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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
|
/* 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)
/* Broadcast CHAR to YMM0. */
vmovd %esi, %xmm0
movl %edi, %eax
andl $(PAGE_SIZE - 1), %eax
VPBROADCAST %xmm0, %ymm0
vpxor %xmm9, %xmm9, %xmm9
/* Check if we cross page boundary with one vector load. */
cmpl $(PAGE_SIZE - VEC_SIZE), %eax
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(aligned_more)
tzcntl %eax, %eax
# ifndef USE_AS_STRCHRNUL
/* Found CHAR or the null byte. */
cmp (%rdi, %rax), %CHAR_REG
jne L(zero)
# endif
addq %rdi, %rax
VZEROUPPER_RETURN
/* .p2align 5 helps keep performance more consistent if ENTRY()
alignment % 32 was either 16 or 0. As well this makes the
alignment % 32 of the loop_4x_vec fixed which makes tuning it
easier. */
.p2align 5
L(first_vec_x4):
tzcntl %eax, %eax
addq $(VEC_SIZE * 3 + 1), %rdi
# ifndef USE_AS_STRCHRNUL
/* Found CHAR or the null byte. */
cmp (%rdi, %rax), %CHAR_REG
jne L(zero)
# endif
addq %rdi, %rax
VZEROUPPER_RETURN
# ifndef USE_AS_STRCHRNUL
L(zero):
xorl %eax, %eax
VZEROUPPER_RETURN
# endif
.p2align 4
L(first_vec_x1):
tzcntl %eax, %eax
incq %rdi
# ifndef USE_AS_STRCHRNUL
/* Found CHAR or the null byte. */
cmp (%rdi, %rax), %CHAR_REG
jne L(zero)
# endif
addq %rdi, %rax
VZEROUPPER_RETURN
.p2align 4
L(first_vec_x2):
tzcntl %eax, %eax
addq $(VEC_SIZE + 1), %rdi
# ifndef USE_AS_STRCHRNUL
/* Found CHAR or the null byte. */
cmp (%rdi, %rax), %CHAR_REG
jne L(zero)
# endif
addq %rdi, %rax
VZEROUPPER_RETURN
.p2align 4
L(first_vec_x3):
tzcntl %eax, %eax
addq $(VEC_SIZE * 2 + 1), %rdi
# ifndef USE_AS_STRCHRNUL
/* Found CHAR or the null byte. */
cmp (%rdi, %rax), %CHAR_REG
jne L(zero)
# endif
addq %rdi, %rax
VZEROUPPER_RETURN
.p2align 4
L(aligned_more):
/* Align data to VEC_SIZE - 1. This is the same number of
instructions as using andq -VEC_SIZE but saves 4 bytes of code
on x4 check. */
orq $(VEC_SIZE - 1), %rdi
L(cross_page_continue):
/* Check the next 4 * VEC_SIZE. Only one VEC_SIZE at a time
since data is only aligned to VEC_SIZE. */
vmovdqa 1(%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 + 1)(%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 * 2 + 1)(%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)
vmovdqa (VEC_SIZE * 3 + 1)(%rdi), %ymm8
VPCMPEQ %ymm8, %ymm0, %ymm1
VPCMPEQ %ymm8, %ymm9, %ymm2
vpor %ymm1, %ymm2, %ymm1
vpmovmskb %ymm1, %eax
testl %eax, %eax
jnz L(first_vec_x4)
/* Align data to VEC_SIZE * 4 - 1. */
addq $(VEC_SIZE * 4 + 1), %rdi
andq $-(VEC_SIZE * 4), %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
/* 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, %ymm6
VPCMPEQ %ymm6, %ymm9, %ymm6
vpmovmskb %ymm6, %ecx
subq $-(VEC_SIZE * 4), %rdi
testl %ecx, %ecx
jz L(loop_4x_vec)
VPCMPEQ %ymm1, %ymm9, %ymm1
vpmovmskb %ymm1, %eax
testl %eax, %eax
jnz L(last_vec_x0)
VPCMPEQ %ymm5, %ymm9, %ymm2
vpmovmskb %ymm2, %eax
testl %eax, %eax
jnz L(last_vec_x1)
VPCMPEQ %ymm3, %ymm9, %ymm3
vpmovmskb %ymm3, %eax
/* rcx has combined result from all 4 VEC. It will only be used
if the first 3 other VEC all did not contain a match. */
salq $32, %rcx
orq %rcx, %rax
tzcntq %rax, %rax
subq $(VEC_SIZE * 2), %rdi
# ifndef USE_AS_STRCHRNUL
/* Found CHAR or the null byte. */
cmp (%rdi, %rax), %CHAR_REG
jne L(zero_end)
# endif
addq %rdi, %rax
VZEROUPPER_RETURN
.p2align 4
L(last_vec_x0):
tzcntl %eax, %eax
addq $-(VEC_SIZE * 4), %rdi
# ifndef USE_AS_STRCHRNUL
/* Found CHAR or the null byte. */
cmp (%rdi, %rax), %CHAR_REG
jne L(zero_end)
# endif
addq %rdi, %rax
VZEROUPPER_RETURN
# ifndef USE_AS_STRCHRNUL
L(zero_end):
xorl %eax, %eax
VZEROUPPER_RETURN
# endif
.p2align 4
L(last_vec_x1):
tzcntl %eax, %eax
subq $(VEC_SIZE * 3), %rdi
# ifndef USE_AS_STRCHRNUL
/* Found CHAR or the null byte. */
cmp (%rdi, %rax), %CHAR_REG
jne L(zero_end)
# endif
addq %rdi, %rax
VZEROUPPER_RETURN
/* Cold case for crossing page with first load. */
.p2align 4
L(cross_page_boundary):
movq %rdi, %rdx
/* Align rdi to VEC_SIZE - 1. */
orq $(VEC_SIZE - 1), %rdi
vmovdqa -(VEC_SIZE - 1)(%rdi), %ymm8
VPCMPEQ %ymm8, %ymm0, %ymm1
VPCMPEQ %ymm8, %ymm9, %ymm2
vpor %ymm1, %ymm2, %ymm1
vpmovmskb %ymm1, %eax
/* Remove the leading bytes. sarxl only uses bits [5:0] of COUNT
so no need to manually mod edx. */
sarxl %edx, %eax, %eax
testl %eax, %eax
jz L(cross_page_continue)
tzcntl %eax, %eax
# ifndef USE_AS_STRCHRNUL
xorl %ecx, %ecx
/* Found CHAR or the null byte. */
cmp (%rdx, %rax), %CHAR_REG
leaq (%rdx, %rax), %rax
cmovne %rcx, %rax
# else
addq %rdx, %rax
# endif
L(return_vzeroupper):
ZERO_UPPER_VEC_REGISTERS_RETURN
END (STRCHR)
# endif
|
