diff options
| author | Wilco Dijkstra <wilco.dijkstra@arm.com> | 2022-08-22 13:21:41 +0100 |
|---|---|---|
| committer | Szabolcs Nagy <szabolcs.nagy@arm.com> | 2022-08-23 10:09:05 +0100 |
| commit | 864fc0254172a47c9ea36e12cd27511108902813 (patch) | |
| tree | ef442f72edae2a71d567aae9eba5f98a391f1ed7 /string | |
| parent | 87e99142bf8273215f58e4770fd7247e4b6e401b (diff) | |
| download | arm-optimized-routines-864fc0254172a47c9ea36e12cd27511108902813.tar.gz | |
string: Improve strchr-mte
Simplify calculation of the mask using shrn. Unroll the main loop.
Small strings are 20% faster.
Diffstat (limited to 'string')
| -rw-r--r-- | string/aarch64/strchr-mte.S | 52 |
1 files changed, 24 insertions, 28 deletions
diff --git a/string/aarch64/strchr-mte.S b/string/aarch64/strchr-mte.S index 4ed6cce..8840f0d 100644 --- a/string/aarch64/strchr-mte.S +++ b/string/aarch64/strchr-mte.S @@ -19,8 +19,7 @@ #define src x2 #define tmp1 x1 -#define wtmp2 w3 -#define tmp3 x3 +#define tmp2 x3 #define vrepchr v0 #define vdata v1 @@ -28,39 +27,30 @@ #define vhas_nul v2 #define vhas_chr v3 #define vrepmask v4 -#define vrepmask2 v5 -#define vend v6 -#define dend d6 +#define vend v5 +#define dend d5 /* Core algorithm. For each 16-byte chunk we calculate a 64-bit syndrome value with four bits - per byte. For even bytes, bits 0-1 are set if the relevant byte matched the - requested character, bits 2-3 are set if the byte is NUL (or matched), and - bits 4-7 are not used and must be zero if none of bits 0-3 are set). Odd - bytes set bits 4-7 so that adjacent bytes can be merged. Since the bits - in the syndrome reflect the order in which things occur in the original - string, counting trailing zeros identifies exactly which byte matched. */ + per byte. Bits 0-1 are set if the relevant byte matched the requested + character, bits 2-3 are set if the byte is NUL or matched. Count trailing + zeroes gives the position of the matching byte if it is a multiple of 4. + If it is not a multiple of 4, there was no match. */ ENTRY (__strchr_aarch64_mte) PTR_ARG (0) bic src, srcin, 15 dup vrepchr.16b, chrin ld1 {vdata.16b}, [src] - mov wtmp2, 0x3003 - dup vrepmask.8h, wtmp2 + movi vrepmask.16b, 0x33 cmeq vhas_nul.16b, vdata.16b, 0 cmeq vhas_chr.16b, vdata.16b, vrepchr.16b - mov wtmp2, 0xf00f - dup vrepmask2.8h, wtmp2 - bit vhas_nul.16b, vhas_chr.16b, vrepmask.16b - and vhas_nul.16b, vhas_nul.16b, vrepmask2.16b - lsl tmp3, srcin, 2 - addp vend.16b, vhas_nul.16b, vhas_nul.16b /* 128->64 */ - + lsl tmp2, srcin, 2 + shrn vend.8b, vhas_nul.8h, 4 /* 128->64 */ fmov tmp1, dend - lsr tmp1, tmp1, tmp3 + lsr tmp1, tmp1, tmp2 cbz tmp1, L(loop) rbit tmp1, tmp1 @@ -74,28 +64,34 @@ ENTRY (__strchr_aarch64_mte) .p2align 4 L(loop): - ldr qdata, [src, 16]! + ldr qdata, [src, 16] + cmeq vhas_chr.16b, vdata.16b, vrepchr.16b + cmhs vhas_nul.16b, vhas_chr.16b, vdata.16b + umaxp vend.16b, vhas_nul.16b, vhas_nul.16b + fmov tmp1, dend + cbnz tmp1, L(end) + ldr qdata, [src, 32]! cmeq vhas_chr.16b, vdata.16b, vrepchr.16b cmhs vhas_nul.16b, vhas_chr.16b, vdata.16b umaxp vend.16b, vhas_nul.16b, vhas_nul.16b fmov tmp1, dend cbz tmp1, L(loop) + sub src, src, 16 +L(end): #ifdef __AARCH64EB__ bif vhas_nul.16b, vhas_chr.16b, vrepmask.16b - and vhas_nul.16b, vhas_nul.16b, vrepmask2.16b - addp vend.16b, vhas_nul.16b, vhas_nul.16b /* 128->64 */ + shrn vend.8b, vhas_nul.8h, 4 /* 128->64 */ fmov tmp1, dend #else bit vhas_nul.16b, vhas_chr.16b, vrepmask.16b - and vhas_nul.16b, vhas_nul.16b, vrepmask2.16b - addp vend.16b, vhas_nul.16b, vhas_nul.16b /* 128->64 */ + shrn vend.8b, vhas_nul.8h, 4 /* 128->64 */ fmov tmp1, dend rbit tmp1, tmp1 #endif + add src, src, 16 clz tmp1, tmp1 - /* Tmp1 is an even multiple of 2 if the target character was - found first. Otherwise we've found the end of string. */ + /* Tmp1 is a multiple of 4 if the target character was found. */ tst tmp1, 2 add result, src, tmp1, lsr 2 csel result, result, xzr, eq |