glibc/sysdeps/x86_64/multiarch/strchr-avx2.S
H.J. Lu 7ebba91361 x86-64: Add AVX optimized string/memory functions for RTM
Since VZEROUPPER triggers RTM abort while VZEROALL won't, select AVX
optimized string/memory functions with

	xtest
	jz	1f
	vzeroall
	ret
1:
	vzeroupper
	ret

at function exit on processors with usable RTM, but without 256-bit EVEX
instructions to avoid VZEROUPPER inside a transactionally executing RTM
region.
2021-03-29 07:40:17 -07:00

252 lines
5.6 KiB
ArmAsm

/* strchr/strchrnul optimized with AVX2.
Copyright (C) 2017-2021 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library; if not, see
<https://www.gnu.org/licenses/>. */
#if IS_IN (libc)
# include <sysdep.h>
# ifndef STRCHR
# define STRCHR __strchr_avx2
# endif
# ifdef USE_AS_WCSCHR
# define VPBROADCAST vpbroadcastd
# define VPCMPEQ vpcmpeqd
# define VPMINU vpminud
# define CHAR_REG esi
# else
# define VPBROADCAST vpbroadcastb
# define VPCMPEQ vpcmpeqb
# define VPMINU vpminub
# define CHAR_REG sil
# endif
# ifndef VZEROUPPER
# define VZEROUPPER vzeroupper
# endif
# ifndef SECTION
# define SECTION(p) p##.avx
# endif
# define VEC_SIZE 32
# define PAGE_SIZE 4096
.section SECTION(.text),"ax",@progbits
ENTRY (STRCHR)
movl %edi, %ecx
# ifndef USE_AS_STRCHRNUL
xorl %edx, %edx
# endif
/* Broadcast CHAR to YMM0. */
vmovd %esi, %xmm0
vpxor %xmm9, %xmm9, %xmm9
VPBROADCAST %xmm0, %ymm0
/* Check if we cross page boundary with one vector load. */
andl $(PAGE_SIZE - 1), %ecx
cmpl $(PAGE_SIZE - VEC_SIZE), %ecx
ja L(cross_page_boundary)
/* Check the first VEC_SIZE bytes. Search for both CHAR and the
null byte. */
vmovdqu (%rdi), %ymm8
VPCMPEQ %ymm8, %ymm0, %ymm1
VPCMPEQ %ymm8, %ymm9, %ymm2
vpor %ymm1, %ymm2, %ymm1
vpmovmskb %ymm1, %eax
testl %eax, %eax
jz L(more_vecs)
tzcntl %eax, %eax
/* Found CHAR or the null byte. */
addq %rdi, %rax
# ifndef USE_AS_STRCHRNUL
cmp (%rax), %CHAR_REG
cmovne %rdx, %rax
# endif
L(return_vzeroupper):
ZERO_UPPER_VEC_REGISTERS_RETURN
.p2align 4
L(more_vecs):
/* Align data for aligned loads in the loop. */
andq $-VEC_SIZE, %rdi
L(aligned_more):
/* Check the next 4 * VEC_SIZE. Only one VEC_SIZE at a time
since data is only aligned to VEC_SIZE. */
vmovdqa VEC_SIZE(%rdi), %ymm8
addq $VEC_SIZE, %rdi
VPCMPEQ %ymm8, %ymm0, %ymm1
VPCMPEQ %ymm8, %ymm9, %ymm2
vpor %ymm1, %ymm2, %ymm1
vpmovmskb %ymm1, %eax
testl %eax, %eax
jnz L(first_vec_x0)
vmovdqa VEC_SIZE(%rdi), %ymm8
VPCMPEQ %ymm8, %ymm0, %ymm1
VPCMPEQ %ymm8, %ymm9, %ymm2
vpor %ymm1, %ymm2, %ymm1
vpmovmskb %ymm1, %eax
testl %eax, %eax
jnz L(first_vec_x1)
vmovdqa (VEC_SIZE * 2)(%rdi), %ymm8
VPCMPEQ %ymm8, %ymm0, %ymm1
VPCMPEQ %ymm8, %ymm9, %ymm2
vpor %ymm1, %ymm2, %ymm1
vpmovmskb %ymm1, %eax
testl %eax, %eax
jnz L(first_vec_x2)
vmovdqa (VEC_SIZE * 3)(%rdi), %ymm8
VPCMPEQ %ymm8, %ymm0, %ymm1
VPCMPEQ %ymm8, %ymm9, %ymm2
vpor %ymm1, %ymm2, %ymm1
vpmovmskb %ymm1, %eax
testl %eax, %eax
jz L(prep_loop_4x)
tzcntl %eax, %eax
leaq (VEC_SIZE * 3)(%rdi, %rax), %rax
# ifndef USE_AS_STRCHRNUL
cmp (%rax), %CHAR_REG
cmovne %rdx, %rax
# endif
VZEROUPPER_RETURN
.p2align 4
L(first_vec_x0):
tzcntl %eax, %eax
/* Found CHAR or the null byte. */
addq %rdi, %rax
# ifndef USE_AS_STRCHRNUL
cmp (%rax), %CHAR_REG
cmovne %rdx, %rax
# endif
VZEROUPPER_RETURN
.p2align 4
L(first_vec_x1):
tzcntl %eax, %eax
leaq VEC_SIZE(%rdi, %rax), %rax
# ifndef USE_AS_STRCHRNUL
cmp (%rax), %CHAR_REG
cmovne %rdx, %rax
# endif
VZEROUPPER_RETURN
.p2align 4
L(first_vec_x2):
tzcntl %eax, %eax
/* Found CHAR or the null byte. */
leaq (VEC_SIZE * 2)(%rdi, %rax), %rax
# ifndef USE_AS_STRCHRNUL
cmp (%rax), %CHAR_REG
cmovne %rdx, %rax
# endif
VZEROUPPER_RETURN
L(prep_loop_4x):
/* Align data to 4 * VEC_SIZE. */
andq $-(VEC_SIZE * 4), %rdi
.p2align 4
L(loop_4x_vec):
/* Compare 4 * VEC at a time forward. */
vmovdqa (VEC_SIZE * 4)(%rdi), %ymm5
vmovdqa (VEC_SIZE * 5)(%rdi), %ymm6
vmovdqa (VEC_SIZE * 6)(%rdi), %ymm7
vmovdqa (VEC_SIZE * 7)(%rdi), %ymm8
/* Leaves only CHARS matching esi as 0. */
vpxor %ymm5, %ymm0, %ymm1
vpxor %ymm6, %ymm0, %ymm2
vpxor %ymm7, %ymm0, %ymm3
vpxor %ymm8, %ymm0, %ymm4
VPMINU %ymm1, %ymm5, %ymm1
VPMINU %ymm2, %ymm6, %ymm2
VPMINU %ymm3, %ymm7, %ymm3
VPMINU %ymm4, %ymm8, %ymm4
VPMINU %ymm1, %ymm2, %ymm5
VPMINU %ymm3, %ymm4, %ymm6
VPMINU %ymm5, %ymm6, %ymm5
VPCMPEQ %ymm5, %ymm9, %ymm5
vpmovmskb %ymm5, %eax
addq $(VEC_SIZE * 4), %rdi
testl %eax, %eax
jz L(loop_4x_vec)
VPCMPEQ %ymm1, %ymm9, %ymm1
vpmovmskb %ymm1, %eax
testl %eax, %eax
jnz L(first_vec_x0)
VPCMPEQ %ymm2, %ymm9, %ymm2
vpmovmskb %ymm2, %eax
testl %eax, %eax
jnz L(first_vec_x1)
VPCMPEQ %ymm3, %ymm9, %ymm3
VPCMPEQ %ymm4, %ymm9, %ymm4
vpmovmskb %ymm3, %ecx
vpmovmskb %ymm4, %eax
salq $32, %rax
orq %rcx, %rax
tzcntq %rax, %rax
leaq (VEC_SIZE * 2)(%rdi, %rax), %rax
# ifndef USE_AS_STRCHRNUL
cmp (%rax), %CHAR_REG
cmovne %rdx, %rax
# endif
VZEROUPPER_RETURN
/* Cold case for crossing page with first load. */
.p2align 4
L(cross_page_boundary):
andq $-VEC_SIZE, %rdi
andl $(VEC_SIZE - 1), %ecx
vmovdqa (%rdi), %ymm8
VPCMPEQ %ymm8, %ymm0, %ymm1
VPCMPEQ %ymm8, %ymm9, %ymm2
vpor %ymm1, %ymm2, %ymm1
vpmovmskb %ymm1, %eax
/* Remove the leading bits. */
sarxl %ecx, %eax, %eax
testl %eax, %eax
jz L(aligned_more)
tzcntl %eax, %eax
addq %rcx, %rdi
addq %rdi, %rax
# ifndef USE_AS_STRCHRNUL
cmp (%rax), %CHAR_REG
cmovne %rdx, %rax
# endif
VZEROUPPER_RETURN
END (STRCHR)
# endif