBIT +#undef USACCUM_IBIT +#undef USACCUM_MIN +#undef USACCUM_MAX +#undef USACCUM_EPSILON +#define USACCUM_FBIT __USACCUM_FBIT__ +#define USACCUM_IBIT __USACCUM_IBIT__ +#define USACCUM_MIN __USACCUM_MIN__ /* GCC extension. */ +#define USACCUM_MAX __USACCUM_MAX__ +#define USACCUM_EPSILON __USACCUM_EPSILON__ + +#undef ACCUM_FBIT +#undef ACCUM_IBIT +#undef ACCUM_MIN +#undef ACCUM_MAX +#undef ACCUM_EPSILON +#define ACCUM_FBIT __ACCUM_FBIT__ +#define ACCUM_IBIT __ACCUM_IBIT__ +#define ACCUM_MIN __ACCUM_MIN__ +#define ACCUM_MAX __ACCUM_MAX__ +#define ACCUM_EPSILON __ACCUM_EPSILON__ + +#undef UACCUM_FBIT +#undef UACCUM_IBIT +#undef UACCUM_MIN +#undef UACCUM_MAX +#undef UACCUM_EPSILON +#define UACCUM_FBIT __UACCUM_FBIT__ +#define UACCUM_IBIT __UACCUM_IBIT__ +#define UACCUM_MIN __UACCUM_MIN__ /* GCC extension. */ +#define UACCUM_MAX __UACCUM_MAX__ +#define UACCUM_EPSILON __UACCUM_EPSILON__ + +#undef LACCUM_FBIT +#undef LACCUM_IBIT +#undef LACCUM_MIN +#undef LACCUM_MAX +#undef LACCUM_EPSILON +#define LACCUM_FBIT __LACCUM_FBIT__ +#define LACCUM_IBIT __LACCUM_IBIT__ +#define LACCUM_MIN __LACCUM_MIN__ +#define LACCUM_MAX __LACCUM_MAX__ +#define LACCUM_EPSILON __LACCUM_EPSILON__ + +#undef ULACCUM_FBIT +#undef ULACCUM_IBIT +#undef ULACCUM_MIN +#undef ULACCUM_MAX +#undef ULACCUM_EPSILON +#define ULACCUM_FBIT __ULACCUM_FBIT__ +#define ULACCUM_IBIT __ULACCUM_IBIT__ +#define ULACCUM_MIN __ULACCUM_MIN__ /* GCC extension. */ +#define ULACCUM_MAX __ULACCUM_MAX__ +#define ULACCUM_EPSILON __ULACCUM_EPSILON__ + +#undef LLACCUM_FBIT +#undef LLACCUM_IBIT +#undef LLACCUM_MIN +#undef LLACCUM_MAX +#undef LLACCUM_EPSILON +#define LLACCUM_FBIT __LLACCUM_FBIT__ /* GCC extension. */ +#define LLACCUM_IBIT __LLACCUM_IBIT__ /* GCC extension. */ +#define LLACCUM_MIN __LLACCUM_MIN__ /* GCC extension. */ +#define LLACCUM_MAX __LLACCUM_MAX__ /* GCC extension. */ +#define LLACCUM_EPSILON __LLACCUM_EPSILON__ /* GCC extension. */ + +#undef ULLACCUM_FBIT +#undef ULLACCUM_IBIT +#undef ULLACCUM_MIN +#undef ULLACCUM_MAX +#undef ULLACCUM_EPSILON +#define ULLACCUM_FBIT __ULLACCUM_FBIT__ /* GCC extension. */ +#define ULLACCUM_IBIT __ULLACCUM_IBIT__ /* GCC extension. */ +#define ULLACCUM_MIN __ULLACCUM_MIN__ /* GCC extension. */ +#define ULLACCUM_MAX __ULLACCUM_MAX__ /* GCC extension. */ +#define ULLACCUM_EPSILON __ULLACCUM_EPSILON__ /* GCC extension. */ + +#endif /* _STDFIX_H */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdint-gcc.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdint-gcc.h new file mode 100644 index 0000000..1470cea --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdint-gcc.h @@ -0,0 +1,263 @@ +/* Copyright (C) 2008-2014 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 3, or (at your option) +any later version. + +GCC is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + +/* + * ISO C Standard: 7.18 Integer types <stdint.h> + */ + +#ifndef _GCC_STDINT_H +#define _GCC_STDINT_H + +/* 7.8.1.1 Exact-width integer types */ + +#ifdef __INT8_TYPE__ +typedef __INT8_TYPE__ int8_t; +#endif +#ifdef __INT16_TYPE__ +typedef __INT16_TYPE__ int16_t; +#endif +#ifdef __INT32_TYPE__ +typedef __INT32_TYPE__ int32_t; +#endif +#ifdef __INT64_TYPE__ +typedef __INT64_TYPE__ int64_t; +#endif +#ifdef __UINT8_TYPE__ +typedef __UINT8_TYPE__ uint8_t; +#endif +#ifdef __UINT16_TYPE__ +typedef __UINT16_TYPE__ uint16_t; +#endif +#ifdef __UINT32_TYPE__ +typedef __UINT32_TYPE__ uint32_t; +#endif +#ifdef __UINT64_TYPE__ +typedef __UINT64_TYPE__ uint64_t; +#endif + +/* 7.8.1.2 Minimum-width integer types */ + +typedef __INT_LEAST8_TYPE__ int_least8_t; +typedef __INT_LEAST16_TYPE__ int_least16_t; +typedef __INT_LEAST32_TYPE__ int_least32_t; +typedef __INT_LEAST64_TYPE__ int_least64_t; +typedef __UINT_LEAST8_TYPE__ uint_least8_t; +typedef __UINT_LEAST16_TYPE__ uint_least16_t; +typedef __UINT_LEAST32_TYPE__ uint_least32_t; +typedef __UINT_LEAST64_TYPE__ uint_least64_t; + +/* 7.8.1.3 Fastest minimum-width integer types */ + +typedef __INT_FAST8_TYPE__ int_fast8_t; +typedef __INT_FAST16_TYPE__ int_fast16_t; +typedef __INT_FAST32_TYPE__ int_fast32_t; +typedef __INT_FAST64_TYPE__ int_fast64_t; +typedef __UINT_FAST8_TYPE__ uint_fast8_t; +typedef __UINT_FAST16_TYPE__ uint_fast16_t; +typedef __UINT_FAST32_TYPE__ uint_fast32_t; +typedef __UINT_FAST64_TYPE__ uint_fast64_t; + +/* 7.8.1.4 Integer types capable of holding object pointers */ + +#ifdef __INTPTR_TYPE__ +typedef __INTPTR_TYPE__ intptr_t; +#endif +#ifdef __UINTPTR_TYPE__ +typedef __UINTPTR_TYPE__ uintptr_t; +#endif + +/* 7.8.1.5 Greatest-width integer types */ + +typedef __INTMAX_TYPE__ intmax_t; +typedef __UINTMAX_TYPE__ uintmax_t; + +#if (!defined __cplusplus || __cplusplus >= 201103L \ + || defined __STDC_LIMIT_MACROS) + +/* 7.18.2 Limits of specified-width integer types */ + +#ifdef __INT8_MAX__ +# undef INT8_MAX +# define INT8_MAX __INT8_MAX__ +# undef INT8_MIN +# define INT8_MIN (-INT8_MAX - 1) +#endif +#ifdef __UINT8_MAX__ +# undef UINT8_MAX +# define UINT8_MAX __UINT8_MAX__ +#endif +#ifdef __INT16_MAX__ +# undef INT16_MAX +# define INT16_MAX __INT16_MAX__ +# undef INT16_MIN +# define INT16_MIN (-INT16_MAX - 1) +#endif +#ifdef __UINT16_MAX__ +# undef UINT16_MAX +# define UINT16_MAX __UINT16_MAX__ +#endif +#ifdef __INT32_MAX__ +# undef INT32_MAX +# define INT32_MAX __INT32_MAX__ +# undef INT32_MIN +# define INT32_MIN (-INT32_MAX - 1) +#endif +#ifdef __UINT32_MAX__ +# undef UINT32_MAX +# define UINT32_MAX __UINT32_MAX__ +#endif +#ifdef __INT64_MAX__ +# undef INT64_MAX +# define INT64_MAX __INT64_MAX__ +# undef INT64_MIN +# define INT64_MIN (-INT64_MAX - 1) +#endif +#ifdef __UINT64_MAX__ +# undef UINT64_MAX +# define UINT64_MAX __UINT64_MAX__ +#endif + +#undef INT_LEAST8_MAX +#define INT_LEAST8_MAX __INT_LEAST8_MAX__ +#undef INT_LEAST8_MIN +#define INT_LEAST8_MIN (-INT_LEAST8_MAX - 1) +#undef UINT_LEAST8_MAX +#define UINT_LEAST8_MAX __UINT_LEAST8_MAX__ +#undef INT_LEAST16_MAX +#define INT_LEAST16_MAX __INT_LEAST16_MAX__ +#undef INT_LEAST16_MIN +#define INT_LEAST16_MIN (-INT_LEAST16_MAX - 1) +#undef UINT_LEAST16_MAX +#define UINT_LEAST16_MAX __UINT_LEAST16_MAX__ +#undef INT_LEAST32_MAX +#define INT_LEAST32_MAX __INT_LEAST32_MAX__ +#undef INT_LEAST32_MIN +#define INT_LEAST32_MIN (-INT_LEAST32_MAX - 1) +#undef UINT_LEAST32_MAX +#define UINT_LEAST32_MAX __UINT_LEAST32_MAX__ +#undef INT_LEAST64_MAX +#define INT_LEAST64_MAX __INT_LEAST64_MAX__ +#undef INT_LEAST64_MIN +#define INT_LEAST64_MIN (-INT_LEAST64_MAX - 1) +#undef UINT_LEAST64_MAX +#define UINT_LEAST64_MAX __UINT_LEAST64_MAX__ + +#undef INT_FAST8_MAX +#define INT_FAST8_MAX __INT_FAST8_MAX__ +#undef INT_FAST8_MIN +#define INT_FAST8_MIN (-INT_FAST8_MAX - 1) +#undef UINT_FAST8_MAX +#define UINT_FAST8_MAX __UINT_FAST8_MAX__ +#undef INT_FAST16_MAX +#define INT_FAST16_MAX __INT_FAST16_MAX__ +#undef INT_FAST16_MIN +#define INT_FAST16_MIN (-INT_FAST16_MAX - 1) +#undef UINT_FAST16_MAX +#define UINT_FAST16_MAX __UINT_FAST16_MAX__ +#undef INT_FAST32_MAX +#define INT_FAST32_MAX __INT_FAST32_MAX__ +#undef INT_FAST32_MIN +#define INT_FAST32_MIN (-INT_FAST32_MAX - 1) +#undef UINT_FAST32_MAX +#define UINT_FAST32_MAX __UINT_FAST32_MAX__ +#undef INT_FAST64_MAX +#define INT_FAST64_MAX __INT_FAST64_MAX__ +#undef INT_FAST64_MIN +#define INT_FAST64_MIN (-INT_FAST64_MAX - 1) +#undef UINT_FAST64_MAX +#define UINT_FAST64_MAX __UINT_FAST64_MAX__ + +#ifdef __INTPTR_MAX__ +# undef INTPTR_MAX +# define INTPTR_MAX __INTPTR_MAX__ +# undef INTPTR_MIN +# define INTPTR_MIN (-INTPTR_MAX - 1) +#endif +#ifdef __UINTPTR_MAX__ +# undef UINTPTR_MAX +# define UINTPTR_MAX __UINTPTR_MAX__ +#endif + +#undef INTMAX_MAX +#define INTMAX_MAX __INTMAX_MAX__ +#undef INTMAX_MIN +#define INTMAX_MIN (-INTMAX_MAX - 1) +#undef UINTMAX_MAX +#define UINTMAX_MAX __UINTMAX_MAX__ + +/* 7.18.3 Limits of other integer types */ + +#undef PTRDIFF_MAX +#define PTRDIFF_MAX __PTRDIFF_MAX__ +#undef PTRDIFF_MIN +#define PTRDIFF_MIN (-PTRDIFF_MAX - 1) + +#undef SIG_ATOMIC_MAX +#define SIG_ATOMIC_MAX __SIG_ATOMIC_MAX__ +#undef SIG_ATOMIC_MIN +#define SIG_ATOMIC_MIN __SIG_ATOMIC_MIN__ + +#undef SIZE_MAX +#define SIZE_MAX __SIZE_MAX__ + +#undef WCHAR_MAX +#define WCHAR_MAX __WCHAR_MAX__ +#undef WCHAR_MIN +#define WCHAR_MIN __WCHAR_MIN__ + +#undef WINT_MAX +#define WINT_MAX __WINT_MAX__ +#undef WINT_MIN +#define WINT_MIN __WINT_MIN__ + +#endif /* (!defined __cplusplus || __cplusplus >= 201103L + || defined __STDC_LIMIT_MACROS) */ + +#if (!defined __cplusplus || __cplusplus >= 201103L \ + || defined __STDC_CONSTANT_MACROS) + +#undef INT8_C +#define INT8_C(c) __INT8_C(c) +#undef INT16_C +#define INT16_C(c) __INT16_C(c) +#undef INT32_C +#define INT32_C(c) __INT32_C(c) +#undef INT64_C +#define INT64_C(c) __INT64_C(c) +#undef UINT8_C +#define UINT8_C(c) __UINT8_C(c) +#undef UINT16_C +#define UINT16_C(c) __UINT16_C(c) +#undef UINT32_C +#define UINT32_C(c) __UINT32_C(c) +#undef UINT64_C +#define UINT64_C(c) __UINT64_C(c) +#undef INTMAX_C +#define INTMAX_C(c) __INTMAX_C(c) +#undef UINTMAX_C +#define UINTMAX_C(c) __UINTMAX_C(c) + +#endif /* (!defined __cplusplus || __cplusplus >= 201103L + || defined __STDC_CONSTANT_MACROS) */ + +#endif /* _GCC_STDINT_H */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdint.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdint.h new file mode 100644 index 0000000..83b6f70 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdint.h @@ -0,0 +1,14 @@ +#ifndef _GCC_WRAP_STDINT_H +#if __STDC_HOSTED__ +# if defined __cplusplus && __cplusplus >= 201103L +# undef __STDC_LIMIT_MACROS +# define __STDC_LIMIT_MACROS +# undef __STDC_CONSTANT_MACROS +# define __STDC_CONSTANT_MACROS +# endif +# include_next <stdint.h> +#else +# include "stdint-gcc.h" +#endif +#define _GCC_WRAP_STDINT_H +#endif diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdnoreturn.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdnoreturn.h new file mode 100644 index 0000000..0134137 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/stdnoreturn.h @@ -0,0 +1,35 @@ +/* Copyright (C) 2011-2014 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 3, or (at your option) +any later version. + +GCC is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + +/* ISO C1X: 7.23 _Noreturn <stdnoreturn.h>. */ + +#ifndef _STDNORETURN_H +#define _STDNORETURN_H + +#ifndef __cplusplus + +#define noreturn _Noreturn + +#endif + +#endif /* stdnoreturn.h */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/unwind-arm-common.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/unwind-arm-common.h new file mode 100644 index 0000000..65b50bc --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/unwind-arm-common.h @@ -0,0 +1,250 @@ +/* Header file for the ARM EABI and C6X unwinders + Copyright (C) 2003-2014 Free Software Foundation, Inc. + Contributed by Paul Brook + + This file is free software; you can redistribute it and/or modify it + under the terms of the GNU General Public License as published by the + Free Software Foundation; either version 3, or (at your option) any + later version. + + This file is distributed in the hope that it will be useful, but + WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + General Public License for more details. + + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see + <http://www.gnu.org/licenses/>. */ + +/* Language-independent unwinder header public defines. This contains both + ABI defined objects, and GNU support routines. */ + +#ifndef UNWIND_ARM_COMMON_H +#define UNWIND_ARM_COMMON_H + +#define __ARM_EABI_UNWINDER__ 1 + +#ifdef __cplusplus +extern "C" { +#endif + typedef unsigned _Unwind_Word __attribute__((__mode__(__word__))); + typedef signed _Unwind_Sword __attribute__((__mode__(__word__))); + typedef unsigned _Unwind_Ptr __attribute__((__mode__(__pointer__))); + typedef unsigned _Unwind_Internal_Ptr __attribute__((__mode__(__pointer__))); + typedef _Unwind_Word _uw; + typedef unsigned _uw64 __attribute__((mode(__DI__))); + typedef unsigned _uw16 __attribute__((mode(__HI__))); + typedef unsigned _uw8 __attribute__((mode(__QI__))); + + typedef enum + { + _URC_OK = 0, /* operation completed successfully */ + _URC_FOREIGN_EXCEPTION_CAUGHT = 1, + _URC_END_OF_STACK = 5, + _URC_HANDLER_FOUND = 6, + _URC_INSTALL_CONTEXT = 7, + _URC_CONTINUE_UNWIND = 8, + _URC_FAILURE = 9 /* unspecified failure of some kind */ + } + _Unwind_Reason_Code; + + typedef enum + { + _US_VIRTUAL_UNWIND_FRAME = 0, + _US_UNWIND_FRAME_STARTING = 1, + _US_UNWIND_FRAME_RESUME = 2, + _US_ACTION_MASK = 3, + _US_FORCE_UNWIND = 8, + _US_END_OF_STACK = 16 + } + _Unwind_State; + + /* Provided only for compatibility with existing code. */ + typedef int _Unwind_Action; +#define _UA_SEARCH_PHASE 1 +#define _UA_CLEANUP_PHASE 2 +#define _UA_HANDLER_FRAME 4 +#define _UA_FORCE_UNWIND 8 +#define _UA_END_OF_STACK 16 +#define _URC_NO_REASON _URC_OK + + typedef struct _Unwind_Control_Block _Unwind_Control_Block; + typedef struct _Unwind_Context _Unwind_Context; + typedef _uw _Unwind_EHT_Header; + + + /* UCB: */ + + struct _Unwind_Control_Block + { + char exception_class[8]; + void (*exception_cleanup)(_Unwind_Reason_Code, _Unwind_Control_Block *); + /* Unwinder cache, private fields for the unwinder's use */ + struct + { + _uw reserved1; /* Forced unwind stop fn, 0 if not forced */ + _uw reserved2; /* Personality routine address */ + _uw reserved3; /* Saved callsite address */ + _uw reserved4; /* Forced unwind stop arg */ + _uw reserved5; + } + unwinder_cache; + /* Propagation barrier cache (valid after phase 1): */ + struct + { + _uw sp; + _uw bitpattern[5]; + } + barrier_cache; + /* Cleanup cache (preserved over cleanup): */ + struct + { + _uw bitpattern[4]; + } + cleanup_cache; + /* Pr cache (for pr's benefit): */ + struct + { + _uw fnstart; /* function start address */ + _Unwind_EHT_Header *ehtp; /* pointer to EHT entry header word */ + _uw additional; /* additional data */ + _uw reserved1; + } + pr_cache; + long long int :0; /* Force alignment to 8-byte boundary */ + }; + + /* Virtual Register Set*/ + + typedef enum + { + _UVRSC_CORE = 0, /* integer register */ + _UVRSC_VFP = 1, /* vfp */ + _UVRSC_FPA = 2, /* fpa */ + _UVRSC_WMMXD = 3, /* Intel WMMX data register */ + _UVRSC_WMMXC = 4 /* Intel WMMX control register */ + } + _Unwind_VRS_RegClass; + + typedef enum + { + _UVRSD_UINT32 = 0, + _UVRSD_VFPX = 1, + _UVRSD_FPAX = 2, + _UVRSD_UINT64 = 3, + _UVRSD_FLOAT = 4, + _UVRSD_DOUBLE = 5 + } + _Unwind_VRS_DataRepresentation; + + typedef enum + { + _UVRSR_OK = 0, + _UVRSR_NOT_IMPLEMENTED = 1, + _UVRSR_FAILED = 2 + } + _Unwind_VRS_Result; + + /* Frame unwinding state. */ + typedef struct + { + /* The current word (bytes packed msb first). */ + _uw data; + /* Pointer to the next word of data. */ + _uw *next; + /* The number of bytes left in this word. */ + _uw8 bytes_left; + /* The number of words pointed to by ptr. */ + _uw8 words_left; + } + __gnu_unwind_state; + + typedef _Unwind_Reason_Code (*personality_routine) (_Unwind_State, + _Unwind_Control_Block *, _Unwind_Context *); + + _Unwind_VRS_Result _Unwind_VRS_Set(_Unwind_Context *, _Unwind_VRS_RegClass, + _uw, _Unwind_VRS_DataRepresentation, + void *); + + _Unwind_VRS_Result _Unwind_VRS_Get(_Unwind_Context *, _Unwind_VRS_RegClass, + _uw, _Unwind_VRS_DataRepresentation, + void *); + + _Unwind_VRS_Result _Unwind_VRS_Pop(_Unwind_Context *, _Unwind_VRS_RegClass, + _uw, _Unwind_VRS_DataRepresentation); + + + /* Support functions for the PR. */ +#define _Unwind_Exception _Unwind_Control_Block + typedef char _Unwind_Exception_Class[8]; + + void * _Unwind_GetLanguageSpecificData (_Unwind_Context *); + _Unwind_Ptr _Unwind_GetRegionStart (_Unwind_Context *); + + _Unwind_Ptr _Unwind_GetDataRelBase (_Unwind_Context *); + /* This should never be used. */ + _Unwind_Ptr _Unwind_GetTextRelBase (_Unwind_Context *); + + /* Interface functions: */ + _Unwind_Reason_Code _Unwind_RaiseException(_Unwind_Control_Block *ucbp); + void __attribute__((noreturn)) _Unwind_Resume(_Unwind_Control_Block *ucbp); + _Unwind_Reason_Code _Unwind_Resume_or_Rethrow (_Unwind_Control_Block *ucbp); + + typedef _Unwind_Reason_Code (*_Unwind_Stop_Fn) + (int, _Unwind_Action, _Unwind_Exception_Class, + _Unwind_Control_Block *, struct _Unwind_Context *, void *); + _Unwind_Reason_Code _Unwind_ForcedUnwind (_Unwind_Control_Block *, + _Unwind_Stop_Fn, void *); + /* @@@ Use unwind data to perform a stack backtrace. The trace callback + is called for every stack frame in the call chain, but no cleanup + actions are performed. */ + typedef _Unwind_Reason_Code (*_Unwind_Trace_Fn) (_Unwind_Context *, void *); + _Unwind_Reason_Code _Unwind_Backtrace(_Unwind_Trace_Fn, + void*); + + _Unwind_Word _Unwind_GetCFA (struct _Unwind_Context *); + void _Unwind_Complete(_Unwind_Control_Block *ucbp); + void _Unwind_DeleteException (_Unwind_Exception *); + + _Unwind_Reason_Code __gnu_unwind_frame (_Unwind_Control_Block *, + _Unwind_Context *); + _Unwind_Reason_Code __gnu_unwind_execute (_Unwind_Context *, + __gnu_unwind_state *); + + static inline _Unwind_Word + _Unwind_GetGR (_Unwind_Context *context, int regno) + { + _uw val; + _Unwind_VRS_Get (context, _UVRSC_CORE, regno, _UVRSD_UINT32, &val); + return val; + } + +#define _Unwind_GetIPInfo(context, ip_before_insn) \ + (*ip_before_insn = 0, _Unwind_GetIP (context)) + + static inline void + _Unwind_SetGR (_Unwind_Context *context, int regno, _Unwind_Word val) + { + _Unwind_VRS_Set (context, _UVRSC_CORE, regno, _UVRSD_UINT32, &val); + } + + _Unwind_Ptr _Unwind_GetRegionStart (_Unwind_Context *); + void * _Unwind_GetLanguageSpecificData (_Unwind_Context *); + +/* leb128 type numbers have a potentially unlimited size. + The target of the following definitions of _sleb128_t and _uleb128_t + is to have efficient data types large enough to hold the leb128 type + numbers used in the unwind code. */ +typedef long _sleb128_t; +typedef unsigned long _uleb128_t; + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* defined UNWIND_ARM_COMMON_H */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/unwind.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/unwind.h new file mode 100644 index 0000000..782d175 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/unwind.h @@ -0,0 +1,85 @@ +/* Header file for the ARM EABI unwinder + Copyright (C) 2003-2014 Free Software Foundation, Inc. + Contributed by Paul Brook + + This file is free software; you can redistribute it and/or modify it + under the terms of the GNU General Public License as published by the + Free Software Foundation; either version 3, or (at your option) any + later version. + + This file is distributed in the hope that it will be useful, but + WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + General Public License for more details. + + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see + <http://www.gnu.org/licenses/>. */ + +/* Language-independent unwinder header public defines. This contains both + ABI defined objects, and GNU support routines. */ + +#ifndef UNWIND_ARM_H +#define UNWIND_ARM_H + +#include "unwind-arm-common.h" + +#define UNWIND_STACK_REG 13 +/* Use IP as a scratch register within the personality routine. */ +#define UNWIND_POINTER_REG 12 + +#ifdef __cplusplus +extern "C" { +#endif + /* Decode an R_ARM_TARGET2 relocation. */ + static inline _Unwind_Word + _Unwind_decode_typeinfo_ptr (_Unwind_Word base __attribute__ ((unused)), + _Unwind_Word ptr) + { + _Unwind_Word tmp; + + tmp = *(_Unwind_Word *) ptr; + /* Zero values are always NULL. */ + if (!tmp) + return 0; + +#if (defined(linux) && !defined(__uClinux__)) || defined(__NetBSD__) + /* Pc-relative indirect. */ +#define _GLIBCXX_OVERRIDE_TTYPE_ENCODING (DW_EH_PE_pcrel | DW_EH_PE_indirect) + tmp += ptr; + tmp = *(_Unwind_Word *) tmp; +#elif defined(__symbian__) || defined(__uClinux__) +#define _GLIBCXX_OVERRIDE_TTYPE_ENCODING (DW_EH_PE_absptr) + /* Absolute pointer. Nothing more to do. */ +#else +#define _GLIBCXX_OVERRIDE_TTYPE_ENCODING (DW_EH_PE_pcrel) + /* Pc-relative pointer. */ + tmp += ptr; +#endif + return tmp; + } + + static inline _Unwind_Reason_Code + __gnu_unwind_24bit (_Unwind_Context * context __attribute__ ((unused)), + _uw data __attribute__ ((unused)), + int compact __attribute__ ((unused))) + { + return _URC_FAILURE; + } + /* Return the address of the instruction, not the actual IP value. */ +#define _Unwind_GetIP(context) \ + (_Unwind_GetGR (context, 15) & ~(_Unwind_Word)1) + +#define _Unwind_SetIP(context, val) \ + _Unwind_SetGR (context, 15, val | (_Unwind_GetGR (context, 15) & 1)) + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* defined UNWIND_ARM_H */ diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/include/varargs.h b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/varargs.h new file mode 100644 index 0000000..4b9803e --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/include/varargs.h @@ -0,0 +1,7 @@ +#ifndef _VARARGS_H +#define _VARARGS_H + +#error "GCC no longer implements <varargs.h>." +#error "Revise your code to use <stdarg.h>." + +#endif diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/libgcc.a b/lib/gcc/arm-linux-androideabi/4.9.x-google/libgcc.a Binary files differnew file mode 100644 index 0000000..1d48aef --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/libgcc.a diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/libgcov.a b/lib/gcc/arm-linux-androideabi/4.9.x-google/libgcov.a Binary files differnew file mode 100644 index 0000000..6753695 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/libgcov.a diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/crtbegin.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/crtbegin.o Binary files differnew file mode 100644 index 0000000..7e34f33 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/crtbegin.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/crtbeginS.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/crtbeginS.o Binary files differnew file mode 100644 index 0000000..15c6854 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/crtbeginS.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/crtbeginT.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/crtbeginT.o Binary files differnew file mode 100644 index 0000000..7e34f33 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/crtbeginT.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/crtend.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/crtend.o Binary files differnew file mode 100644 index 0000000..d67f538 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/crtend.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/crtendS.o b/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/crtendS.o Binary files differnew file mode 100644 index 0000000..d67f538 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/crtendS.o diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/libgcc.a b/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/libgcc.a Binary files differnew file mode 100644 index 0000000..3e14f32 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/libgcc.a diff --git a/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/libgcov.a b/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/libgcov.a Binary files differnew file mode 100644 index 0000000..908719a --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.9.x-google/thumb/libgcov.a |