forked from OSchip/llvm-project
149 lines
4.8 KiB
ArmAsm
149 lines
4.8 KiB
ArmAsm
/*
|
|
* strrchr - find last position of a character in a string.
|
|
*
|
|
* Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
* See https://llvm.org/LICENSE.txt for license information.
|
|
* SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
*/
|
|
|
|
/* Assumptions:
|
|
*
|
|
* ARMv8-a, AArch64
|
|
* Neon Available.
|
|
*/
|
|
|
|
#include "../asmdefs.h"
|
|
|
|
/* Arguments and results. */
|
|
#define srcin x0
|
|
#define chrin w1
|
|
|
|
#define result x0
|
|
|
|
#define src x2
|
|
#define tmp1 x3
|
|
#define wtmp2 w4
|
|
#define tmp3 x5
|
|
#define src_match x6
|
|
#define src_offset x7
|
|
#define const_m1 x8
|
|
#define tmp4 x9
|
|
#define nul_match x10
|
|
#define chr_match x11
|
|
|
|
#define vrepchr v0
|
|
#define vdata1 v1
|
|
#define vdata2 v2
|
|
#define vhas_nul1 v3
|
|
#define vhas_nul2 v4
|
|
#define vhas_chr1 v5
|
|
#define vhas_chr2 v6
|
|
#define vrepmask_0 v7
|
|
#define vrepmask_c v16
|
|
#define vend1 v17
|
|
#define vend2 v18
|
|
|
|
/* Core algorithm.
|
|
|
|
For each 32-byte hunk we calculate a 64-bit syndrome value, with
|
|
two bits per byte (LSB is always in bits 0 and 1, for both big
|
|
and little-endian systems). For each tuple, bit 0 is set iff
|
|
the relevant byte matched the requested character; bit 1 is set
|
|
iff the relevant byte matched the NUL end of string (we trigger
|
|
off bit0 for the special case of looking for NUL). Since the bits
|
|
in the syndrome reflect exactly the order in which things occur
|
|
in the original string a count_trailing_zeros() operation will
|
|
identify exactly which byte is causing the termination, and why. */
|
|
|
|
ENTRY (__strrchr_aarch64)
|
|
/* Magic constant 0x40100401 to allow us to identify which lane
|
|
matches the requested byte. Magic constant 0x80200802 used
|
|
similarly for NUL termination. */
|
|
mov wtmp2, #0x0401
|
|
movk wtmp2, #0x4010, lsl #16
|
|
dup vrepchr.16b, chrin
|
|
bic src, srcin, #31 /* Work with aligned 32-byte hunks. */
|
|
dup vrepmask_c.4s, wtmp2
|
|
mov src_offset, #0
|
|
ands tmp1, srcin, #31
|
|
add vrepmask_0.4s, vrepmask_c.4s, vrepmask_c.4s /* equiv: lsl #1 */
|
|
b.eq L(aligned)
|
|
|
|
/* Input string is not 32-byte aligned. Rather than forcing
|
|
the padding bytes to a safe value, we calculate the syndrome
|
|
for all the bytes, but then mask off those bits of the
|
|
syndrome that are related to the padding. */
|
|
ld1 {vdata1.16b, vdata2.16b}, [src], #32
|
|
neg tmp1, tmp1
|
|
cmeq vhas_nul1.16b, vdata1.16b, #0
|
|
cmeq vhas_chr1.16b, vdata1.16b, vrepchr.16b
|
|
cmeq vhas_nul2.16b, vdata2.16b, #0
|
|
cmeq vhas_chr2.16b, vdata2.16b, vrepchr.16b
|
|
and vhas_nul1.16b, vhas_nul1.16b, vrepmask_0.16b
|
|
and vhas_chr1.16b, vhas_chr1.16b, vrepmask_c.16b
|
|
and vhas_nul2.16b, vhas_nul2.16b, vrepmask_0.16b
|
|
and vhas_chr2.16b, vhas_chr2.16b, vrepmask_c.16b
|
|
addp vhas_nul1.16b, vhas_nul1.16b, vhas_nul2.16b // 256->128
|
|
addp vhas_chr1.16b, vhas_chr1.16b, vhas_chr2.16b // 256->128
|
|
addp vhas_nul1.16b, vhas_nul1.16b, vhas_nul1.16b // 128->64
|
|
addp vhas_chr1.16b, vhas_chr1.16b, vhas_chr1.16b // 128->64
|
|
mov nul_match, vhas_nul1.d[0]
|
|
lsl tmp1, tmp1, #1
|
|
mov const_m1, #~0
|
|
mov chr_match, vhas_chr1.d[0]
|
|
lsr tmp3, const_m1, tmp1
|
|
|
|
bic nul_match, nul_match, tmp3 // Mask padding bits.
|
|
bic chr_match, chr_match, tmp3 // Mask padding bits.
|
|
cbnz nul_match, L(tail)
|
|
|
|
L(loop):
|
|
cmp chr_match, #0
|
|
csel src_match, src, src_match, ne
|
|
csel src_offset, chr_match, src_offset, ne
|
|
L(aligned):
|
|
ld1 {vdata1.16b, vdata2.16b}, [src], #32
|
|
cmeq vhas_nul1.16b, vdata1.16b, #0
|
|
cmeq vhas_chr1.16b, vdata1.16b, vrepchr.16b
|
|
cmeq vhas_nul2.16b, vdata2.16b, #0
|
|
cmeq vhas_chr2.16b, vdata2.16b, vrepchr.16b
|
|
addp vend1.16b, vhas_nul1.16b, vhas_nul2.16b // 256->128
|
|
and vhas_chr1.16b, vhas_chr1.16b, vrepmask_c.16b
|
|
and vhas_chr2.16b, vhas_chr2.16b, vrepmask_c.16b
|
|
addp vhas_chr1.16b, vhas_chr1.16b, vhas_chr2.16b // 256->128
|
|
addp vend1.16b, vend1.16b, vend1.16b // 128->64
|
|
addp vhas_chr1.16b, vhas_chr1.16b, vhas_chr1.16b // 128->64
|
|
mov nul_match, vend1.d[0]
|
|
mov chr_match, vhas_chr1.d[0]
|
|
cbz nul_match, L(loop)
|
|
|
|
and vhas_nul1.16b, vhas_nul1.16b, vrepmask_0.16b
|
|
and vhas_nul2.16b, vhas_nul2.16b, vrepmask_0.16b
|
|
addp vhas_nul1.16b, vhas_nul1.16b, vhas_nul2.16b
|
|
addp vhas_nul1.16b, vhas_nul1.16b, vhas_nul1.16b
|
|
mov nul_match, vhas_nul1.d[0]
|
|
|
|
L(tail):
|
|
/* Work out exactly where the string ends. */
|
|
sub tmp4, nul_match, #1
|
|
eor tmp4, tmp4, nul_match
|
|
ands chr_match, chr_match, tmp4
|
|
/* And pick the values corresponding to the last match. */
|
|
csel src_match, src, src_match, ne
|
|
csel src_offset, chr_match, src_offset, ne
|
|
|
|
/* Count down from the top of the syndrome to find the last match. */
|
|
clz tmp3, src_offset
|
|
/* Src_match points beyond the word containing the match, so we can
|
|
simply subtract half the bit-offset into the syndrome. Because
|
|
we are counting down, we need to go back one more character. */
|
|
add tmp3, tmp3, #2
|
|
sub result, src_match, tmp3, lsr #1
|
|
/* But if the syndrome shows no match was found, then return NULL. */
|
|
cmp src_offset, #0
|
|
csel result, result, xzr, ne
|
|
|
|
ret
|
|
|
|
END (__strrchr_aarch64)
|