You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
85 lines
1.9 KiB
85 lines
1.9 KiB
/*
|
|
* strchrnul - find a character or nul in a string
|
|
*
|
|
* Copyright (c) 2020, Arm Limited.
|
|
* SPDX-License-Identifier: MIT
|
|
*/
|
|
|
|
/* Assumptions:
|
|
*
|
|
* ARMv8-a, AArch64, Advanced SIMD.
|
|
* MTE compatible.
|
|
*/
|
|
|
|
#include "../asmdefs.h"
|
|
|
|
#define srcin x0
|
|
#define chrin w1
|
|
#define result x0
|
|
|
|
#define src x2
|
|
#define tmp1 x1
|
|
#define tmp2 x3
|
|
#define tmp2w w3
|
|
|
|
#define vrepchr v0
|
|
#define vdata v1
|
|
#define qdata q1
|
|
#define vhas_nul v2
|
|
#define vhas_chr v3
|
|
#define vrepmask v4
|
|
#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 0-3 are set if the relevant byte matched the
|
|
requested character or the byte is NUL. Bits 4-7 must be zero. Bits 4-7 are
|
|
set likewise for odd bytes 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. */
|
|
|
|
ENTRY (__strchrnul_aarch64_mte)
|
|
PTR_ARG (0)
|
|
bic src, srcin, 15
|
|
dup vrepchr.16b, chrin
|
|
ld1 {vdata.16b}, [src]
|
|
mov tmp2w, 0xf00f
|
|
dup vrepmask.8h, tmp2w
|
|
cmeq vhas_chr.16b, vdata.16b, vrepchr.16b
|
|
cmhs vhas_chr.16b, vhas_chr.16b, vdata.16b
|
|
lsl tmp2, srcin, 2
|
|
and vhas_chr.16b, vhas_chr.16b, vrepmask.16b
|
|
addp vend.16b, vhas_chr.16b, vhas_chr.16b /* 128->64 */
|
|
fmov tmp1, dend
|
|
lsr tmp1, tmp1, tmp2 /* Mask padding bits. */
|
|
cbz tmp1, L(loop)
|
|
|
|
rbit tmp1, tmp1
|
|
clz tmp1, tmp1
|
|
add result, srcin, tmp1, lsr 2
|
|
ret
|
|
|
|
.p2align 4
|
|
L(loop):
|
|
ldr qdata, [src, 16]!
|
|
cmeq vhas_chr.16b, vdata.16b, vrepchr.16b
|
|
cmhs vhas_chr.16b, vhas_chr.16b, vdata.16b
|
|
umaxp vend.16b, vhas_chr.16b, vhas_chr.16b
|
|
fmov tmp1, dend
|
|
cbz tmp1, L(loop)
|
|
|
|
and vhas_chr.16b, vhas_chr.16b, vrepmask.16b
|
|
addp vend.16b, vhas_chr.16b, vhas_chr.16b /* 128->64 */
|
|
fmov tmp1, dend
|
|
#ifndef __AARCH64EB__
|
|
rbit tmp1, tmp1
|
|
#endif
|
|
clz tmp1, tmp1
|
|
add result, src, tmp1, lsr 2
|
|
ret
|
|
|
|
END (__strchrnul_aarch64_mte)
|
|
|