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
|
/* memset/bzero with unaligned store and rep stosb
Copyright (C) 2016 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
<http://www.gnu.org/licenses/>. */
/* memset is implemented as:
1. Use overlapping store to avoid branch.
2. Force 32-bit displacement for branches to avoid long nop between
instructions.
3. If size is less than VEC, use integer register stores.
4. If size is from VEC_SIZE to 2 * VEC_SIZE, use 2 VEC stores.
5. If size is from 2 * VEC_SIZE to 4 * VEC_SIZE, use 4 VEC stores.
6. If size is more to 4 * VEC_SIZE, align to 4 * VEC_SIZE with
4 VEC stores and store 4 * VEC at a time until done. */
#include <sysdep.h>
#ifndef VZEROUPPER
# if VEC_SIZE > 16
# define VZEROUPPER vzeroupper
# else
# define VZEROUPPER
# endif
#endif
#ifndef VZEROUPPER_SHORT_RETURN
# if VEC_SIZE > 16
# define VZEROUPPER_SHORT_RETURN vzeroupper
# else
# define VZEROUPPER_SHORT_RETURN rep
# endif
#endif
#ifndef MOVQ
# if VEC_SIZE > 16
# define MOVQ vmovq
# else
# define MOVQ movq
# endif
#endif
/* Threshold to use Enhanced REP STOSB. Since there is overhead to set
up REP STOSB operation, REP STOSB isn't faster on short data. The
memset micro benchmark in glibc shows that 2KB is the approximate
value above which REP STOSB becomes faster on processors with
Enhanced REP STOSB. Since the stored value is fixed, larger register
size has minimal impact on threshold. */
#ifndef REP_STOSB_THRESHOLD
# define REP_STOSB_THRESHOLD 2048
#endif
#ifndef SECTION
# error SECTION is not defined!
#endif
#if !defined USE_MULTIARCH && IS_IN (libc)
.section SECTION(.text),"ax",@progbits
ENTRY (__bzero)
movq %rdi, %rax /* Set return value. */
movq %rsi, %rdx /* Set n. */
pxor %xmm0, %xmm0
jmp L(entry_from_bzero)
END (__bzero)
weak_alias (__bzero, bzero)
#endif
#if defined SHARED && IS_IN (libc)
ENTRY_CHK (MEMSET_SYMBOL (__memset_chk, unaligned))
cmpq %rdx, %rcx
jb HIDDEN_JUMPTARGET (__chk_fail)
END_CHK (MEMSET_SYMBOL (__memset_chk, unaligned))
#endif
ENTRY (MEMSET_SYMBOL (__memset, unaligned))
L(memset_entry):
VDUP_TO_VEC0_AND_SET_RETURN (%esi, %rdi)
L(entry_from_bzero):
cmpq $VEC_SIZE, %rdx
jb L(less_vec)
cmpq $(VEC_SIZE * 2), %rdx
ja L(more_2x_vec)
/* From VEC and to 2 * VEC. No branch when size == VEC_SIZE. */
VMOVU %VEC(0), -VEC_SIZE(%rdi,%rdx)
VMOVU %VEC(0), (%rdi)
VZEROUPPER
ret
END (MEMSET_SYMBOL (__memset, unaligned))
#if VEC_SIZE == 16
/* Only used to measure performance of REP STOSB. */
ENTRY (__memset_erms)
#else
/* Provide a symbol to debugger. */
ENTRY (MEMSET_SYMBOL (__memset, erms))
#endif
L(stosb):
movq %rdx, %rcx
movzbl %sil, %eax
movq %rdi, %rdx
rep stosb
movq %rdx, %rax
ret
#if VEC_SIZE == 16
END (__memset_erms)
#else
END (MEMSET_SYMBOL (__memset, erms))
#endif
#if defined SHARED && IS_IN (libc)
ENTRY_CHK (MEMSET_SYMBOL (__memset_chk, unaligned_erms))
cmpq %rdx, %rcx
jb HIDDEN_JUMPTARGET (__chk_fail)
END_CHK (MEMSET_SYMBOL (__memset_chk, unaligned_erms))
#endif
ENTRY (MEMSET_SYMBOL (__memset, unaligned_erms))
VDUP_TO_VEC0_AND_SET_RETURN (%esi, %rdi)
cmpq $VEC_SIZE, %rdx
jb L(less_vec)
cmpq $(VEC_SIZE * 2), %rdx
ja L(stosb_more_2x_vec)
/* From VEC and to 2 * VEC. No branch when size == VEC_SIZE. */
VMOVU %VEC(0), -VEC_SIZE(%rdi,%rdx)
VMOVU %VEC(0), (%rdi)
VZEROUPPER
ret
.p2align 4
L(stosb_more_2x_vec):
cmpq $REP_STOSB_THRESHOLD, %rdx
/* Force 32-bit displacement to avoid long nop between
instructions. */
ja.d32 L(stosb)
.p2align 4
L(more_2x_vec):
cmpq $(VEC_SIZE * 4), %rdx
ja L(loop_start)
VMOVU %VEC(0), (%rdi)
VMOVU %VEC(0), VEC_SIZE(%rdi)
VMOVU %VEC(0), -VEC_SIZE(%rdi,%rdx)
VMOVU %VEC(0), -(VEC_SIZE * 2)(%rdi,%rdx)
L(return):
VZEROUPPER
ret
.p2align 4
L(loop_start):
leaq (VEC_SIZE * 4)(%rdi), %rcx
# if VEC_SIZE == 32 || VEC_SIZE == 64
/* Force 32-bit displacement to avoid long nop between
instructions. */
VMOVU.d32 %VEC(0), (%rdi)
# else
VMOVU %VEC(0), (%rdi)
# endif
andq $-(VEC_SIZE * 4), %rcx
# if VEC_SIZE == 32
/* Force 32-bit displacement to avoid long nop between
instructions. */
VMOVU.d32 %VEC(0), -VEC_SIZE(%rdi,%rdx)
VMOVU.d32 %VEC(0), VEC_SIZE(%rdi)
# else
VMOVU %VEC(0), -VEC_SIZE(%rdi,%rdx)
VMOVU %VEC(0), VEC_SIZE(%rdi)
# endif
VMOVU %VEC(0), -(VEC_SIZE * 2)(%rdi,%rdx)
VMOVU %VEC(0), (VEC_SIZE * 2)(%rdi)
VMOVU %VEC(0), -(VEC_SIZE * 3)(%rdi,%rdx)
VMOVU %VEC(0), (VEC_SIZE * 3)(%rdi)
VMOVU %VEC(0), -(VEC_SIZE * 4)(%rdi,%rdx)
addq %rdi, %rdx
andq $-(VEC_SIZE * 4), %rdx
cmpq %rdx, %rcx
# if VEC_SIZE == 32 || VEC_SIZE == 64
/* Force 32-bit displacement to avoid long nop between
instructions. */
je.d32 L(return)
# else
je L(return)
# endif
.p2align 4
L(loop):
VMOVA %VEC(0), (%rcx)
VMOVA %VEC(0), VEC_SIZE(%rcx)
VMOVA %VEC(0), (VEC_SIZE * 2)(%rcx)
VMOVA %VEC(0), (VEC_SIZE * 3)(%rcx)
addq $(VEC_SIZE * 4), %rcx
cmpq %rcx, %rdx
jne L(loop)
VZEROUPPER_SHORT_RETURN
ret
L(less_vec):
/* Less than 1 VEC. */
# if VEC_SIZE != 16 && VEC_SIZE != 32 && VEC_SIZE != 64
# error Unsupported VEC_SIZE!
# endif
# if VEC_SIZE > 32
cmpb $32, %dl
jae L(between_32_63)
# endif
# if VEC_SIZE > 16
cmpb $16, %dl
jae L(between_16_31)
# endif
MOVQ %xmm0, %rcx
cmpb $8, %dl
jae L(between_8_15)
cmpb $4, %dl
jae L(between_4_7)
cmpb $1, %dl
ja L(between_2_3)
jb 1f
movb %cl, (%rdi)
1:
VZEROUPPER
ret
# if VEC_SIZE > 32
/* From 32 to 63. No branch when size == 32. */
L(between_32_63):
vmovdqu %ymm0, -32(%rdi,%rdx)
vmovdqu %ymm0, (%rdi)
VZEROUPPER
ret
# endif
# if VEC_SIZE > 16
/* From 16 to 31. No branch when size == 16. */
L(between_16_31):
vmovdqu %xmm0, -16(%rdi,%rdx)
vmovdqu %xmm0, (%rdi)
VZEROUPPER
ret
# endif
/* From 8 to 15. No branch when size == 8. */
L(between_8_15):
movq %rcx, -8(%rdi,%rdx)
movq %rcx, (%rdi)
VZEROUPPER
ret
L(between_4_7):
/* From 4 to 7. No branch when size == 4. */
movl %ecx, -4(%rdi,%rdx)
movl %ecx, (%rdi)
VZEROUPPER
ret
L(between_2_3):
/* From 2 to 3. No branch when size == 2. */
movw %cx, -2(%rdi,%rdx)
movw %cx, (%rdi)
VZEROUPPER
ret
END (MEMSET_SYMBOL (__memset, unaligned_erms))
|
