diff options
Diffstat (limited to 'lib/gcc/arm-linux-androideabi/4.8/include')
16 files changed, 16119 insertions, 0 deletions
diff --git a/lib/gcc/arm-linux-androideabi/4.8/include/arm_neon.h b/lib/gcc/arm-linux-androideabi/4.8/include/arm_neon.h new file mode 100644 index 0000000..4d945ce --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/include/arm_neon.h @@ -0,0 +1,12342 @@ +/* ARM NEON intrinsics include file. This file is generated automatically + using neon-gen.ml. Please do not edit manually. + + Copyright (C) 2006-2013 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_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))); +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))); +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; + +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; + +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; + +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; + + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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 }); +} + +__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); +} + +__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); +} + +__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) +vtrn_s8 (int8x8_t __a, int8x8_t __b) +{ + int8x8x2_t __rv; + __rv.val[0] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 }); + return __rv; +} + +__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) +vtrn_s16 (int16x4_t __a, int16x4_t __b) +{ + int16x4x2_t __rv; + __rv.val[0] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 }); + return __rv; +} + +__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) +vtrn_u8 (uint8x8_t __a, uint8x8_t __b) +{ + uint8x8x2_t __rv; + __rv.val[0] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 }); + return __rv; +} + +__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) +vtrn_u16 (uint16x4_t __a, uint16x4_t __b) +{ + uint16x4x2_t __rv; + __rv.val[0] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 }); + return __rv; +} + +__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) +vtrn_p8 (poly8x8_t __a, poly8x8_t __b) +{ + poly8x8x2_t __rv; + __rv.val[0] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 }); + return __rv; +} + +__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) +vtrn_p16 (poly16x4_t __a, poly16x4_t __b) +{ + poly16x4x2_t __rv; + __rv.val[0] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 }); + return __rv; +} + +__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) +vtrn_s32 (int32x2_t __a, int32x2_t __b) +{ + int32x2x2_t __rv; + __rv.val[0] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); + return __rv; +} + +__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) +vtrn_f32 (float32x2_t __a, float32x2_t __b) +{ + float32x2x2_t __rv; + __rv.val[0] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); + return __rv; +} + +__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) +vtrn_u32 (uint32x2_t __a, uint32x2_t __b) +{ + uint32x2x2_t __rv; + __rv.val[0] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); + return __rv; +} + +__extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__)) +vtrnq_s8 (int8x16_t __a, int8x16_t __b) +{ + int8x16x2_t __rv; + __rv.val[0] = (int8x16_t) __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] = (int8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 }); + return __rv; +} + +__extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) +vtrnq_s16 (int16x8_t __a, int16x8_t __b) +{ + int16x8x2_t __rv; + __rv.val[0] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 }); + return __rv; +} + +__extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) +vtrnq_s32 (int32x4_t __a, int32x4_t __b) +{ + int32x4x2_t __rv; + __rv.val[0] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 }); + return __rv; +} + +__extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) +vtrnq_f32 (float32x4_t __a, float32x4_t __b) +{ + float32x4x2_t __rv; + __rv.val[0] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 }); + return __rv; +} + +__extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__)) +vtrnq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + uint8x16x2_t __rv; + __rv.val[0] = (uint8x16_t) __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] = (uint8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 }); + return __rv; +} + +__extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) +vtrnq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + uint16x8x2_t __rv; + __rv.val[0] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 }); + return __rv; +} + +__extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) +vtrnq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + uint32x4x2_t __rv; + __rv.val[0] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 }); + return __rv; +} + +__extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__)) +vtrnq_p8 (poly8x16_t __a, poly8x16_t __b) +{ + poly8x16x2_t __rv; + __rv.val[0] = (poly8x16_t) __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] = (poly8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 }); + return __rv; +} + +__extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) +vtrnq_p16 (poly16x8_t __a, poly16x8_t __b) +{ + poly16x8x2_t __rv; + __rv.val[0] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 }); + return __rv; +} + +__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) +vzip_s8 (int8x8_t __a, int8x8_t __b) +{ + int8x8x2_t __rv; + __rv.val[0] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 }); + return __rv; +} + +__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) +vzip_s16 (int16x4_t __a, int16x4_t __b) +{ + int16x4x2_t __rv; + __rv.val[0] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 }); + return __rv; +} + +__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) +vzip_u8 (uint8x8_t __a, uint8x8_t __b) +{ + uint8x8x2_t __rv; + __rv.val[0] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 }); + return __rv; +} + +__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) +vzip_u16 (uint16x4_t __a, uint16x4_t __b) +{ + uint16x4x2_t __rv; + __rv.val[0] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 }); + return __rv; +} + +__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) +vzip_p8 (poly8x8_t __a, poly8x8_t __b) +{ + poly8x8x2_t __rv; + __rv.val[0] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 }); + return __rv; +} + +__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) +vzip_p16 (poly16x4_t __a, poly16x4_t __b) +{ + poly16x4x2_t __rv; + __rv.val[0] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 }); + return __rv; +} + +__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) +vzip_s32 (int32x2_t __a, int32x2_t __b) +{ + int32x2x2_t __rv; + __rv.val[0] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); + return __rv; +} + +__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) +vzip_f32 (float32x2_t __a, float32x2_t __b) +{ + float32x2x2_t __rv; + __rv.val[0] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); + return __rv; +} + +__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) +vzip_u32 (uint32x2_t __a, uint32x2_t __b) +{ + uint32x2x2_t __rv; + __rv.val[0] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); + return __rv; +} + +__extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__)) +vzipq_s8 (int8x16_t __a, int8x16_t __b) +{ + int8x16x2_t __rv; + __rv.val[0] = (int8x16_t) __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] = (int8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 }); + return __rv; +} + +__extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) +vzipq_s16 (int16x8_t __a, int16x8_t __b) +{ + int16x8x2_t __rv; + __rv.val[0] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 }); + return __rv; +} + +__extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) +vzipq_s32 (int32x4_t __a, int32x4_t __b) +{ + int32x4x2_t __rv; + __rv.val[0] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 }); + return __rv; +} + +__extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) +vzipq_f32 (float32x4_t __a, float32x4_t __b) +{ + float32x4x2_t __rv; + __rv.val[0] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 }); + return __rv; +} + +__extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__)) +vzipq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + uint8x16x2_t __rv; + __rv.val[0] = (uint8x16_t) __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] = (uint8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 }); + return __rv; +} + +__extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) +vzipq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + uint16x8x2_t __rv; + __rv.val[0] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 }); + return __rv; +} + +__extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) +vzipq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + uint32x4x2_t __rv; + __rv.val[0] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 }); + return __rv; +} + +__extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__)) +vzipq_p8 (poly8x16_t __a, poly8x16_t __b) +{ + poly8x16x2_t __rv; + __rv.val[0] = (poly8x16_t) __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] = (poly8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 }); + return __rv; +} + +__extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) +vzipq_p16 (poly16x8_t __a, poly16x8_t __b) +{ + poly16x8x2_t __rv; + __rv.val[0] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 }); + return __rv; +} + +__extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) +vuzp_s8 (int8x8_t __a, int8x8_t __b) +{ + int8x8x2_t __rv; + __rv.val[0] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 }); + return __rv; +} + +__extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) +vuzp_s16 (int16x4_t __a, int16x4_t __b) +{ + int16x4x2_t __rv; + __rv.val[0] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 }); + return __rv; +} + +__extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) +vuzp_s32 (int32x2_t __a, int32x2_t __b) +{ + int32x2x2_t __rv; + __rv.val[0] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); + return __rv; +} + +__extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) +vuzp_f32 (float32x2_t __a, float32x2_t __b) +{ + float32x2x2_t __rv; + __rv.val[0] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); + return __rv; +} + +__extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) +vuzp_u8 (uint8x8_t __a, uint8x8_t __b) +{ + uint8x8x2_t __rv; + __rv.val[0] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 }); + return __rv; +} + +__extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) +vuzp_u16 (uint16x4_t __a, uint16x4_t __b) +{ + uint16x4x2_t __rv; + __rv.val[0] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 }); + return __rv; +} + +__extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) +vuzp_u32 (uint32x2_t __a, uint32x2_t __b) +{ + uint32x2x2_t __rv; + __rv.val[0] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); + return __rv; +} + +__extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) +vuzp_p8 (poly8x8_t __a, poly8x8_t __b) +{ + poly8x8x2_t __rv; + __rv.val[0] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 }); + return __rv; +} + +__extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) +vuzp_p16 (poly16x4_t __a, poly16x4_t __b) +{ + poly16x4x2_t __rv; + __rv.val[0] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 }); + return __rv; +} + +__extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__)) +vuzpq_s8 (int8x16_t __a, int8x16_t __b) +{ + int8x16x2_t __rv; + __rv.val[0] = (int8x16_t) __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] = (int8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 }); + return __rv; +} + +__extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) +vuzpq_s16 (int16x8_t __a, int16x8_t __b) +{ + int16x8x2_t __rv; + __rv.val[0] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 }); + return __rv; +} + +__extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) +vuzpq_s32 (int32x4_t __a, int32x4_t __b) +{ + int32x4x2_t __rv; + __rv.val[0] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 }); + return __rv; +} + +__extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) +vuzpq_f32 (float32x4_t __a, float32x4_t __b) +{ + float32x4x2_t __rv; + __rv.val[0] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 }); + return __rv; +} + +__extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__)) +vuzpq_u8 (uint8x16_t __a, uint8x16_t __b) +{ + uint8x16x2_t __rv; + __rv.val[0] = (uint8x16_t) __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] = (uint8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 }); + return __rv; +} + +__extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) +vuzpq_u16 (uint16x8_t __a, uint16x8_t __b) +{ + uint16x8x2_t __rv; + __rv.val[0] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 }); + return __rv; +} + +__extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) +vuzpq_u32 (uint32x4_t __a, uint32x4_t __b) +{ + uint32x4x2_t __rv; + __rv.val[0] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 }); + return __rv; +} + +__extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__)) +vuzpq_p8 (poly8x16_t __a, poly8x16_t __b) +{ + poly8x16x2_t __rv; + __rv.val[0] = (poly8x16_t) __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] = (poly8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 }); + return __rv; +} + +__extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) +vuzpq_p16 (poly16x8_t __a, poly16x8_t __b) +{ + poly16x8x2_t __rv; + __rv.val[0] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 }); + return __rv; +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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); +} + +__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; +} + +__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; +} + +__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); +} + +__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; +} + +__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; +} + +__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); +} + +__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; +} + +__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; +} + +__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); +} + +__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_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_s64 (int64x1_t __a) +{ + return (poly8x8_t)__builtin_neon_vreinterpretv8qidi (__a); +} + +__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) +vreinterpret_p8_f32 (float32x2_t __a) +{ + return (poly8x8_t)__builtin_neon_vreinterpretv8qiv2sf (__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 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_p16 (poly16x4_t __a) +{ + return (poly8x8_t)__builtin_neon_vreinterpretv8qiv4hi ((int16x4_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_s64 (int64x2_t __a) +{ + return (poly8x16_t)__builtin_neon_vreinterpretv16qiv2di (__a); +} + +__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_p8_f32 (float32x4_t __a) +{ + return (poly8x16_t)__builtin_neon_vreinterpretv16qiv4sf (__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 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_p16 (poly16x8_t __a) +{ + return (poly8x16_t)__builtin_neon_vreinterpretv16qiv8hi ((int16x8_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_s64 (int64x1_t __a) +{ + return (poly16x4_t)__builtin_neon_vreinterpretv4hidi (__a); +} + +__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) +vreinterpret_p16_f32 (float32x2_t __a) +{ + return (poly16x4_t)__builtin_neon_vreinterpretv4hiv2sf (__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 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_p8 (poly8x8_t __a) +{ + return (poly16x4_t)__builtin_neon_vreinterpretv4hiv8qi ((int8x8_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_s64 (int64x2_t __a) +{ + return (poly16x8_t)__builtin_neon_vreinterpretv8hiv2di (__a); +} + +__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_p16_f32 (float32x4_t __a) +{ + return (poly16x8_t)__builtin_neon_vreinterpretv8hiv4sf (__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 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_p8 (poly8x16_t __a) +{ + return (poly16x8_t)__builtin_neon_vreinterpretv8hiv16qi ((int8x16_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_s64 (int64x1_t __a) +{ + return (float32x2_t)__builtin_neon_vreinterpretv2sfdi (__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); +} + +__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_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); +} + +__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_s64 (int64x2_t __a) +{ + return (float32x4_t)__builtin_neon_vreinterpretv4sfv2di (__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); +} + +__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_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); +} + +__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_f32 (float32x2_t __a) +{ + return (int64x1_t)__builtin_neon_vreinterpretdiv2sf (__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 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_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 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_f32 (float32x4_t __a) +{ + return (int64x2_t)__builtin_neon_vreinterpretv2div4sf (__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 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_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 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_s64 (int64x1_t __a) +{ + return (uint64x1_t)__builtin_neon_vreinterpretdidi (__a); +} + +__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) +vreinterpret_u64_f32 (float32x2_t __a) +{ + return (uint64x1_t)__builtin_neon_vreinterpretdiv2sf (__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 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 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_s64 (int64x2_t __a) +{ + return (uint64x2_t)__builtin_neon_vreinterpretv2div2di (__a); +} + +__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) +vreinterpretq_u64_f32 (float32x4_t __a) +{ + return (uint64x2_t)__builtin_neon_vreinterpretv2div4sf (__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 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 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_s64 (int64x1_t __a) +{ + return (int8x8_t)__builtin_neon_vreinterpretv8qidi (__a); +} + +__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) +vreinterpret_s8_f32 (float32x2_t __a) +{ + return (int8x8_t)__builtin_neon_vreinterpretv8qiv2sf (__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 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_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 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_s64 (int64x2_t __a) +{ + return (int8x16_t)__builtin_neon_vreinterpretv16qiv2di (__a); +} + +__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_s8_f32 (float32x4_t __a) +{ + return (int8x16_t)__builtin_neon_vreinterpretv16qiv4sf (__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 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_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 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_s64 (int64x1_t __a) +{ + return (int16x4_t)__builtin_neon_vreinterpretv4hidi (__a); +} + +__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) +vreinterpret_s16_f32 (float32x2_t __a) +{ + return (int16x4_t)__builtin_neon_vreinterpretv4hiv2sf (__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 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_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 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_s64 (int64x2_t __a) +{ + return (int16x8_t)__builtin_neon_vreinterpretv8hiv2di (__a); +} + +__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_s16_f32 (float32x4_t __a) +{ + return (int16x8_t)__builtin_neon_vreinterpretv8hiv4sf (__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 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_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 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_s64 (int64x1_t __a) +{ + return (int32x2_t)__builtin_neon_vreinterpretv2sidi (__a); +} + +__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) +vreinterpret_s32_f32 (float32x2_t __a) +{ + return (int32x2_t)__builtin_neon_vreinterpretv2siv2sf (__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 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_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 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_s64 (int64x2_t __a) +{ + return (int32x4_t)__builtin_neon_vreinterpretv4siv2di (__a); +} + +__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_s32_f32 (float32x4_t __a) +{ + return (int32x4_t)__builtin_neon_vreinterpretv4siv4sf (__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 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_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 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_s64 (int64x1_t __a) +{ + return (uint8x8_t)__builtin_neon_vreinterpretv8qidi (__a); +} + +__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) +vreinterpret_u8_f32 (float32x2_t __a) +{ + return (uint8x8_t)__builtin_neon_vreinterpretv8qiv2sf (__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 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_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 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_s64 (int64x2_t __a) +{ + return (uint8x16_t)__builtin_neon_vreinterpretv16qiv2di (__a); +} + +__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) +vreinterpretq_u8_f32 (float32x4_t __a) +{ + return (uint8x16_t)__builtin_neon_vreinterpretv16qiv4sf (__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 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_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 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_s64 (int64x1_t __a) +{ + return (uint16x4_t)__builtin_neon_vreinterpretv4hidi (__a); +} + +__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) +vreinterpret_u16_f32 (float32x2_t __a) +{ + return (uint16x4_t)__builtin_neon_vreinterpretv4hiv2sf (__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 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_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 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_s64 (int64x2_t __a) +{ + return (uint16x8_t)__builtin_neon_vreinterpretv8hiv2di (__a); +} + +__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) +vreinterpretq_u16_f32 (float32x4_t __a) +{ + return (uint16x8_t)__builtin_neon_vreinterpretv8hiv4sf (__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 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_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 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_s64 (int64x1_t __a) +{ + return (uint32x2_t)__builtin_neon_vreinterpretv2sidi (__a); +} + +__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) +vreinterpret_u32_f32 (float32x2_t __a) +{ + return (uint32x2_t)__builtin_neon_vreinterpretv2siv2sf (__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 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_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 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_s64 (int64x2_t __a) +{ + return (uint32x4_t)__builtin_neon_vreinterpretv4siv2di (__a); +} + +__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) +vreinterpretq_u32_f32 (float32x4_t __a) +{ + return (uint32x4_t)__builtin_neon_vreinterpretv4siv4sf (__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); +} + +__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_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); +} + +#ifdef __cplusplus +} +#endif +#endif +#endif diff --git a/lib/gcc/arm-linux-androideabi/4.8/include/float.h b/lib/gcc/arm-linux-androideabi/4.8/include/float.h new file mode 100644 index 0000000..dd461d7 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/include/float.h @@ -0,0 +1,277 @@ +/* Copyright (C) 2002-2013 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/4.8/include/iso646.h b/lib/gcc/arm-linux-androideabi/4.8/include/iso646.h new file mode 100644 index 0000000..36dec91 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/include/iso646.h @@ -0,0 +1,45 @@ +/* Copyright (C) 1997-2013 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/4.8/include/mmintrin.h b/lib/gcc/arm-linux-androideabi/4.8/include/mmintrin.h new file mode 100644 index 0000000..7e0360f --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/include/mmintrin.h @@ -0,0 +1,1836 @@ +/* Copyright (C) 2002-2013 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/4.8/include/omp.h b/lib/gcc/arm-linux-androideabi/4.8/include/omp.h new file mode 100644 index 0000000..11ab7b8 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/include/omp.h @@ -0,0 +1,107 @@ +/* Copyright (C) 2005-2013 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; + +#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; + +void omp_set_schedule (omp_sched_t, int) __GOMP_NOTHROW; +void omp_get_schedule (omp_sched_t *, int *) __GOMP_NOTHROW; +int omp_get_thread_limit (void) __GOMP_NOTHROW; +void omp_set_max_active_levels (int) __GOMP_NOTHROW; +int omp_get_max_active_levels (void) __GOMP_NOTHROW; +int omp_get_level (void) __GOMP_NOTHROW; +int omp_get_ancestor_thread_num (int) __GOMP_NOTHROW; +int omp_get_team_size (int) __GOMP_NOTHROW; +int omp_get_active_level (void) __GOMP_NOTHROW; + +int omp_in_final (void) __GOMP_NOTHROW; + +#ifdef __cplusplus +} +#endif + +#endif /* OMP_H */ diff --git a/lib/gcc/arm-linux-androideabi/4.8/include/stdalign.h b/lib/gcc/arm-linux-androideabi/4.8/include/stdalign.h new file mode 100644 index 0000000..fe545dd --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/include/stdalign.h @@ -0,0 +1,39 @@ +/* Copyright (C) 2011-2013 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/4.8/include/stdarg.h b/lib/gcc/arm-linux-androideabi/4.8/include/stdarg.h new file mode 100644 index 0000000..fb4e0d6 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/include/stdarg.h @@ -0,0 +1,126 @@ +/* Copyright (C) 1989-2013 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/4.8/include/stdbool.h b/lib/gcc/arm-linux-androideabi/4.8/include/stdbool.h new file mode 100644 index 0000000..7146e63 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/include/stdbool.h @@ -0,0 +1,50 @@ +/* Copyright (C) 1998-2013 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/4.8/include/stddef.h b/lib/gcc/arm-linux-androideabi/4.8/include/stddef.h new file mode 100644 index 0000000..b04dd65 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/include/stddef.h @@ -0,0 +1,439 @@ +/* Copyright (C) 1989-2013 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/4.8/include/stdfix.h b/lib/gcc/arm-linux-androideabi/4.8/include/stdfix.h new file mode 100644 index 0000000..fdcef1e --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/include/stdfix.h @@ -0,0 +1,204 @@ +/* Copyright (C) 2007-2013 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/4.8/include/stdint-gcc.h b/lib/gcc/arm-linux-androideabi/4.8/include/stdint-gcc.h new file mode 100644 index 0000000..97339e2 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/include/stdint-gcc.h @@ -0,0 +1,263 @@ +/* Copyright (C) 2008-2013 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/4.8/include/stdint.h b/lib/gcc/arm-linux-androideabi/4.8/include/stdint.h new file mode 100644 index 0000000..83b6f70 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/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/4.8/include/stdnoreturn.h b/lib/gcc/arm-linux-androideabi/4.8/include/stdnoreturn.h new file mode 100644 index 0000000..ce4bec9 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/include/stdnoreturn.h @@ -0,0 +1,35 @@ +/* Copyright (C) 2011-2013 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/4.8/include/unwind-arm-common.h b/lib/gcc/arm-linux-androideabi/4.8/include/unwind-arm-common.h new file mode 100644 index 0000000..9db8af4 --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/include/unwind-arm-common.h @@ -0,0 +1,250 @@ +/* Header file for the ARM EABI and C6X unwinders + Copyright (C) 2003-2013 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/4.8/include/unwind.h b/lib/gcc/arm-linux-androideabi/4.8/include/unwind.h new file mode 100644 index 0000000..8668eda --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/include/unwind.h @@ -0,0 +1,85 @@ +/* Header file for the ARM EABI unwinder + Copyright (C) 2003-2013 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/4.8/include/varargs.h b/lib/gcc/arm-linux-androideabi/4.8/include/varargs.h new file mode 100644 index 0000000..4b9803e --- /dev/null +++ b/lib/gcc/arm-linux-androideabi/4.8/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 |