/* strchr/strchrnul optimized with AVX2.
   Copyright (C) 2017-2019 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 CHAR_REG	esi
# else
#  define VPBROADCAST	vpbroadcastb
#  define VPCMPEQ	vpcmpeqb
#  define CHAR_REG	sil
# endif

# ifndef VZEROUPPER
#  define VZEROUPPER	vzeroupper
# endif

# define VEC_SIZE 32

	.section .text.avx,"ax",@progbits
ENTRY (STRCHR)
	movl	%edi, %ecx
	/* Broadcast CHAR to YMM0.  */
	vmovd	%esi, %xmm0
	vpxor	%xmm9, %xmm9, %xmm9
	VPBROADCAST %xmm0, %ymm0
	/* Check if we may cross page boundary with one vector load.  */
	andl	$(2 * VEC_SIZE - 1), %ecx
	cmpl	$VEC_SIZE, %ecx
	ja	L(cros_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
	jnz	L(first_vec_x0)

	/* Align data for aligned loads in the loop.  */
	addq	$VEC_SIZE, %rdi
	andl	$(VEC_SIZE - 1), %ecx
	andq	$-VEC_SIZE, %rdi

	jmp	L(more_4x_vec)

	.p2align 4
L(cros_page_boundary):
	andl	$(VEC_SIZE - 1), %ecx
	andq	$-VEC_SIZE, %rdi
	vmovdqu	(%rdi), %ymm8
	VPCMPEQ %ymm8, %ymm0, %ymm1
	VPCMPEQ %ymm8, %ymm9, %ymm2
	vpor	%ymm1, %ymm2, %ymm1
	vpmovmskb %ymm1, %eax
	/* Remove the leading bytes.  */
	sarl	%cl, %eax
	testl	%eax, %eax
	jz	L(aligned_more)
	/* Found CHAR or the null byte.  */
	tzcntl	%eax, %eax
	addq	%rcx, %rax
# ifdef USE_AS_STRCHRNUL
	addq	%rdi, %rax
# else
	xorl	%edx, %edx
	leaq	(%rdi, %rax), %rax
	cmp	(%rax), %CHAR_REG
	cmovne	%rdx, %rax
# endif
	VZEROUPPER
	ret

	.p2align 4
L(aligned_more):
	addq	$VEC_SIZE, %rdi

L(more_4x_vec):
	/* Check the first 4 * VEC_SIZE.  Only one VEC_SIZE at a time
	   since data is only aligned to VEC_SIZE.  */
	vmovdqa	(%rdi), %ymm8
	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
	jnz	L(first_vec_x3)

	addq	$(VEC_SIZE * 4), %rdi

	/* Align data to 4 * VEC_SIZE.  */
	movq	%rdi, %rcx
	andl	$(4 * VEC_SIZE - 1), %ecx
	andq	$-(4 * VEC_SIZE), %rdi

	.p2align 4
L(loop_4x_vec):
	/* Compare 4 * VEC at a time forward.  */
	vmovdqa	(%rdi), %ymm5
	vmovdqa	VEC_SIZE(%rdi), %ymm6
	vmovdqa	(VEC_SIZE * 2)(%rdi), %ymm7
	vmovdqa	(VEC_SIZE * 3)(%rdi), %ymm8

	VPCMPEQ %ymm5, %ymm0, %ymm1
	VPCMPEQ %ymm6, %ymm0, %ymm2
	VPCMPEQ %ymm7, %ymm0, %ymm3
	VPCMPEQ %ymm8, %ymm0, %ymm4

	VPCMPEQ %ymm5, %ymm9, %ymm5
	VPCMPEQ %ymm6, %ymm9, %ymm6
	VPCMPEQ %ymm7, %ymm9, %ymm7
	VPCMPEQ %ymm8, %ymm9, %ymm8

	vpor	%ymm1, %ymm5, %ymm1
	vpor	%ymm2, %ymm6, %ymm2
	vpor	%ymm3, %ymm7, %ymm3
	vpor	%ymm4, %ymm8, %ymm4

	vpor	%ymm1, %ymm2, %ymm5
	vpor	%ymm3, %ymm4, %ymm6

	vpor	%ymm5, %ymm6, %ymm5

	vpmovmskb %ymm5, %eax
	testl	%eax, %eax
	jnz	L(4x_vec_end)

	addq	$(VEC_SIZE * 4), %rdi

	jmp	L(loop_4x_vec)

	.p2align 4
L(first_vec_x0):
	/* Found CHAR or the null byte.  */
	tzcntl	%eax, %eax
# ifdef USE_AS_STRCHRNUL
	addq	%rdi, %rax
# else
	xorl	%edx, %edx
	leaq	(%rdi, %rax), %rax
	cmp	(%rax), %CHAR_REG
	cmovne	%rdx, %rax
# endif
	VZEROUPPER
	ret

	.p2align 4
L(first_vec_x1):
	tzcntl	%eax, %eax
# ifdef USE_AS_STRCHRNUL
	addq	$VEC_SIZE, %rax
	addq	%rdi, %rax
# else
	xorl	%edx, %edx
	leaq	VEC_SIZE(%rdi, %rax), %rax
	cmp	(%rax), %CHAR_REG
	cmovne	%rdx, %rax
# endif
	VZEROUPPER
	ret

	.p2align 4
L(first_vec_x2):
	tzcntl	%eax, %eax
# ifdef USE_AS_STRCHRNUL
	addq	$(VEC_SIZE * 2), %rax
	addq	%rdi, %rax
# else
	xorl	%edx, %edx
	leaq	(VEC_SIZE * 2)(%rdi, %rax), %rax
	cmp	(%rax), %CHAR_REG
	cmovne	%rdx, %rax
# endif
	VZEROUPPER
	ret

	.p2align 4
L(4x_vec_end):
	vpmovmskb %ymm1, %eax
	testl	%eax, %eax
	jnz	L(first_vec_x0)
	vpmovmskb %ymm2, %eax
	testl	%eax, %eax
	jnz	L(first_vec_x1)
	vpmovmskb %ymm3, %eax
	testl	%eax, %eax
	jnz	L(first_vec_x2)
	vpmovmskb %ymm4, %eax
	testl	%eax, %eax
L(first_vec_x3):
	tzcntl	%eax, %eax
# ifdef USE_AS_STRCHRNUL
	addq	$(VEC_SIZE * 3), %rax
	addq	%rdi, %rax
# else
	xorl	%edx, %edx
	leaq	(VEC_SIZE * 3)(%rdi, %rax), %rax
	cmp	(%rax), %CHAR_REG
	cmovne	%rdx, %rax
# endif
	VZEROUPPER
	ret

END (STRCHR)
#endif