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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354
|
/* wcsrchr with SSE2, without using bsf instructions.
Copyright (C) 2011-2014 Free Software Foundation, Inc.
Contributed by Intel Corporation.
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/>. */
#ifndef NOT_IN_libc
# include <sysdep.h>
# define CFI_PUSH(REG) \
cfi_adjust_cfa_offset (4); \
cfi_rel_offset (REG, 0)
# define CFI_POP(REG) \
cfi_adjust_cfa_offset (-4); \
cfi_restore (REG)
# define PUSH(REG) pushl REG; CFI_PUSH (REG)
# define POP(REG) popl REG; CFI_POP (REG)
# define PARMS 8
# define ENTRANCE PUSH (%edi);
# define RETURN POP (%edi); ret; CFI_PUSH (%edi);
# define STR1 PARMS
# define STR2 STR1+4
atom_text_section
ENTRY (__wcsrchr_sse2)
ENTRANCE
mov STR1(%esp), %ecx
movd STR2(%esp), %xmm1
mov %ecx, %edi
punpckldq %xmm1, %xmm1
pxor %xmm2, %xmm2
punpckldq %xmm1, %xmm1
/* ECX has OFFSET. */
and $63, %ecx
cmp $48, %ecx
ja L(crosscache)
/* unaligned string. */
movdqu (%edi), %xmm0
pcmpeqd %xmm0, %xmm2
pcmpeqd %xmm1, %xmm0
/* Find where NULL is. */
pmovmskb %xmm2, %ecx
/* Check if there is a match. */
pmovmskb %xmm0, %eax
add $16, %edi
test %eax, %eax
jnz L(unaligned_match1)
test %ecx, %ecx
jnz L(return_null)
and $-16, %edi
PUSH (%esi)
xor %edx, %edx
jmp L(loop)
CFI_POP (%esi)
.p2align 4
L(unaligned_match1):
test %ecx, %ecx
jnz L(prolog_find_zero_1)
PUSH (%esi)
/* Save current match */
mov %eax, %edx
mov %edi, %esi
and $-16, %edi
jmp L(loop)
CFI_POP (%esi)
.p2align 4
L(crosscache):
/* Hancle unaligned string. */
and $15, %ecx
and $-16, %edi
pxor %xmm3, %xmm3
movdqa (%edi), %xmm0
pcmpeqd %xmm0, %xmm3
pcmpeqd %xmm1, %xmm0
/* Find where NULL is. */
pmovmskb %xmm3, %edx
/* Check if there is a match. */
pmovmskb %xmm0, %eax
/* Remove the leading bytes. */
shr %cl, %edx
shr %cl, %eax
add $16, %edi
test %eax, %eax
jnz L(unaligned_match)
test %edx, %edx
jnz L(return_null)
PUSH (%esi)
xor %edx, %edx
jmp L(loop)
CFI_POP (%esi)
.p2align 4
L(unaligned_match):
test %edx, %edx
jnz L(prolog_find_zero)
PUSH (%esi)
mov %eax, %edx
lea (%edi, %ecx), %esi
/* Loop start on aligned string. */
.p2align 4
L(loop):
movdqa (%edi), %xmm0
pcmpeqd %xmm0, %xmm2
add $16, %edi
pcmpeqd %xmm1, %xmm0
pmovmskb %xmm2, %ecx
pmovmskb %xmm0, %eax
or %eax, %ecx
jnz L(matches)
movdqa (%edi), %xmm3
pcmpeqd %xmm3, %xmm2
add $16, %edi
pcmpeqd %xmm1, %xmm3
pmovmskb %xmm2, %ecx
pmovmskb %xmm3, %eax
or %eax, %ecx
jnz L(matches)
movdqa (%edi), %xmm4
pcmpeqd %xmm4, %xmm2
add $16, %edi
pcmpeqd %xmm1, %xmm4
pmovmskb %xmm2, %ecx
pmovmskb %xmm4, %eax
or %eax, %ecx
jnz L(matches)
movdqa (%edi), %xmm5
pcmpeqd %xmm5, %xmm2
add $16, %edi
pcmpeqd %xmm1, %xmm5
pmovmskb %xmm2, %ecx
pmovmskb %xmm5, %eax
or %eax, %ecx
jz L(loop)
.p2align 4
L(matches):
test %eax, %eax
jnz L(match)
L(return_value):
test %edx, %edx
jz L(return_null_1)
mov %edx, %eax
mov %esi, %edi
POP (%esi)
test %ah, %ah
jnz L(match_third_or_fourth_wchar)
test $15 << 4, %al
jnz L(match_second_wchar)
lea -16(%edi), %eax
RETURN
CFI_PUSH (%esi)
.p2align 4
L(return_null_1):
POP (%esi)
xor %eax, %eax
RETURN
CFI_PUSH (%esi)
.p2align 4
L(match):
pmovmskb %xmm2, %ecx
test %ecx, %ecx
jnz L(find_zero)
/* save match info */
mov %eax, %edx
mov %edi, %esi
jmp L(loop)
.p2align 4
L(find_zero):
test %cl, %cl
jz L(find_zero_in_third_or_fourth_wchar)
test $15, %cl
jz L(find_zero_in_second_wchar)
and $1, %eax
jz L(return_value)
POP (%esi)
lea -16(%edi), %eax
RETURN
CFI_PUSH (%esi)
.p2align 4
L(find_zero_in_second_wchar):
and $1 << 5 - 1, %eax
jz L(return_value)
POP (%esi)
test $15 << 4, %al
jnz L(match_second_wchar)
lea -16(%edi), %eax
RETURN
CFI_PUSH (%esi)
.p2align 4
L(find_zero_in_third_or_fourth_wchar):
test $15, %ch
jz L(find_zero_in_fourth_wchar)
and $1 << 9 - 1, %eax
jz L(return_value)
POP (%esi)
test %ah, %ah
jnz L(match_third_wchar)
test $15 << 4, %al
jnz L(match_second_wchar)
lea -16(%edi), %eax
RETURN
CFI_PUSH (%esi)
.p2align 4
L(find_zero_in_fourth_wchar):
POP (%esi)
test %ah, %ah
jnz L(match_third_or_fourth_wchar)
test $15 << 4, %al
jnz L(match_second_wchar)
lea -16(%edi), %eax
RETURN
CFI_PUSH (%esi)
.p2align 4
L(match_second_wchar):
lea -12(%edi), %eax
RETURN
.p2align 4
L(match_third_or_fourth_wchar):
test $15 << 4, %ah
jnz L(match_fourth_wchar)
lea -8(%edi), %eax
RETURN
.p2align 4
L(match_third_wchar):
lea -8(%edi), %eax
RETURN
.p2align 4
L(match_fourth_wchar):
lea -4(%edi), %eax
RETURN
.p2align 4
L(return_null):
xor %eax, %eax
RETURN
.p2align 4
L(prolog_find_zero):
add %ecx, %edi
mov %edx, %ecx
L(prolog_find_zero_1):
test %cl, %cl
jz L(prolog_find_zero_in_third_or_fourth_wchar)
test $15, %cl
jz L(prolog_find_zero_in_second_wchar)
and $1, %eax
jz L(return_null)
lea -16(%edi), %eax
RETURN
.p2align 4
L(prolog_find_zero_in_second_wchar):
and $1 << 5 - 1, %eax
jz L(return_null)
test $15 << 4, %al
jnz L(match_second_wchar)
lea -16(%edi), %eax
RETURN
.p2align 4
L(prolog_find_zero_in_third_or_fourth_wchar):
test $15, %ch
jz L(prolog_find_zero_in_fourth_wchar)
and $1 << 9 - 1, %eax
jz L(return_null)
test %ah, %ah
jnz L(match_third_wchar)
test $15 << 4, %al
jnz L(match_second_wchar)
lea -16(%edi), %eax
RETURN
.p2align 4
L(prolog_find_zero_in_fourth_wchar):
test %ah, %ah
jnz L(match_third_or_fourth_wchar)
test $15 << 4, %al
jnz L(match_second_wchar)
lea -16(%edi), %eax
RETURN
END (__wcsrchr_sse2)
#endif
|