about summary refs log tree commit diff
path: root/sysdeps/x86_64/multiarch/wcschr-sse2.S
blob: 1c83957cbc1ca6367c90864b93e891854e7723d6 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
/* wcschr optimized with SSE2.
   Copyright (C) 2017-2022 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/>.  */


#include <isa-level.h>

/* ISA level >= 2 because there is no wcschr-sse4 implementations.  */
#if ISA_SHOULD_BUILD (2)

# ifndef WCSCHR
#  define WCSCHR __wcschr_sse2
# endif

# include <sysdep.h>

	.text
ENTRY (WCSCHR)

	movd	%rsi, %xmm1
	pxor	%xmm2, %xmm2
	mov	%rdi, %rcx
	punpckldq %xmm1, %xmm1
	punpckldq %xmm1, %xmm1

	and	$63, %rcx
	cmp	$48, %rcx
	ja	L(cross_cache)

	movdqu	(%rdi), %xmm0
	pcmpeqd	%xmm0, %xmm2
	add	$16, %rdi
	pcmpeqd	%xmm1, %xmm0
	pmovmskb %xmm2, %rdx
	pmovmskb %xmm0, %rax
	or	%rax, %rdx
	jnz	L(matches)

	and	$-16, %rdi

	movdqa	(%rdi), %xmm0
	pcmpeqd	%xmm0, %xmm2
	add	$16, %rdi
	pcmpeqd	%xmm1, %xmm0
	pmovmskb %xmm2, %rdx
	pmovmskb %xmm0, %rax
	or	%rax, %rdx
	jnz	L(matches)

	jmp	L(loop)

L(cross_cache):
	and	$15, %rcx
	and	$-16, %rdi
	movdqa	(%rdi), %xmm0
	pcmpeqd	%xmm0, %xmm2
	pcmpeqd	%xmm1, %xmm0
	pmovmskb %xmm2, %rdx
	pmovmskb %xmm0, %rax

	sar	%cl, %rdx
	sar	%cl, %rax
	test	%rax, %rax
	je	L(unaligned_no_match)

	bsf	%rax, %rax
	test	%rdx, %rdx
	je	L(unaligned_match)
	bsf	%rdx, %rdx
	cmp	%rdx, %rax
	ja	L(return_null)

L(unaligned_match):
	add	%rdi, %rax
	add	%rcx, %rax
	ret

	.p2align 4
L(unaligned_no_match):
	test	%rdx, %rdx
	jne	L(return_null)
	pxor	%xmm2, %xmm2

	add	$16, %rdi

	.p2align 4
/* Loop start on aligned string.  */
L(loop):
	movdqa	(%rdi), %xmm0
	pcmpeqd	%xmm0, %xmm2
	add	$16, %rdi
	pcmpeqd	%xmm1, %xmm0
	pmovmskb %xmm2, %rdx
	pmovmskb %xmm0, %rax
	or	%rax, %rdx
	jnz	L(matches)

	movdqa	(%rdi), %xmm0
	pcmpeqd	%xmm0, %xmm2
	add	$16, %rdi
	pcmpeqd	%xmm1, %xmm0
	pmovmskb %xmm2, %rdx
	pmovmskb %xmm0, %rax
	or	%rax, %rdx
	jnz	L(matches)

	movdqa	(%rdi), %xmm0
	pcmpeqd	%xmm0, %xmm2
	add	$16, %rdi
	pcmpeqd	%xmm1, %xmm0
	pmovmskb %xmm2, %rdx
	pmovmskb %xmm0, %rax
	or	%rax, %rdx
	jnz	L(matches)

	movdqa	(%rdi), %xmm0
	pcmpeqd	%xmm0, %xmm2
	add	$16, %rdi
	pcmpeqd	%xmm1, %xmm0
	pmovmskb %xmm2, %rdx
	pmovmskb %xmm0, %rax
	or	%rax, %rdx
	jnz	L(matches)
	jmp	L(loop)

	.p2align 4
L(matches):
	pmovmskb %xmm2, %rdx
	test	%rax, %rax
	jz	L(return_null)
	bsf	%rax, %rax
	test	%rdx, %rdx
	je	L(match)
	bsf	%rdx, %rcx
	cmp	%rcx, %rax
	ja	L(return_null)
L(match):
	sub	$16, %rdi
	add	%rdi, %rax
	ret

	.p2align 4
L(return_null):
	xor	%rax, %rax
	ret

END (WCSCHR)
#endif