projects / mirror_zfs.git / blame
| Commit | Line | Data |
|---|---|---|
| 0b04990a TC |
1 | /* |
| 2 | * ==================================================================== | |
| 3 | * Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL | |
| 4 | * project. Rights for redistribution and usage in source and binary | |
| 5 | * forms are granted according to the OpenSSL license. | |
| 6 | * ==================================================================== | |
| 7 | * | |
| 8 | * sha256/512_block procedure for x86_64. | |
| 9 | * | |
| 10 | * 40% improvement over compiler-generated code on Opteron. On EM64T | |
| 11 | * sha256 was observed to run >80% faster and sha512 - >40%. No magical | |
| 12 | * tricks, just straight implementation... I really wonder why gcc | |
| 13 | * [being armed with inline assembler] fails to generate as fast code. | |
| 14 | * The only thing which is cool about this module is that it's very | |
| 15 | * same instruction sequence used for both SHA-256 and SHA-512. In | |
| 16 | * former case the instructions operate on 32-bit operands, while in | |
| 17 | * latter - on 64-bit ones. All I had to do is to get one flavor right, | |
| 18 | * the other one passed the test right away:-) | |
| 19 | * | |
| 20 | * sha256_block runs in ~1005 cycles on Opteron, which gives you | |
| 21 | * asymptotic performance of 64*1000/1005=63.7MBps times CPU clock | |
| 22 | * frequency in GHz. sha512_block runs in ~1275 cycles, which results | |
| 23 | * in 128*1000/1275=100MBps per GHz. Is there room for improvement? | |
| 24 | * Well, if you compare it to IA-64 implementation, which maintains | |
| 25 | * X[16] in register bank[!], tends to 4 instructions per CPU clock | |
| 26 | * cycle and runs in 1003 cycles, 1275 is very good result for 3-way | |
| 27 | * issue Opteron pipeline and X[16] maintained in memory. So that *if* | |
| 28 | * there is a way to improve it, *then* the only way would be to try to | |
| 29 | * offload X[16] updates to SSE unit, but that would require "deeper" | |
| 30 | * loop unroll, which in turn would naturally cause size blow-up, not | |
| 31 | * to mention increased complexity! And once again, only *if* it's | |
| 32 | * actually possible to noticeably improve overall ILP, instruction | |
| 33 | * level parallelism, on a given CPU implementation in this case. | |
| 34 | * | |
| 35 | * Special note on Intel EM64T. While Opteron CPU exhibits perfect | |
| 4e33ba4c | 36 | * performance ratio of 1.5 between 64- and 32-bit flavors [see above], |
| 0b04990a TC |
37 | * [currently available] EM64T CPUs apparently are far from it. On the |
| 38 | * contrary, 64-bit version, sha512_block, is ~30% *slower* than 32-bit | |
| 39 | * sha256_block:-( This is presumably because 64-bit shifts/rotates | |
| 40 | * apparently are not atomic instructions, but implemented in microcode. | |
| 41 | */ | |
| 42 | ||
| 43 | /* | |
| 44 | * OpenSolaris OS modifications | |
| 45 | * | |
| 46 | * Sun elects to use this software under the BSD license. | |
| 47 | * | |
| 48 | * This source originates from OpenSSL file sha512-x86_64.pl at | |
| 49 | * ftp://ftp.openssl.org/snapshot/openssl-0.9.8-stable-SNAP-20080131.tar.gz | |
| 50 | * (presumably for future OpenSSL release 0.9.8h), with these changes: | |
| 51 | * | |
| 52 | * 1. Added perl "use strict" and declared variables. | |
| 53 | * | |
| 54 | * 2. Added OpenSolaris ENTRY_NP/SET_SIZE macros from | |
| 55 | * /usr/include/sys/asm_linkage.h, .ident keywords, and lint(1B) guards. | |
| 56 | * | |
| 57 | * 3. Removed x86_64-xlate.pl script (not needed for as(1) or gas(1) | |
| 58 | * assemblers). Replaced the .picmeup macro with assembler code. | |
| 59 | * | |
| 60 | * 4. Added 8 to $ctx, as OpenSolaris OS has an extra 4-byte field, "algotype", | |
| 61 | * at the beginning of SHA2_CTX (the next field is 8-byte aligned). | |
| 62 | */ | |
| 63 | ||
| 64 | /* | |
| 650383f2 | 65 | * This file was generated by a perl script (sha512-x86_64.pl) that were |
| 3c67d83a TH |
66 | * used to generate sha256 and sha512 variants from the same code base. |
| 67 | * The comments from the original file have been pasted above. | |
| 0b04990a TC |
68 | */ |
| 69 | ||
| 70 | #if defined(lint) || defined(__lint) | |
| 71 | #include <sys/stdint.h> | |
| 72 | #include <sha2/sha2.h> | |
| 73 | ||
| 0b04990a TC |
74 | void |
| 75 | SHA256TransformBlocks(SHA2_CTX *ctx, const void *in, size_t num) | |
| 76 | { | |
| 18e4f679 | 77 | (void) ctx, (void) in, (void) num; |
| 0b04990a TC |
78 | } |
| 79 | ||
| 80 | ||
| 81 | #else | |
| 82 | #define _ASM | |
| 83 | #include <sys/asm_linkage.h> | |
| 84 | ||
| 85 | ENTRY_NP(SHA256TransformBlocks) | |
| a9c93ac5 AF |
86 | .cfi_startproc |
| 87 | movq %rsp, %rax | |
| 88 | .cfi_def_cfa_register %rax | |
| 0b04990a | 89 | push %rbx |
| a9c93ac5 | 90 | .cfi_offset %rbx,-16 |
| 0b04990a | 91 | push %rbp |
| a9c93ac5 | 92 | .cfi_offset %rbp,-24 |
| 0b04990a | 93 | push %r12 |
| a9c93ac5 | 94 | .cfi_offset %r12,-32 |
| 0b04990a | 95 | push %r13 |
| a9c93ac5 | 96 | .cfi_offset %r13,-40 |
| 0b04990a | 97 | push %r14 |
| a9c93ac5 | 98 | .cfi_offset %r14,-48 |
| 0b04990a | 99 | push %r15 |
| a9c93ac5 | 100 | .cfi_offset %r15,-56 |
| 0b04990a TC |
101 | mov %rsp,%rbp # copy %rsp |
| 102 | shl $4,%rdx # num*16 | |
| 103 | sub $16*4+4*8,%rsp | |
| 104 | lea (%rsi,%rdx,4),%rdx # inp+num*16*4 | |
| 105 | and $-64,%rsp # align stack frame | |
| 106 | add $8,%rdi # Skip OpenSolaris field, "algotype" | |
| 107 | mov %rdi,16*4+0*8(%rsp) # save ctx, 1st arg | |
| 108 | mov %rsi,16*4+1*8(%rsp) # save inp, 2nd arg | |
| 109 | mov %rdx,16*4+2*8(%rsp) # save end pointer, "3rd" arg | |
| 110 | mov %rbp,16*4+3*8(%rsp) # save copy of %rsp | |
| a9c93ac5 AF |
111 | # echo ".cfi_cfa_expression %rsp+88,deref,+56" | |
| 112 | # openssl/crypto/perlasm/x86_64-xlate.pl | |
| 113 | .cfi_escape 0x0f,0x06,0x77,0xd8,0x00,0x06,0x23,0x38 | |
| 0b04990a | 114 | |
| 688c94c5 HL |
115 | #.picmeup %rbp |
| 116 | # The .picmeup pseudo-directive, from perlasm/x86_64_xlate.pl, puts | |
| 117 | # the address of the "next" instruction into the target register | |
| 118 | # (%rbp). This generates these 2 instructions: | |
| 0b04990a | 119 | lea .Llea(%rip),%rbp |
| 688c94c5 | 120 | #nop # .picmeup generates a nop for mod 8 alignment--not needed here |
| 0b04990a TC |
121 | |
| 122 | .Llea: | |
| 123 | lea K256-.(%rbp),%rbp | |
| 124 | ||
| 125 | mov 4*0(%rdi),%eax | |
| 126 | mov 4*1(%rdi),%ebx | |
| 127 | mov 4*2(%rdi),%ecx | |
| 128 | mov 4*3(%rdi),%edx | |
| 129 | mov 4*4(%rdi),%r8d | |
| 130 | mov 4*5(%rdi),%r9d | |
| 131 | mov 4*6(%rdi),%r10d | |
| 132 | mov 4*7(%rdi),%r11d | |
| 133 | jmp .Lloop | |
| 134 | ||
| 135 | .align 16 | |
| 136 | .Lloop: | |
| 137 | xor %rdi,%rdi | |
| 138 | mov 4*0(%rsi),%r12d | |
| 139 | bswap %r12d | |
| 140 | mov %r8d,%r13d | |
| 141 | mov %r8d,%r14d | |
| 142 | mov %r9d,%r15d | |
| 143 | ||
| 144 | ror $6,%r13d | |
| 145 | ror $11,%r14d | |
| 146 | xor %r10d,%r15d # f^g | |
| 147 | ||
| 148 | xor %r14d,%r13d | |
| 149 | ror $14,%r14d | |
| 150 | and %r8d,%r15d # (f^g)&e | |
| 151 | mov %r12d,0(%rsp) | |
| 152 | ||
| 153 | xor %r14d,%r13d # Sigma1(e) | |
| 154 | xor %r10d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 155 | add %r11d,%r12d # T1+=h | |
| 156 | ||
| 157 | mov %eax,%r11d | |
| 158 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 159 | ||
| 160 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 161 | mov %eax,%r13d | |
| 162 | mov %eax,%r14d | |
| 163 | ||
| 164 | ror $2,%r11d | |
| 165 | ror $13,%r13d | |
| 166 | mov %eax,%r15d | |
| 167 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 168 | ||
| 169 | xor %r13d,%r11d | |
| 170 | ror $9,%r13d | |
| 171 | or %ecx,%r14d # a|c | |
| 172 | ||
| 173 | xor %r13d,%r11d # h=Sigma0(a) | |
| 174 | and %ecx,%r15d # a&c | |
| 175 | add %r12d,%edx # d+=T1 | |
| 176 | ||
| 177 | and %ebx,%r14d # (a|c)&b | |
| 178 | add %r12d,%r11d # h+=T1 | |
| 179 | ||
| 180 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 181 | lea 1(%rdi),%rdi # round++ | |
| 182 | ||
| 183 | add %r14d,%r11d # h+=Maj(a,b,c) | |
| 184 | mov 4*1(%rsi),%r12d | |
| 185 | bswap %r12d | |
| 186 | mov %edx,%r13d | |
| 187 | mov %edx,%r14d | |
| 188 | mov %r8d,%r15d | |
| 189 | ||
| 190 | ror $6,%r13d | |
| 191 | ror $11,%r14d | |
| 192 | xor %r9d,%r15d # f^g | |
| 193 | ||
| 194 | xor %r14d,%r13d | |
| 195 | ror $14,%r14d | |
| 196 | and %edx,%r15d # (f^g)&e | |
| 197 | mov %r12d,4(%rsp) | |
| 198 | ||
| 199 | xor %r14d,%r13d # Sigma1(e) | |
| 200 | xor %r9d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 201 | add %r10d,%r12d # T1+=h | |
| 202 | ||
| 203 | mov %r11d,%r10d | |
| 204 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 205 | ||
| 206 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 207 | mov %r11d,%r13d | |
| 208 | mov %r11d,%r14d | |
| 209 | ||
| 210 | ror $2,%r10d | |
| 211 | ror $13,%r13d | |
| 212 | mov %r11d,%r15d | |
| 213 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 214 | ||
| 215 | xor %r13d,%r10d | |
| 216 | ror $9,%r13d | |
| 217 | or %ebx,%r14d # a|c | |
| 218 | ||
| 219 | xor %r13d,%r10d # h=Sigma0(a) | |
| 220 | and %ebx,%r15d # a&c | |
| 221 | add %r12d,%ecx # d+=T1 | |
| 222 | ||
| 223 | and %eax,%r14d # (a|c)&b | |
| 224 | add %r12d,%r10d # h+=T1 | |
| 225 | ||
| 226 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 227 | lea 1(%rdi),%rdi # round++ | |
| 228 | ||
| 229 | add %r14d,%r10d # h+=Maj(a,b,c) | |
| 230 | mov 4*2(%rsi),%r12d | |
| 231 | bswap %r12d | |
| 232 | mov %ecx,%r13d | |
| 233 | mov %ecx,%r14d | |
| 234 | mov %edx,%r15d | |
| 235 | ||
| 236 | ror $6,%r13d | |
| 237 | ror $11,%r14d | |
| 238 | xor %r8d,%r15d # f^g | |
| 239 | ||
| 240 | xor %r14d,%r13d | |
| 241 | ror $14,%r14d | |
| 242 | and %ecx,%r15d # (f^g)&e | |
| 243 | mov %r12d,8(%rsp) | |
| 244 | ||
| 245 | xor %r14d,%r13d # Sigma1(e) | |
| 246 | xor %r8d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 247 | add %r9d,%r12d # T1+=h | |
| 248 | ||
| 249 | mov %r10d,%r9d | |
| 250 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 251 | ||
| 252 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 253 | mov %r10d,%r13d | |
| 254 | mov %r10d,%r14d | |
| 255 | ||
| 256 | ror $2,%r9d | |
| 257 | ror $13,%r13d | |
| 258 | mov %r10d,%r15d | |
| 259 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 260 | ||
| 261 | xor %r13d,%r9d | |
| 262 | ror $9,%r13d | |
| 263 | or %eax,%r14d # a|c | |
| 264 | ||
| 265 | xor %r13d,%r9d # h=Sigma0(a) | |
| 266 | and %eax,%r15d # a&c | |
| 267 | add %r12d,%ebx # d+=T1 | |
| 268 | ||
| 269 | and %r11d,%r14d # (a|c)&b | |
| 270 | add %r12d,%r9d # h+=T1 | |
| 271 | ||
| 272 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 273 | lea 1(%rdi),%rdi # round++ | |
| 274 | ||
| 275 | add %r14d,%r9d # h+=Maj(a,b,c) | |
| 276 | mov 4*3(%rsi),%r12d | |
| 277 | bswap %r12d | |
| 278 | mov %ebx,%r13d | |
| 279 | mov %ebx,%r14d | |
| 280 | mov %ecx,%r15d | |
| 281 | ||
| 282 | ror $6,%r13d | |
| 283 | ror $11,%r14d | |
| 284 | xor %edx,%r15d # f^g | |
| 285 | ||
| 286 | xor %r14d,%r13d | |
| 287 | ror $14,%r14d | |
| 288 | and %ebx,%r15d # (f^g)&e | |
| 289 | mov %r12d,12(%rsp) | |
| 290 | ||
| 291 | xor %r14d,%r13d # Sigma1(e) | |
| 292 | xor %edx,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 293 | add %r8d,%r12d # T1+=h | |
| 294 | ||
| 295 | mov %r9d,%r8d | |
| 296 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 297 | ||
| 298 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 299 | mov %r9d,%r13d | |
| 300 | mov %r9d,%r14d | |
| 301 | ||
| 302 | ror $2,%r8d | |
| 303 | ror $13,%r13d | |
| 304 | mov %r9d,%r15d | |
| 305 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 306 | ||
| 307 | xor %r13d,%r8d | |
| 308 | ror $9,%r13d | |
| 309 | or %r11d,%r14d # a|c | |
| 310 | ||
| 311 | xor %r13d,%r8d # h=Sigma0(a) | |
| 312 | and %r11d,%r15d # a&c | |
| 313 | add %r12d,%eax # d+=T1 | |
| 314 | ||
| 315 | and %r10d,%r14d # (a|c)&b | |
| 316 | add %r12d,%r8d # h+=T1 | |
| 317 | ||
| 318 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 319 | lea 1(%rdi),%rdi # round++ | |
| 320 | ||
| 321 | add %r14d,%r8d # h+=Maj(a,b,c) | |
| 322 | mov 4*4(%rsi),%r12d | |
| 323 | bswap %r12d | |
| 324 | mov %eax,%r13d | |
| 325 | mov %eax,%r14d | |
| 326 | mov %ebx,%r15d | |
| 327 | ||
| 328 | ror $6,%r13d | |
| 329 | ror $11,%r14d | |
| 330 | xor %ecx,%r15d # f^g | |
| 331 | ||
| 332 | xor %r14d,%r13d | |
| 333 | ror $14,%r14d | |
| 334 | and %eax,%r15d # (f^g)&e | |
| 335 | mov %r12d,16(%rsp) | |
| 336 | ||
| 337 | xor %r14d,%r13d # Sigma1(e) | |
| 338 | xor %ecx,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 339 | add %edx,%r12d # T1+=h | |
| 340 | ||
| 341 | mov %r8d,%edx | |
| 342 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 343 | ||
| 344 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 345 | mov %r8d,%r13d | |
| 346 | mov %r8d,%r14d | |
| 347 | ||
| 348 | ror $2,%edx | |
| 349 | ror $13,%r13d | |
| 350 | mov %r8d,%r15d | |
| 351 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 352 | ||
| 353 | xor %r13d,%edx | |
| 354 | ror $9,%r13d | |
| 355 | or %r10d,%r14d # a|c | |
| 356 | ||
| 357 | xor %r13d,%edx # h=Sigma0(a) | |
| 358 | and %r10d,%r15d # a&c | |
| 359 | add %r12d,%r11d # d+=T1 | |
| 360 | ||
| 361 | and %r9d,%r14d # (a|c)&b | |
| 362 | add %r12d,%edx # h+=T1 | |
| 363 | ||
| 364 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 365 | lea 1(%rdi),%rdi # round++ | |
| 366 | ||
| 367 | add %r14d,%edx # h+=Maj(a,b,c) | |
| 368 | mov 4*5(%rsi),%r12d | |
| 369 | bswap %r12d | |
| 370 | mov %r11d,%r13d | |
| 371 | mov %r11d,%r14d | |
| 372 | mov %eax,%r15d | |
| 373 | ||
| 374 | ror $6,%r13d | |
| 375 | ror $11,%r14d | |
| 376 | xor %ebx,%r15d # f^g | |
| 377 | ||
| 378 | xor %r14d,%r13d | |
| 379 | ror $14,%r14d | |
| 380 | and %r11d,%r15d # (f^g)&e | |
| 381 | mov %r12d,20(%rsp) | |
| 382 | ||
| 383 | xor %r14d,%r13d # Sigma1(e) | |
| 384 | xor %ebx,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 385 | add %ecx,%r12d # T1+=h | |
| 386 | ||
| 387 | mov %edx,%ecx | |
| 388 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 389 | ||
| 390 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 391 | mov %edx,%r13d | |
| 392 | mov %edx,%r14d | |
| 393 | ||
| 394 | ror $2,%ecx | |
| 395 | ror $13,%r13d | |
| 396 | mov %edx,%r15d | |
| 397 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 398 | ||
| 399 | xor %r13d,%ecx | |
| 400 | ror $9,%r13d | |
| 401 | or %r9d,%r14d # a|c | |
| 402 | ||
| 403 | xor %r13d,%ecx # h=Sigma0(a) | |
| 404 | and %r9d,%r15d # a&c | |
| 405 | add %r12d,%r10d # d+=T1 | |
| 406 | ||
| 407 | and %r8d,%r14d # (a|c)&b | |
| 408 | add %r12d,%ecx # h+=T1 | |
| 409 | ||
| 410 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 411 | lea 1(%rdi),%rdi # round++ | |
| 412 | ||
| 413 | add %r14d,%ecx # h+=Maj(a,b,c) | |
| 414 | mov 4*6(%rsi),%r12d | |
| 415 | bswap %r12d | |
| 416 | mov %r10d,%r13d | |
| 417 | mov %r10d,%r14d | |
| 418 | mov %r11d,%r15d | |
| 419 | ||
| 420 | ror $6,%r13d | |
| 421 | ror $11,%r14d | |
| 422 | xor %eax,%r15d # f^g | |
| 423 | ||
| 424 | xor %r14d,%r13d | |
| 425 | ror $14,%r14d | |
| 426 | and %r10d,%r15d # (f^g)&e | |
| 427 | mov %r12d,24(%rsp) | |
| 428 | ||
| 429 | xor %r14d,%r13d # Sigma1(e) | |
| 430 | xor %eax,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 431 | add %ebx,%r12d # T1+=h | |
| 432 | ||
| 433 | mov %ecx,%ebx | |
| 434 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 435 | ||
| 436 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 437 | mov %ecx,%r13d | |
| 438 | mov %ecx,%r14d | |
| 439 | ||
| 440 | ror $2,%ebx | |
| 441 | ror $13,%r13d | |
| 442 | mov %ecx,%r15d | |
| 443 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 444 | ||
| 445 | xor %r13d,%ebx | |
| 446 | ror $9,%r13d | |
| 447 | or %r8d,%r14d # a|c | |
| 448 | ||
| 449 | xor %r13d,%ebx # h=Sigma0(a) | |
| 450 | and %r8d,%r15d # a&c | |
| 451 | add %r12d,%r9d # d+=T1 | |
| 452 | ||
| 453 | and %edx,%r14d # (a|c)&b | |
| 454 | add %r12d,%ebx # h+=T1 | |
| 455 | ||
| 456 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 457 | lea 1(%rdi),%rdi # round++ | |
| 458 | ||
| 459 | add %r14d,%ebx # h+=Maj(a,b,c) | |
| 460 | mov 4*7(%rsi),%r12d | |
| 461 | bswap %r12d | |
| 462 | mov %r9d,%r13d | |
| 463 | mov %r9d,%r14d | |
| 464 | mov %r10d,%r15d | |
| 465 | ||
| 466 | ror $6,%r13d | |
| 467 | ror $11,%r14d | |
| 468 | xor %r11d,%r15d # f^g | |
| 469 | ||
| 470 | xor %r14d,%r13d | |
| 471 | ror $14,%r14d | |
| 472 | and %r9d,%r15d # (f^g)&e | |
| 473 | mov %r12d,28(%rsp) | |
| 474 | ||
| 475 | xor %r14d,%r13d # Sigma1(e) | |
| 476 | xor %r11d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 477 | add %eax,%r12d # T1+=h | |
| 478 | ||
| 479 | mov %ebx,%eax | |
| 480 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 481 | ||
| 482 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 483 | mov %ebx,%r13d | |
| 484 | mov %ebx,%r14d | |
| 485 | ||
| 486 | ror $2,%eax | |
| 487 | ror $13,%r13d | |
| 488 | mov %ebx,%r15d | |
| 489 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 490 | ||
| 491 | xor %r13d,%eax | |
| 492 | ror $9,%r13d | |
| 493 | or %edx,%r14d # a|c | |
| 494 | ||
| 495 | xor %r13d,%eax # h=Sigma0(a) | |
| 496 | and %edx,%r15d # a&c | |
| 497 | add %r12d,%r8d # d+=T1 | |
| 498 | ||
| 499 | and %ecx,%r14d # (a|c)&b | |
| 500 | add %r12d,%eax # h+=T1 | |
| 501 | ||
| 502 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 503 | lea 1(%rdi),%rdi # round++ | |
| 504 | ||
| 505 | add %r14d,%eax # h+=Maj(a,b,c) | |
| 506 | mov 4*8(%rsi),%r12d | |
| 507 | bswap %r12d | |
| 508 | mov %r8d,%r13d | |
| 509 | mov %r8d,%r14d | |
| 510 | mov %r9d,%r15d | |
| 511 | ||
| 512 | ror $6,%r13d | |
| 513 | ror $11,%r14d | |
| 514 | xor %r10d,%r15d # f^g | |
| 515 | ||
| 516 | xor %r14d,%r13d | |
| 517 | ror $14,%r14d | |
| 518 | and %r8d,%r15d # (f^g)&e | |
| 519 | mov %r12d,32(%rsp) | |
| 520 | ||
| 521 | xor %r14d,%r13d # Sigma1(e) | |
| 522 | xor %r10d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 523 | add %r11d,%r12d # T1+=h | |
| 524 | ||
| 525 | mov %eax,%r11d | |
| 526 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 527 | ||
| 528 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 529 | mov %eax,%r13d | |
| 530 | mov %eax,%r14d | |
| 531 | ||
| 532 | ror $2,%r11d | |
| 533 | ror $13,%r13d | |
| 534 | mov %eax,%r15d | |
| 535 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 536 | ||
| 537 | xor %r13d,%r11d | |
| 538 | ror $9,%r13d | |
| 539 | or %ecx,%r14d # a|c | |
| 540 | ||
| 541 | xor %r13d,%r11d # h=Sigma0(a) | |
| 542 | and %ecx,%r15d # a&c | |
| 543 | add %r12d,%edx # d+=T1 | |
| 544 | ||
| 545 | and %ebx,%r14d # (a|c)&b | |
| 546 | add %r12d,%r11d # h+=T1 | |
| 547 | ||
| 548 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 549 | lea 1(%rdi),%rdi # round++ | |
| 550 | ||
| 551 | add %r14d,%r11d # h+=Maj(a,b,c) | |
| 552 | mov 4*9(%rsi),%r12d | |
| 553 | bswap %r12d | |
| 554 | mov %edx,%r13d | |
| 555 | mov %edx,%r14d | |
| 556 | mov %r8d,%r15d | |
| 557 | ||
| 558 | ror $6,%r13d | |
| 559 | ror $11,%r14d | |
| 560 | xor %r9d,%r15d # f^g | |
| 561 | ||
| 562 | xor %r14d,%r13d | |
| 563 | ror $14,%r14d | |
| 564 | and %edx,%r15d # (f^g)&e | |
| 565 | mov %r12d,36(%rsp) | |
| 566 | ||
| 567 | xor %r14d,%r13d # Sigma1(e) | |
| 568 | xor %r9d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 569 | add %r10d,%r12d # T1+=h | |
| 570 | ||
| 571 | mov %r11d,%r10d | |
| 572 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 573 | ||
| 574 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 575 | mov %r11d,%r13d | |
| 576 | mov %r11d,%r14d | |
| 577 | ||
| 578 | ror $2,%r10d | |
| 579 | ror $13,%r13d | |
| 580 | mov %r11d,%r15d | |
| 581 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 582 | ||
| 583 | xor %r13d,%r10d | |
| 584 | ror $9,%r13d | |
| 585 | or %ebx,%r14d # a|c | |
| 586 | ||
| 587 | xor %r13d,%r10d # h=Sigma0(a) | |
| 588 | and %ebx,%r15d # a&c | |
| 589 | add %r12d,%ecx # d+=T1 | |
| 590 | ||
| 591 | and %eax,%r14d # (a|c)&b | |
| 592 | add %r12d,%r10d # h+=T1 | |
| 593 | ||
| 594 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 595 | lea 1(%rdi),%rdi # round++ | |
| 596 | ||
| 597 | add %r14d,%r10d # h+=Maj(a,b,c) | |
| 598 | mov 4*10(%rsi),%r12d | |
| 599 | bswap %r12d | |
| 600 | mov %ecx,%r13d | |
| 601 | mov %ecx,%r14d | |
| 602 | mov %edx,%r15d | |
| 603 | ||
| 604 | ror $6,%r13d | |
| 605 | ror $11,%r14d | |
| 606 | xor %r8d,%r15d # f^g | |
| 607 | ||
| 608 | xor %r14d,%r13d | |
| 609 | ror $14,%r14d | |
| 610 | and %ecx,%r15d # (f^g)&e | |
| 611 | mov %r12d,40(%rsp) | |
| 612 | ||
| 613 | xor %r14d,%r13d # Sigma1(e) | |
| 614 | xor %r8d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 615 | add %r9d,%r12d # T1+=h | |
| 616 | ||
| 617 | mov %r10d,%r9d | |
| 618 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 619 | ||
| 620 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 621 | mov %r10d,%r13d | |
| 622 | mov %r10d,%r14d | |
| 623 | ||
| 624 | ror $2,%r9d | |
| 625 | ror $13,%r13d | |
| 626 | mov %r10d,%r15d | |
| 627 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 628 | ||
| 629 | xor %r13d,%r9d | |
| 630 | ror $9,%r13d | |
| 631 | or %eax,%r14d # a|c | |
| 632 | ||
| 633 | xor %r13d,%r9d # h=Sigma0(a) | |
| 634 | and %eax,%r15d # a&c | |
| 635 | add %r12d,%ebx # d+=T1 | |
| 636 | ||
| 637 | and %r11d,%r14d # (a|c)&b | |
| 638 | add %r12d,%r9d # h+=T1 | |
| 639 | ||
| 640 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 641 | lea 1(%rdi),%rdi # round++ | |
| 642 | ||
| 643 | add %r14d,%r9d # h+=Maj(a,b,c) | |
| 644 | mov 4*11(%rsi),%r12d | |
| 645 | bswap %r12d | |
| 646 | mov %ebx,%r13d | |
| 647 | mov %ebx,%r14d | |
| 648 | mov %ecx,%r15d | |
| 649 | ||
| 650 | ror $6,%r13d | |
| 651 | ror $11,%r14d | |
| 652 | xor %edx,%r15d # f^g | |
| 653 | ||
| 654 | xor %r14d,%r13d | |
| 655 | ror $14,%r14d | |
| 656 | and %ebx,%r15d # (f^g)&e | |
| 657 | mov %r12d,44(%rsp) | |
| 658 | ||
| 659 | xor %r14d,%r13d # Sigma1(e) | |
| 660 | xor %edx,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 661 | add %r8d,%r12d # T1+=h | |
| 662 | ||
| 663 | mov %r9d,%r8d | |
| 664 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 665 | ||
| 666 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 667 | mov %r9d,%r13d | |
| 668 | mov %r9d,%r14d | |
| 669 | ||
| 670 | ror $2,%r8d | |
| 671 | ror $13,%r13d | |
| 672 | mov %r9d,%r15d | |
| 673 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 674 | ||
| 675 | xor %r13d,%r8d | |
| 676 | ror $9,%r13d | |
| 677 | or %r11d,%r14d # a|c | |
| 678 | ||
| 679 | xor %r13d,%r8d # h=Sigma0(a) | |
| 680 | and %r11d,%r15d # a&c | |
| 681 | add %r12d,%eax # d+=T1 | |
| 682 | ||
| 683 | and %r10d,%r14d # (a|c)&b | |
| 684 | add %r12d,%r8d # h+=T1 | |
| 685 | ||
| 686 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 687 | lea 1(%rdi),%rdi # round++ | |
| 688 | ||
| 689 | add %r14d,%r8d # h+=Maj(a,b,c) | |
| 690 | mov 4*12(%rsi),%r12d | |
| 691 | bswap %r12d | |
| 692 | mov %eax,%r13d | |
| 693 | mov %eax,%r14d | |
| 694 | mov %ebx,%r15d | |
| 695 | ||
| 696 | ror $6,%r13d | |
| 697 | ror $11,%r14d | |
| 698 | xor %ecx,%r15d # f^g | |
| 699 | ||
| 700 | xor %r14d,%r13d | |
| 701 | ror $14,%r14d | |
| 702 | and %eax,%r15d # (f^g)&e | |
| 703 | mov %r12d,48(%rsp) | |
| 704 | ||
| 705 | xor %r14d,%r13d # Sigma1(e) | |
| 706 | xor %ecx,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 707 | add %edx,%r12d # T1+=h | |
| 708 | ||
| 709 | mov %r8d,%edx | |
| 710 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 711 | ||
| 712 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 713 | mov %r8d,%r13d | |
| 714 | mov %r8d,%r14d | |
| 715 | ||
| 716 | ror $2,%edx | |
| 717 | ror $13,%r13d | |
| 718 | mov %r8d,%r15d | |
| 719 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 720 | ||
| 721 | xor %r13d,%edx | |
| 722 | ror $9,%r13d | |
| 723 | or %r10d,%r14d # a|c | |
| 724 | ||
| 725 | xor %r13d,%edx # h=Sigma0(a) | |
| 726 | and %r10d,%r15d # a&c | |
| 727 | add %r12d,%r11d # d+=T1 | |
| 728 | ||
| 729 | and %r9d,%r14d # (a|c)&b | |
| 730 | add %r12d,%edx # h+=T1 | |
| 731 | ||
| 732 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 733 | lea 1(%rdi),%rdi # round++ | |
| 734 | ||
| 735 | add %r14d,%edx # h+=Maj(a,b,c) | |
| 736 | mov 4*13(%rsi),%r12d | |
| 737 | bswap %r12d | |
| 738 | mov %r11d,%r13d | |
| 739 | mov %r11d,%r14d | |
| 740 | mov %eax,%r15d | |
| 741 | ||
| 742 | ror $6,%r13d | |
| 743 | ror $11,%r14d | |
| 744 | xor %ebx,%r15d # f^g | |
| 745 | ||
| 746 | xor %r14d,%r13d | |
| 747 | ror $14,%r14d | |
| 748 | and %r11d,%r15d # (f^g)&e | |
| 749 | mov %r12d,52(%rsp) | |
| 750 | ||
| 751 | xor %r14d,%r13d # Sigma1(e) | |
| 752 | xor %ebx,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 753 | add %ecx,%r12d # T1+=h | |
| 754 | ||
| 755 | mov %edx,%ecx | |
| 756 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 757 | ||
| 758 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 759 | mov %edx,%r13d | |
| 760 | mov %edx,%r14d | |
| 761 | ||
| 762 | ror $2,%ecx | |
| 763 | ror $13,%r13d | |
| 764 | mov %edx,%r15d | |
| 765 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 766 | ||
| 767 | xor %r13d,%ecx | |
| 768 | ror $9,%r13d | |
| 769 | or %r9d,%r14d # a|c | |
| 770 | ||
| 771 | xor %r13d,%ecx # h=Sigma0(a) | |
| 772 | and %r9d,%r15d # a&c | |
| 773 | add %r12d,%r10d # d+=T1 | |
| 774 | ||
| 775 | and %r8d,%r14d # (a|c)&b | |
| 776 | add %r12d,%ecx # h+=T1 | |
| 777 | ||
| 778 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 779 | lea 1(%rdi),%rdi # round++ | |
| 780 | ||
| 781 | add %r14d,%ecx # h+=Maj(a,b,c) | |
| 782 | mov 4*14(%rsi),%r12d | |
| 783 | bswap %r12d | |
| 784 | mov %r10d,%r13d | |
| 785 | mov %r10d,%r14d | |
| 786 | mov %r11d,%r15d | |
| 787 | ||
| 788 | ror $6,%r13d | |
| 789 | ror $11,%r14d | |
| 790 | xor %eax,%r15d # f^g | |
| 791 | ||
| 792 | xor %r14d,%r13d | |
| 793 | ror $14,%r14d | |
| 794 | and %r10d,%r15d # (f^g)&e | |
| 795 | mov %r12d,56(%rsp) | |
| 796 | ||
| 797 | xor %r14d,%r13d # Sigma1(e) | |
| 798 | xor %eax,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 799 | add %ebx,%r12d # T1+=h | |
| 800 | ||
| 801 | mov %ecx,%ebx | |
| 802 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 803 | ||
| 804 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 805 | mov %ecx,%r13d | |
| 806 | mov %ecx,%r14d | |
| 807 | ||
| 808 | ror $2,%ebx | |
| 809 | ror $13,%r13d | |
| 810 | mov %ecx,%r15d | |
| 811 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 812 | ||
| 813 | xor %r13d,%ebx | |
| 814 | ror $9,%r13d | |
| 815 | or %r8d,%r14d # a|c | |
| 816 | ||
| 817 | xor %r13d,%ebx # h=Sigma0(a) | |
| 818 | and %r8d,%r15d # a&c | |
| 819 | add %r12d,%r9d # d+=T1 | |
| 820 | ||
| 821 | and %edx,%r14d # (a|c)&b | |
| 822 | add %r12d,%ebx # h+=T1 | |
| 823 | ||
| 824 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 825 | lea 1(%rdi),%rdi # round++ | |
| 826 | ||
| 827 | add %r14d,%ebx # h+=Maj(a,b,c) | |
| 828 | mov 4*15(%rsi),%r12d | |
| 829 | bswap %r12d | |
| 830 | mov %r9d,%r13d | |
| 831 | mov %r9d,%r14d | |
| 832 | mov %r10d,%r15d | |
| 833 | ||
| 834 | ror $6,%r13d | |
| 835 | ror $11,%r14d | |
| 836 | xor %r11d,%r15d # f^g | |
| 837 | ||
| 838 | xor %r14d,%r13d | |
| 839 | ror $14,%r14d | |
| 840 | and %r9d,%r15d # (f^g)&e | |
| 841 | mov %r12d,60(%rsp) | |
| 842 | ||
| 843 | xor %r14d,%r13d # Sigma1(e) | |
| 844 | xor %r11d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 845 | add %eax,%r12d # T1+=h | |
| 846 | ||
| 847 | mov %ebx,%eax | |
| 848 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 849 | ||
| 850 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 851 | mov %ebx,%r13d | |
| 852 | mov %ebx,%r14d | |
| 853 | ||
| 854 | ror $2,%eax | |
| 855 | ror $13,%r13d | |
| 856 | mov %ebx,%r15d | |
| 857 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 858 | ||
| 859 | xor %r13d,%eax | |
| 860 | ror $9,%r13d | |
| 861 | or %edx,%r14d # a|c | |
| 862 | ||
| 863 | xor %r13d,%eax # h=Sigma0(a) | |
| 864 | and %edx,%r15d # a&c | |
| 865 | add %r12d,%r8d # d+=T1 | |
| 866 | ||
| 867 | and %ecx,%r14d # (a|c)&b | |
| 868 | add %r12d,%eax # h+=T1 | |
| 869 | ||
| 870 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 871 | lea 1(%rdi),%rdi # round++ | |
| 872 | ||
| 873 | add %r14d,%eax # h+=Maj(a,b,c) | |
| 874 | jmp .Lrounds_16_xx | |
| 875 | .align 16 | |
| 876 | .Lrounds_16_xx: | |
| 877 | mov 4(%rsp),%r13d | |
| 878 | mov 56(%rsp),%r12d | |
| 879 | ||
| 880 | mov %r13d,%r15d | |
| 881 | ||
| 882 | shr $3,%r13d | |
| 883 | ror $7,%r15d | |
| 884 | ||
| 885 | xor %r15d,%r13d | |
| 886 | ror $11,%r15d | |
| 887 | ||
| 888 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 889 | mov %r12d,%r14d | |
| 890 | ||
| 891 | shr $10,%r12d | |
| 892 | ror $17,%r14d | |
| 893 | ||
| 894 | xor %r14d,%r12d | |
| 895 | ror $2,%r14d | |
| 896 | ||
| 897 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 898 | ||
| 899 | add %r13d,%r12d | |
| 900 | ||
| 901 | add 36(%rsp),%r12d | |
| 902 | ||
| 903 | add 0(%rsp),%r12d | |
| 904 | mov %r8d,%r13d | |
| 905 | mov %r8d,%r14d | |
| 906 | mov %r9d,%r15d | |
| 907 | ||
| 908 | ror $6,%r13d | |
| 909 | ror $11,%r14d | |
| 910 | xor %r10d,%r15d # f^g | |
| 911 | ||
| 912 | xor %r14d,%r13d | |
| 913 | ror $14,%r14d | |
| 914 | and %r8d,%r15d # (f^g)&e | |
| 915 | mov %r12d,0(%rsp) | |
| 916 | ||
| 917 | xor %r14d,%r13d # Sigma1(e) | |
| 918 | xor %r10d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 919 | add %r11d,%r12d # T1+=h | |
| 920 | ||
| 921 | mov %eax,%r11d | |
| 922 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 923 | ||
| 924 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 925 | mov %eax,%r13d | |
| 926 | mov %eax,%r14d | |
| 927 | ||
| 928 | ror $2,%r11d | |
| 929 | ror $13,%r13d | |
| 930 | mov %eax,%r15d | |
| 931 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 932 | ||
| 933 | xor %r13d,%r11d | |
| 934 | ror $9,%r13d | |
| 935 | or %ecx,%r14d # a|c | |
| 936 | ||
| 937 | xor %r13d,%r11d # h=Sigma0(a) | |
| 938 | and %ecx,%r15d # a&c | |
| 939 | add %r12d,%edx # d+=T1 | |
| 940 | ||
| 941 | and %ebx,%r14d # (a|c)&b | |
| 942 | add %r12d,%r11d # h+=T1 | |
| 943 | ||
| 944 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 945 | lea 1(%rdi),%rdi # round++ | |
| 946 | ||
| 947 | add %r14d,%r11d # h+=Maj(a,b,c) | |
| 948 | mov 8(%rsp),%r13d | |
| 949 | mov 60(%rsp),%r12d | |
| 950 | ||
| 951 | mov %r13d,%r15d | |
| 952 | ||
| 953 | shr $3,%r13d | |
| 954 | ror $7,%r15d | |
| 955 | ||
| 956 | xor %r15d,%r13d | |
| 957 | ror $11,%r15d | |
| 958 | ||
| 959 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 960 | mov %r12d,%r14d | |
| 961 | ||
| 962 | shr $10,%r12d | |
| 963 | ror $17,%r14d | |
| 964 | ||
| 965 | xor %r14d,%r12d | |
| 966 | ror $2,%r14d | |
| 967 | ||
| 968 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 969 | ||
| 970 | add %r13d,%r12d | |
| 971 | ||
| 972 | add 40(%rsp),%r12d | |
| 973 | ||
| 974 | add 4(%rsp),%r12d | |
| 975 | mov %edx,%r13d | |
| 976 | mov %edx,%r14d | |
| 977 | mov %r8d,%r15d | |
| 978 | ||
| 979 | ror $6,%r13d | |
| 980 | ror $11,%r14d | |
| 981 | xor %r9d,%r15d # f^g | |
| 982 | ||
| 983 | xor %r14d,%r13d | |
| 984 | ror $14,%r14d | |
| 985 | and %edx,%r15d # (f^g)&e | |
| 986 | mov %r12d,4(%rsp) | |
| 987 | ||
| 988 | xor %r14d,%r13d # Sigma1(e) | |
| 989 | xor %r9d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 990 | add %r10d,%r12d # T1+=h | |
| 991 | ||
| 992 | mov %r11d,%r10d | |
| 993 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 994 | ||
| 995 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 996 | mov %r11d,%r13d | |
| 997 | mov %r11d,%r14d | |
| 998 | ||
| 999 | ror $2,%r10d | |
| 1000 | ror $13,%r13d | |
| 1001 | mov %r11d,%r15d | |
| 1002 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 1003 | ||
| 1004 | xor %r13d,%r10d | |
| 1005 | ror $9,%r13d | |
| 1006 | or %ebx,%r14d # a|c | |
| 1007 | ||
| 1008 | xor %r13d,%r10d # h=Sigma0(a) | |
| 1009 | and %ebx,%r15d # a&c | |
| 1010 | add %r12d,%ecx # d+=T1 | |
| 1011 | ||
| 1012 | and %eax,%r14d # (a|c)&b | |
| 1013 | add %r12d,%r10d # h+=T1 | |
| 1014 | ||
| 1015 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 1016 | lea 1(%rdi),%rdi # round++ | |
| 1017 | ||
| 1018 | add %r14d,%r10d # h+=Maj(a,b,c) | |
| 1019 | mov 12(%rsp),%r13d | |
| 1020 | mov 0(%rsp),%r12d | |
| 1021 | ||
| 1022 | mov %r13d,%r15d | |
| 1023 | ||
| 1024 | shr $3,%r13d | |
| 1025 | ror $7,%r15d | |
| 1026 | ||
| 1027 | xor %r15d,%r13d | |
| 1028 | ror $11,%r15d | |
| 1029 | ||
| 1030 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 1031 | mov %r12d,%r14d | |
| 1032 | ||
| 1033 | shr $10,%r12d | |
| 1034 | ror $17,%r14d | |
| 1035 | ||
| 1036 | xor %r14d,%r12d | |
| 1037 | ror $2,%r14d | |
| 1038 | ||
| 1039 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 1040 | ||
| 1041 | add %r13d,%r12d | |
| 1042 | ||
| 1043 | add 44(%rsp),%r12d | |
| 1044 | ||
| 1045 | add 8(%rsp),%r12d | |
| 1046 | mov %ecx,%r13d | |
| 1047 | mov %ecx,%r14d | |
| 1048 | mov %edx,%r15d | |
| 1049 | ||
| 1050 | ror $6,%r13d | |
| 1051 | ror $11,%r14d | |
| 1052 | xor %r8d,%r15d # f^g | |
| 1053 | ||
| 1054 | xor %r14d,%r13d | |
| 1055 | ror $14,%r14d | |
| 1056 | and %ecx,%r15d # (f^g)&e | |
| 1057 | mov %r12d,8(%rsp) | |
| 1058 | ||
| 1059 | xor %r14d,%r13d # Sigma1(e) | |
| 1060 | xor %r8d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 1061 | add %r9d,%r12d # T1+=h | |
| 1062 | ||
| 1063 | mov %r10d,%r9d | |
| 1064 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 1065 | ||
| 1066 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 1067 | mov %r10d,%r13d | |
| 1068 | mov %r10d,%r14d | |
| 1069 | ||
| 1070 | ror $2,%r9d | |
| 1071 | ror $13,%r13d | |
| 1072 | mov %r10d,%r15d | |
| 1073 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 1074 | ||
| 1075 | xor %r13d,%r9d | |
| 1076 | ror $9,%r13d | |
| 1077 | or %eax,%r14d # a|c | |
| 1078 | ||
| 1079 | xor %r13d,%r9d # h=Sigma0(a) | |
| 1080 | and %eax,%r15d # a&c | |
| 1081 | add %r12d,%ebx # d+=T1 | |
| 1082 | ||
| 1083 | and %r11d,%r14d # (a|c)&b | |
| 1084 | add %r12d,%r9d # h+=T1 | |
| 1085 | ||
| 1086 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 1087 | lea 1(%rdi),%rdi # round++ | |
| 1088 | ||
| 1089 | add %r14d,%r9d # h+=Maj(a,b,c) | |
| 1090 | mov 16(%rsp),%r13d | |
| 1091 | mov 4(%rsp),%r12d | |
| 1092 | ||
| 1093 | mov %r13d,%r15d | |
| 1094 | ||
| 1095 | shr $3,%r13d | |
| 1096 | ror $7,%r15d | |
| 1097 | ||
| 1098 | xor %r15d,%r13d | |
| 1099 | ror $11,%r15d | |
| 1100 | ||
| 1101 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 1102 | mov %r12d,%r14d | |
| 1103 | ||
| 1104 | shr $10,%r12d | |
| 1105 | ror $17,%r14d | |
| 1106 | ||
| 1107 | xor %r14d,%r12d | |
| 1108 | ror $2,%r14d | |
| 1109 | ||
| 1110 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 1111 | ||
| 1112 | add %r13d,%r12d | |
| 1113 | ||
| 1114 | add 48(%rsp),%r12d | |
| 1115 | ||
| 1116 | add 12(%rsp),%r12d | |
| 1117 | mov %ebx,%r13d | |
| 1118 | mov %ebx,%r14d | |
| 1119 | mov %ecx,%r15d | |
| 1120 | ||
| 1121 | ror $6,%r13d | |
| 1122 | ror $11,%r14d | |
| 1123 | xor %edx,%r15d # f^g | |
| 1124 | ||
| 1125 | xor %r14d,%r13d | |
| 1126 | ror $14,%r14d | |
| 1127 | and %ebx,%r15d # (f^g)&e | |
| 1128 | mov %r12d,12(%rsp) | |
| 1129 | ||
| 1130 | xor %r14d,%r13d # Sigma1(e) | |
| 1131 | xor %edx,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 1132 | add %r8d,%r12d # T1+=h | |
| 1133 | ||
| 1134 | mov %r9d,%r8d | |
| 1135 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 1136 | ||
| 1137 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 1138 | mov %r9d,%r13d | |
| 1139 | mov %r9d,%r14d | |
| 1140 | ||
| 1141 | ror $2,%r8d | |
| 1142 | ror $13,%r13d | |
| 1143 | mov %r9d,%r15d | |
| 1144 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 1145 | ||
| 1146 | xor %r13d,%r8d | |
| 1147 | ror $9,%r13d | |
| 1148 | or %r11d,%r14d # a|c | |
| 1149 | ||
| 1150 | xor %r13d,%r8d # h=Sigma0(a) | |
| 1151 | and %r11d,%r15d # a&c | |
| 1152 | add %r12d,%eax # d+=T1 | |
| 1153 | ||
| 1154 | and %r10d,%r14d # (a|c)&b | |
| 1155 | add %r12d,%r8d # h+=T1 | |
| 1156 | ||
| 1157 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 1158 | lea 1(%rdi),%rdi # round++ | |
| 1159 | ||
| 1160 | add %r14d,%r8d # h+=Maj(a,b,c) | |
| 1161 | mov 20(%rsp),%r13d | |
| 1162 | mov 8(%rsp),%r12d | |
| 1163 | ||
| 1164 | mov %r13d,%r15d | |
| 1165 | ||
| 1166 | shr $3,%r13d | |
| 1167 | ror $7,%r15d | |
| 1168 | ||
| 1169 | xor %r15d,%r13d | |
| 1170 | ror $11,%r15d | |
| 1171 | ||
| 1172 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 1173 | mov %r12d,%r14d | |
| 1174 | ||
| 1175 | shr $10,%r12d | |
| 1176 | ror $17,%r14d | |
| 1177 | ||
| 1178 | xor %r14d,%r12d | |
| 1179 | ror $2,%r14d | |
| 1180 | ||
| 1181 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 1182 | ||
| 1183 | add %r13d,%r12d | |
| 1184 | ||
| 1185 | add 52(%rsp),%r12d | |
| 1186 | ||
| 1187 | add 16(%rsp),%r12d | |
| 1188 | mov %eax,%r13d | |
| 1189 | mov %eax,%r14d | |
| 1190 | mov %ebx,%r15d | |
| 1191 | ||
| 1192 | ror $6,%r13d | |
| 1193 | ror $11,%r14d | |
| 1194 | xor %ecx,%r15d # f^g | |
| 1195 | ||
| 1196 | xor %r14d,%r13d | |
| 1197 | ror $14,%r14d | |
| 1198 | and %eax,%r15d # (f^g)&e | |
| 1199 | mov %r12d,16(%rsp) | |
| 1200 | ||
| 1201 | xor %r14d,%r13d # Sigma1(e) | |
| 1202 | xor %ecx,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 1203 | add %edx,%r12d # T1+=h | |
| 1204 | ||
| 1205 | mov %r8d,%edx | |
| 1206 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 1207 | ||
| 1208 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 1209 | mov %r8d,%r13d | |
| 1210 | mov %r8d,%r14d | |
| 1211 | ||
| 1212 | ror $2,%edx | |
| 1213 | ror $13,%r13d | |
| 1214 | mov %r8d,%r15d | |
| 1215 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 1216 | ||
| 1217 | xor %r13d,%edx | |
| 1218 | ror $9,%r13d | |
| 1219 | or %r10d,%r14d # a|c | |
| 1220 | ||
| 1221 | xor %r13d,%edx # h=Sigma0(a) | |
| 1222 | and %r10d,%r15d # a&c | |
| 1223 | add %r12d,%r11d # d+=T1 | |
| 1224 | ||
| 1225 | and %r9d,%r14d # (a|c)&b | |
| 1226 | add %r12d,%edx # h+=T1 | |
| 1227 | ||
| 1228 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 1229 | lea 1(%rdi),%rdi # round++ | |
| 1230 | ||
| 1231 | add %r14d,%edx # h+=Maj(a,b,c) | |
| 1232 | mov 24(%rsp),%r13d | |
| 1233 | mov 12(%rsp),%r12d | |
| 1234 | ||
| 1235 | mov %r13d,%r15d | |
| 1236 | ||
| 1237 | shr $3,%r13d | |
| 1238 | ror $7,%r15d | |
| 1239 | ||
| 1240 | xor %r15d,%r13d | |
| 1241 | ror $11,%r15d | |
| 1242 | ||
| 1243 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 1244 | mov %r12d,%r14d | |
| 1245 | ||
| 1246 | shr $10,%r12d | |
| 1247 | ror $17,%r14d | |
| 1248 | ||
| 1249 | xor %r14d,%r12d | |
| 1250 | ror $2,%r14d | |
| 1251 | ||
| 1252 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 1253 | ||
| 1254 | add %r13d,%r12d | |
| 1255 | ||
| 1256 | add 56(%rsp),%r12d | |
| 1257 | ||
| 1258 | add 20(%rsp),%r12d | |
| 1259 | mov %r11d,%r13d | |
| 1260 | mov %r11d,%r14d | |
| 1261 | mov %eax,%r15d | |
| 1262 | ||
| 1263 | ror $6,%r13d | |
| 1264 | ror $11,%r14d | |
| 1265 | xor %ebx,%r15d # f^g | |
| 1266 | ||
| 1267 | xor %r14d,%r13d | |
| 1268 | ror $14,%r14d | |
| 1269 | and %r11d,%r15d # (f^g)&e | |
| 1270 | mov %r12d,20(%rsp) | |
| 1271 | ||
| 1272 | xor %r14d,%r13d # Sigma1(e) | |
| 1273 | xor %ebx,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 1274 | add %ecx,%r12d # T1+=h | |
| 1275 | ||
| 1276 | mov %edx,%ecx | |
| 1277 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 1278 | ||
| 1279 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 1280 | mov %edx,%r13d | |
| 1281 | mov %edx,%r14d | |
| 1282 | ||
| 1283 | ror $2,%ecx | |
| 1284 | ror $13,%r13d | |
| 1285 | mov %edx,%r15d | |
| 1286 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 1287 | ||
| 1288 | xor %r13d,%ecx | |
| 1289 | ror $9,%r13d | |
| 1290 | or %r9d,%r14d # a|c | |
| 1291 | ||
| 1292 | xor %r13d,%ecx # h=Sigma0(a) | |
| 1293 | and %r9d,%r15d # a&c | |
| 1294 | add %r12d,%r10d # d+=T1 | |
| 1295 | ||
| 1296 | and %r8d,%r14d # (a|c)&b | |
| 1297 | add %r12d,%ecx # h+=T1 | |
| 1298 | ||
| 1299 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 1300 | lea 1(%rdi),%rdi # round++ | |
| 1301 | ||
| 1302 | add %r14d,%ecx # h+=Maj(a,b,c) | |
| 1303 | mov 28(%rsp),%r13d | |
| 1304 | mov 16(%rsp),%r12d | |
| 1305 | ||
| 1306 | mov %r13d,%r15d | |
| 1307 | ||
| 1308 | shr $3,%r13d | |
| 1309 | ror $7,%r15d | |
| 1310 | ||
| 1311 | xor %r15d,%r13d | |
| 1312 | ror $11,%r15d | |
| 1313 | ||
| 1314 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 1315 | mov %r12d,%r14d | |
| 1316 | ||
| 1317 | shr $10,%r12d | |
| 1318 | ror $17,%r14d | |
| 1319 | ||
| 1320 | xor %r14d,%r12d | |
| 1321 | ror $2,%r14d | |
| 1322 | ||
| 1323 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 1324 | ||
| 1325 | add %r13d,%r12d | |
| 1326 | ||
| 1327 | add 60(%rsp),%r12d | |
| 1328 | ||
| 1329 | add 24(%rsp),%r12d | |
| 1330 | mov %r10d,%r13d | |
| 1331 | mov %r10d,%r14d | |
| 1332 | mov %r11d,%r15d | |
| 1333 | ||
| 1334 | ror $6,%r13d | |
| 1335 | ror $11,%r14d | |
| 1336 | xor %eax,%r15d # f^g | |
| 1337 | ||
| 1338 | xor %r14d,%r13d | |
| 1339 | ror $14,%r14d | |
| 1340 | and %r10d,%r15d # (f^g)&e | |
| 1341 | mov %r12d,24(%rsp) | |
| 1342 | ||
| 1343 | xor %r14d,%r13d # Sigma1(e) | |
| 1344 | xor %eax,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 1345 | add %ebx,%r12d # T1+=h | |
| 1346 | ||
| 1347 | mov %ecx,%ebx | |
| 1348 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 1349 | ||
| 1350 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 1351 | mov %ecx,%r13d | |
| 1352 | mov %ecx,%r14d | |
| 1353 | ||
| 1354 | ror $2,%ebx | |
| 1355 | ror $13,%r13d | |
| 1356 | mov %ecx,%r15d | |
| 1357 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 1358 | ||
| 1359 | xor %r13d,%ebx | |
| 1360 | ror $9,%r13d | |
| 1361 | or %r8d,%r14d # a|c | |
| 1362 | ||
| 1363 | xor %r13d,%ebx # h=Sigma0(a) | |
| 1364 | and %r8d,%r15d # a&c | |
| 1365 | add %r12d,%r9d # d+=T1 | |
| 1366 | ||
| 1367 | and %edx,%r14d # (a|c)&b | |
| 1368 | add %r12d,%ebx # h+=T1 | |
| 1369 | ||
| 1370 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 1371 | lea 1(%rdi),%rdi # round++ | |
| 1372 | ||
| 1373 | add %r14d,%ebx # h+=Maj(a,b,c) | |
| 1374 | mov 32(%rsp),%r13d | |
| 1375 | mov 20(%rsp),%r12d | |
| 1376 | ||
| 1377 | mov %r13d,%r15d | |
| 1378 | ||
| 1379 | shr $3,%r13d | |
| 1380 | ror $7,%r15d | |
| 1381 | ||
| 1382 | xor %r15d,%r13d | |
| 1383 | ror $11,%r15d | |
| 1384 | ||
| 1385 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 1386 | mov %r12d,%r14d | |
| 1387 | ||
| 1388 | shr $10,%r12d | |
| 1389 | ror $17,%r14d | |
| 1390 | ||
| 1391 | xor %r14d,%r12d | |
| 1392 | ror $2,%r14d | |
| 1393 | ||
| 1394 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 1395 | ||
| 1396 | add %r13d,%r12d | |
| 1397 | ||
| 1398 | add 0(%rsp),%r12d | |
| 1399 | ||
| 1400 | add 28(%rsp),%r12d | |
| 1401 | mov %r9d,%r13d | |
| 1402 | mov %r9d,%r14d | |
| 1403 | mov %r10d,%r15d | |
| 1404 | ||
| 1405 | ror $6,%r13d | |
| 1406 | ror $11,%r14d | |
| 1407 | xor %r11d,%r15d # f^g | |
| 1408 | ||
| 1409 | xor %r14d,%r13d | |
| 1410 | ror $14,%r14d | |
| 1411 | and %r9d,%r15d # (f^g)&e | |
| 1412 | mov %r12d,28(%rsp) | |
| 1413 | ||
| 1414 | xor %r14d,%r13d # Sigma1(e) | |
| 1415 | xor %r11d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 1416 | add %eax,%r12d # T1+=h | |
| 1417 | ||
| 1418 | mov %ebx,%eax | |
| 1419 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 1420 | ||
| 1421 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 1422 | mov %ebx,%r13d | |
| 1423 | mov %ebx,%r14d | |
| 1424 | ||
| 1425 | ror $2,%eax | |
| 1426 | ror $13,%r13d | |
| 1427 | mov %ebx,%r15d | |
| 1428 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 1429 | ||
| 1430 | xor %r13d,%eax | |
| 1431 | ror $9,%r13d | |
| 1432 | or %edx,%r14d # a|c | |
| 1433 | ||
| 1434 | xor %r13d,%eax # h=Sigma0(a) | |
| 1435 | and %edx,%r15d # a&c | |
| 1436 | add %r12d,%r8d # d+=T1 | |
| 1437 | ||
| 1438 | and %ecx,%r14d # (a|c)&b | |
| 1439 | add %r12d,%eax # h+=T1 | |
| 1440 | ||
| 1441 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 1442 | lea 1(%rdi),%rdi # round++ | |
| 1443 | ||
| 1444 | add %r14d,%eax # h+=Maj(a,b,c) | |
| 1445 | mov 36(%rsp),%r13d | |
| 1446 | mov 24(%rsp),%r12d | |
| 1447 | ||
| 1448 | mov %r13d,%r15d | |
| 1449 | ||
| 1450 | shr $3,%r13d | |
| 1451 | ror $7,%r15d | |
| 1452 | ||
| 1453 | xor %r15d,%r13d | |
| 1454 | ror $11,%r15d | |
| 1455 | ||
| 1456 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 1457 | mov %r12d,%r14d | |
| 1458 | ||
| 1459 | shr $10,%r12d | |
| 1460 | ror $17,%r14d | |
| 1461 | ||
| 1462 | xor %r14d,%r12d | |
| 1463 | ror $2,%r14d | |
| 1464 | ||
| 1465 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 1466 | ||
| 1467 | add %r13d,%r12d | |
| 1468 | ||
| 1469 | add 4(%rsp),%r12d | |
| 1470 | ||
| 1471 | add 32(%rsp),%r12d | |
| 1472 | mov %r8d,%r13d | |
| 1473 | mov %r8d,%r14d | |
| 1474 | mov %r9d,%r15d | |
| 1475 | ||
| 1476 | ror $6,%r13d | |
| 1477 | ror $11,%r14d | |
| 1478 | xor %r10d,%r15d # f^g | |
| 1479 | ||
| 1480 | xor %r14d,%r13d | |
| 1481 | ror $14,%r14d | |
| 1482 | and %r8d,%r15d # (f^g)&e | |
| 1483 | mov %r12d,32(%rsp) | |
| 1484 | ||
| 1485 | xor %r14d,%r13d # Sigma1(e) | |
| 1486 | xor %r10d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 1487 | add %r11d,%r12d # T1+=h | |
| 1488 | ||
| 1489 | mov %eax,%r11d | |
| 1490 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 1491 | ||
| 1492 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 1493 | mov %eax,%r13d | |
| 1494 | mov %eax,%r14d | |
| 1495 | ||
| 1496 | ror $2,%r11d | |
| 1497 | ror $13,%r13d | |
| 1498 | mov %eax,%r15d | |
| 1499 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 1500 | ||
| 1501 | xor %r13d,%r11d | |
| 1502 | ror $9,%r13d | |
| 1503 | or %ecx,%r14d # a|c | |
| 1504 | ||
| 1505 | xor %r13d,%r11d # h=Sigma0(a) | |
| 1506 | and %ecx,%r15d # a&c | |
| 1507 | add %r12d,%edx # d+=T1 | |
| 1508 | ||
| 1509 | and %ebx,%r14d # (a|c)&b | |
| 1510 | add %r12d,%r11d # h+=T1 | |
| 1511 | ||
| 1512 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 1513 | lea 1(%rdi),%rdi # round++ | |
| 1514 | ||
| 1515 | add %r14d,%r11d # h+=Maj(a,b,c) | |
| 1516 | mov 40(%rsp),%r13d | |
| 1517 | mov 28(%rsp),%r12d | |
| 1518 | ||
| 1519 | mov %r13d,%r15d | |
| 1520 | ||
| 1521 | shr $3,%r13d | |
| 1522 | ror $7,%r15d | |
| 1523 | ||
| 1524 | xor %r15d,%r13d | |
| 1525 | ror $11,%r15d | |
| 1526 | ||
| 1527 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 1528 | mov %r12d,%r14d | |
| 1529 | ||
| 1530 | shr $10,%r12d | |
| 1531 | ror $17,%r14d | |
| 1532 | ||
| 1533 | xor %r14d,%r12d | |
| 1534 | ror $2,%r14d | |
| 1535 | ||
| 1536 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 1537 | ||
| 1538 | add %r13d,%r12d | |
| 1539 | ||
| 1540 | add 8(%rsp),%r12d | |
| 1541 | ||
| 1542 | add 36(%rsp),%r12d | |
| 1543 | mov %edx,%r13d | |
| 1544 | mov %edx,%r14d | |
| 1545 | mov %r8d,%r15d | |
| 1546 | ||
| 1547 | ror $6,%r13d | |
| 1548 | ror $11,%r14d | |
| 1549 | xor %r9d,%r15d # f^g | |
| 1550 | ||
| 1551 | xor %r14d,%r13d | |
| 1552 | ror $14,%r14d | |
| 1553 | and %edx,%r15d # (f^g)&e | |
| 1554 | mov %r12d,36(%rsp) | |
| 1555 | ||
| 1556 | xor %r14d,%r13d # Sigma1(e) | |
| 1557 | xor %r9d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 1558 | add %r10d,%r12d # T1+=h | |
| 1559 | ||
| 1560 | mov %r11d,%r10d | |
| 1561 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 1562 | ||
| 1563 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 1564 | mov %r11d,%r13d | |
| 1565 | mov %r11d,%r14d | |
| 1566 | ||
| 1567 | ror $2,%r10d | |
| 1568 | ror $13,%r13d | |
| 1569 | mov %r11d,%r15d | |
| 1570 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 1571 | ||
| 1572 | xor %r13d,%r10d | |
| 1573 | ror $9,%r13d | |
| 1574 | or %ebx,%r14d # a|c | |
| 1575 | ||
| 1576 | xor %r13d,%r10d # h=Sigma0(a) | |
| 1577 | and %ebx,%r15d # a&c | |
| 1578 | add %r12d,%ecx # d+=T1 | |
| 1579 | ||
| 1580 | and %eax,%r14d # (a|c)&b | |
| 1581 | add %r12d,%r10d # h+=T1 | |
| 1582 | ||
| 1583 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 1584 | lea 1(%rdi),%rdi # round++ | |
| 1585 | ||
| 1586 | add %r14d,%r10d # h+=Maj(a,b,c) | |
| 1587 | mov 44(%rsp),%r13d | |
| 1588 | mov 32(%rsp),%r12d | |
| 1589 | ||
| 1590 | mov %r13d,%r15d | |
| 1591 | ||
| 1592 | shr $3,%r13d | |
| 1593 | ror $7,%r15d | |
| 1594 | ||
| 1595 | xor %r15d,%r13d | |
| 1596 | ror $11,%r15d | |
| 1597 | ||
| 1598 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 1599 | mov %r12d,%r14d | |
| 1600 | ||
| 1601 | shr $10,%r12d | |
| 1602 | ror $17,%r14d | |
| 1603 | ||
| 1604 | xor %r14d,%r12d | |
| 1605 | ror $2,%r14d | |
| 1606 | ||
| 1607 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 1608 | ||
| 1609 | add %r13d,%r12d | |
| 1610 | ||
| 1611 | add 12(%rsp),%r12d | |
| 1612 | ||
| 1613 | add 40(%rsp),%r12d | |
| 1614 | mov %ecx,%r13d | |
| 1615 | mov %ecx,%r14d | |
| 1616 | mov %edx,%r15d | |
| 1617 | ||
| 1618 | ror $6,%r13d | |
| 1619 | ror $11,%r14d | |
| 1620 | xor %r8d,%r15d # f^g | |
| 1621 | ||
| 1622 | xor %r14d,%r13d | |
| 1623 | ror $14,%r14d | |
| 1624 | and %ecx,%r15d # (f^g)&e | |
| 1625 | mov %r12d,40(%rsp) | |
| 1626 | ||
| 1627 | xor %r14d,%r13d # Sigma1(e) | |
| 1628 | xor %r8d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 1629 | add %r9d,%r12d # T1+=h | |
| 1630 | ||
| 1631 | mov %r10d,%r9d | |
| 1632 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 1633 | ||
| 1634 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 1635 | mov %r10d,%r13d | |
| 1636 | mov %r10d,%r14d | |
| 1637 | ||
| 1638 | ror $2,%r9d | |
| 1639 | ror $13,%r13d | |
| 1640 | mov %r10d,%r15d | |
| 1641 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 1642 | ||
| 1643 | xor %r13d,%r9d | |
| 1644 | ror $9,%r13d | |
| 1645 | or %eax,%r14d # a|c | |
| 1646 | ||
| 1647 | xor %r13d,%r9d # h=Sigma0(a) | |
| 1648 | and %eax,%r15d # a&c | |
| 1649 | add %r12d,%ebx # d+=T1 | |
| 1650 | ||
| 1651 | and %r11d,%r14d # (a|c)&b | |
| 1652 | add %r12d,%r9d # h+=T1 | |
| 1653 | ||
| 1654 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 1655 | lea 1(%rdi),%rdi # round++ | |
| 1656 | ||
| 1657 | add %r14d,%r9d # h+=Maj(a,b,c) | |
| 1658 | mov 48(%rsp),%r13d | |
| 1659 | mov 36(%rsp),%r12d | |
| 1660 | ||
| 1661 | mov %r13d,%r15d | |
| 1662 | ||
| 1663 | shr $3,%r13d | |
| 1664 | ror $7,%r15d | |
| 1665 | ||
| 1666 | xor %r15d,%r13d | |
| 1667 | ror $11,%r15d | |
| 1668 | ||
| 1669 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 1670 | mov %r12d,%r14d | |
| 1671 | ||
| 1672 | shr $10,%r12d | |
| 1673 | ror $17,%r14d | |
| 1674 | ||
| 1675 | xor %r14d,%r12d | |
| 1676 | ror $2,%r14d | |
| 1677 | ||
| 1678 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 1679 | ||
| 1680 | add %r13d,%r12d | |
| 1681 | ||
| 1682 | add 16(%rsp),%r12d | |
| 1683 | ||
| 1684 | add 44(%rsp),%r12d | |
| 1685 | mov %ebx,%r13d | |
| 1686 | mov %ebx,%r14d | |
| 1687 | mov %ecx,%r15d | |
| 1688 | ||
| 1689 | ror $6,%r13d | |
| 1690 | ror $11,%r14d | |
| 1691 | xor %edx,%r15d # f^g | |
| 1692 | ||
| 1693 | xor %r14d,%r13d | |
| 1694 | ror $14,%r14d | |
| 1695 | and %ebx,%r15d # (f^g)&e | |
| 1696 | mov %r12d,44(%rsp) | |
| 1697 | ||
| 1698 | xor %r14d,%r13d # Sigma1(e) | |
| 1699 | xor %edx,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 1700 | add %r8d,%r12d # T1+=h | |
| 1701 | ||
| 1702 | mov %r9d,%r8d | |
| 1703 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 1704 | ||
| 1705 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 1706 | mov %r9d,%r13d | |
| 1707 | mov %r9d,%r14d | |
| 1708 | ||
| 1709 | ror $2,%r8d | |
| 1710 | ror $13,%r13d | |
| 1711 | mov %r9d,%r15d | |
| 1712 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 1713 | ||
| 1714 | xor %r13d,%r8d | |
| 1715 | ror $9,%r13d | |
| 1716 | or %r11d,%r14d # a|c | |
| 1717 | ||
| 1718 | xor %r13d,%r8d # h=Sigma0(a) | |
| 1719 | and %r11d,%r15d # a&c | |
| 1720 | add %r12d,%eax # d+=T1 | |
| 1721 | ||
| 1722 | and %r10d,%r14d # (a|c)&b | |
| 1723 | add %r12d,%r8d # h+=T1 | |
| 1724 | ||
| 1725 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 1726 | lea 1(%rdi),%rdi # round++ | |
| 1727 | ||
| 1728 | add %r14d,%r8d # h+=Maj(a,b,c) | |
| 1729 | mov 52(%rsp),%r13d | |
| 1730 | mov 40(%rsp),%r12d | |
| 1731 | ||
| 1732 | mov %r13d,%r15d | |
| 1733 | ||
| 1734 | shr $3,%r13d | |
| 1735 | ror $7,%r15d | |
| 1736 | ||
| 1737 | xor %r15d,%r13d | |
| 1738 | ror $11,%r15d | |
| 1739 | ||
| 1740 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 1741 | mov %r12d,%r14d | |
| 1742 | ||
| 1743 | shr $10,%r12d | |
| 1744 | ror $17,%r14d | |
| 1745 | ||
| 1746 | xor %r14d,%r12d | |
| 1747 | ror $2,%r14d | |
| 1748 | ||
| 1749 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 1750 | ||
| 1751 | add %r13d,%r12d | |
| 1752 | ||
| 1753 | add 20(%rsp),%r12d | |
| 1754 | ||
| 1755 | add 48(%rsp),%r12d | |
| 1756 | mov %eax,%r13d | |
| 1757 | mov %eax,%r14d | |
| 1758 | mov %ebx,%r15d | |
| 1759 | ||
| 1760 | ror $6,%r13d | |
| 1761 | ror $11,%r14d | |
| 1762 | xor %ecx,%r15d # f^g | |
| 1763 | ||
| 1764 | xor %r14d,%r13d | |
| 1765 | ror $14,%r14d | |
| 1766 | and %eax,%r15d # (f^g)&e | |
| 1767 | mov %r12d,48(%rsp) | |
| 1768 | ||
| 1769 | xor %r14d,%r13d # Sigma1(e) | |
| 1770 | xor %ecx,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 1771 | add %edx,%r12d # T1+=h | |
| 1772 | ||
| 1773 | mov %r8d,%edx | |
| 1774 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 1775 | ||
| 1776 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 1777 | mov %r8d,%r13d | |
| 1778 | mov %r8d,%r14d | |
| 1779 | ||
| 1780 | ror $2,%edx | |
| 1781 | ror $13,%r13d | |
| 1782 | mov %r8d,%r15d | |
| 1783 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 1784 | ||
| 1785 | xor %r13d,%edx | |
| 1786 | ror $9,%r13d | |
| 1787 | or %r10d,%r14d # a|c | |
| 1788 | ||
| 1789 | xor %r13d,%edx # h=Sigma0(a) | |
| 1790 | and %r10d,%r15d # a&c | |
| 1791 | add %r12d,%r11d # d+=T1 | |
| 1792 | ||
| 1793 | and %r9d,%r14d # (a|c)&b | |
| 1794 | add %r12d,%edx # h+=T1 | |
| 1795 | ||
| 1796 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 1797 | lea 1(%rdi),%rdi # round++ | |
| 1798 | ||
| 1799 | add %r14d,%edx # h+=Maj(a,b,c) | |
| 1800 | mov 56(%rsp),%r13d | |
| 1801 | mov 44(%rsp),%r12d | |
| 1802 | ||
| 1803 | mov %r13d,%r15d | |
| 1804 | ||
| 1805 | shr $3,%r13d | |
| 1806 | ror $7,%r15d | |
| 1807 | ||
| 1808 | xor %r15d,%r13d | |
| 1809 | ror $11,%r15d | |
| 1810 | ||
| 1811 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 1812 | mov %r12d,%r14d | |
| 1813 | ||
| 1814 | shr $10,%r12d | |
| 1815 | ror $17,%r14d | |
| 1816 | ||
| 1817 | xor %r14d,%r12d | |
| 1818 | ror $2,%r14d | |
| 1819 | ||
| 1820 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 1821 | ||
| 1822 | add %r13d,%r12d | |
| 1823 | ||
| 1824 | add 24(%rsp),%r12d | |
| 1825 | ||
| 1826 | add 52(%rsp),%r12d | |
| 1827 | mov %r11d,%r13d | |
| 1828 | mov %r11d,%r14d | |
| 1829 | mov %eax,%r15d | |
| 1830 | ||
| 1831 | ror $6,%r13d | |
| 1832 | ror $11,%r14d | |
| 1833 | xor %ebx,%r15d # f^g | |
| 1834 | ||
| 1835 | xor %r14d,%r13d | |
| 1836 | ror $14,%r14d | |
| 1837 | and %r11d,%r15d # (f^g)&e | |
| 1838 | mov %r12d,52(%rsp) | |
| 1839 | ||
| 1840 | xor %r14d,%r13d # Sigma1(e) | |
| 1841 | xor %ebx,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 1842 | add %ecx,%r12d # T1+=h | |
| 1843 | ||
| 1844 | mov %edx,%ecx | |
| 1845 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 1846 | ||
| 1847 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 1848 | mov %edx,%r13d | |
| 1849 | mov %edx,%r14d | |
| 1850 | ||
| 1851 | ror $2,%ecx | |
| 1852 | ror $13,%r13d | |
| 1853 | mov %edx,%r15d | |
| 1854 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 1855 | ||
| 1856 | xor %r13d,%ecx | |
| 1857 | ror $9,%r13d | |
| 1858 | or %r9d,%r14d # a|c | |
| 1859 | ||
| 1860 | xor %r13d,%ecx # h=Sigma0(a) | |
| 1861 | and %r9d,%r15d # a&c | |
| 1862 | add %r12d,%r10d # d+=T1 | |
| 1863 | ||
| 1864 | and %r8d,%r14d # (a|c)&b | |
| 1865 | add %r12d,%ecx # h+=T1 | |
| 1866 | ||
| 1867 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 1868 | lea 1(%rdi),%rdi # round++ | |
| 1869 | ||
| 1870 | add %r14d,%ecx # h+=Maj(a,b,c) | |
| 1871 | mov 60(%rsp),%r13d | |
| 1872 | mov 48(%rsp),%r12d | |
| 1873 | ||
| 1874 | mov %r13d,%r15d | |
| 1875 | ||
| 1876 | shr $3,%r13d | |
| 1877 | ror $7,%r15d | |
| 1878 | ||
| 1879 | xor %r15d,%r13d | |
| 1880 | ror $11,%r15d | |
| 1881 | ||
| 1882 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 1883 | mov %r12d,%r14d | |
| 1884 | ||
| 1885 | shr $10,%r12d | |
| 1886 | ror $17,%r14d | |
| 1887 | ||
| 1888 | xor %r14d,%r12d | |
| 1889 | ror $2,%r14d | |
| 1890 | ||
| 1891 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 1892 | ||
| 1893 | add %r13d,%r12d | |
| 1894 | ||
| 1895 | add 28(%rsp),%r12d | |
| 1896 | ||
| 1897 | add 56(%rsp),%r12d | |
| 1898 | mov %r10d,%r13d | |
| 1899 | mov %r10d,%r14d | |
| 1900 | mov %r11d,%r15d | |
| 1901 | ||
| 1902 | ror $6,%r13d | |
| 1903 | ror $11,%r14d | |
| 1904 | xor %eax,%r15d # f^g | |
| 1905 | ||
| 1906 | xor %r14d,%r13d | |
| 1907 | ror $14,%r14d | |
| 1908 | and %r10d,%r15d # (f^g)&e | |
| 1909 | mov %r12d,56(%rsp) | |
| 1910 | ||
| 1911 | xor %r14d,%r13d # Sigma1(e) | |
| 1912 | xor %eax,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 1913 | add %ebx,%r12d # T1+=h | |
| 1914 | ||
| 1915 | mov %ecx,%ebx | |
| 1916 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 1917 | ||
| 1918 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 1919 | mov %ecx,%r13d | |
| 1920 | mov %ecx,%r14d | |
| 1921 | ||
| 1922 | ror $2,%ebx | |
| 1923 | ror $13,%r13d | |
| 1924 | mov %ecx,%r15d | |
| 1925 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 1926 | ||
| 1927 | xor %r13d,%ebx | |
| 1928 | ror $9,%r13d | |
| 1929 | or %r8d,%r14d # a|c | |
| 1930 | ||
| 1931 | xor %r13d,%ebx # h=Sigma0(a) | |
| 1932 | and %r8d,%r15d # a&c | |
| 1933 | add %r12d,%r9d # d+=T1 | |
| 1934 | ||
| 1935 | and %edx,%r14d # (a|c)&b | |
| 1936 | add %r12d,%ebx # h+=T1 | |
| 1937 | ||
| 1938 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 1939 | lea 1(%rdi),%rdi # round++ | |
| 1940 | ||
| 1941 | add %r14d,%ebx # h+=Maj(a,b,c) | |
| 1942 | mov 0(%rsp),%r13d | |
| 1943 | mov 52(%rsp),%r12d | |
| 1944 | ||
| 1945 | mov %r13d,%r15d | |
| 1946 | ||
| 1947 | shr $3,%r13d | |
| 1948 | ror $7,%r15d | |
| 1949 | ||
| 1950 | xor %r15d,%r13d | |
| 1951 | ror $11,%r15d | |
| 1952 | ||
| 1953 | xor %r15d,%r13d # sigma0(X[(i+1)&0xf]) | |
| 1954 | mov %r12d,%r14d | |
| 1955 | ||
| 1956 | shr $10,%r12d | |
| 1957 | ror $17,%r14d | |
| 1958 | ||
| 1959 | xor %r14d,%r12d | |
| 1960 | ror $2,%r14d | |
| 1961 | ||
| 1962 | xor %r14d,%r12d # sigma1(X[(i+14)&0xf]) | |
| 1963 | ||
| 1964 | add %r13d,%r12d | |
| 1965 | ||
| 1966 | add 32(%rsp),%r12d | |
| 1967 | ||
| 1968 | add 60(%rsp),%r12d | |
| 1969 | mov %r9d,%r13d | |
| 1970 | mov %r9d,%r14d | |
| 1971 | mov %r10d,%r15d | |
| 1972 | ||
| 1973 | ror $6,%r13d | |
| 1974 | ror $11,%r14d | |
| 1975 | xor %r11d,%r15d # f^g | |
| 1976 | ||
| 1977 | xor %r14d,%r13d | |
| 1978 | ror $14,%r14d | |
| 1979 | and %r9d,%r15d # (f^g)&e | |
| 1980 | mov %r12d,60(%rsp) | |
| 1981 | ||
| 1982 | xor %r14d,%r13d # Sigma1(e) | |
| 1983 | xor %r11d,%r15d # Ch(e,f,g)=((f^g)&e)^g | |
| 1984 | add %eax,%r12d # T1+=h | |
| 1985 | ||
| 1986 | mov %ebx,%eax | |
| 1987 | add %r13d,%r12d # T1+=Sigma1(e) | |
| 1988 | ||
| 1989 | add %r15d,%r12d # T1+=Ch(e,f,g) | |
| 1990 | mov %ebx,%r13d | |
| 1991 | mov %ebx,%r14d | |
| 1992 | ||
| 1993 | ror $2,%eax | |
| 1994 | ror $13,%r13d | |
| 1995 | mov %ebx,%r15d | |
| 1996 | add (%rbp,%rdi,4),%r12d # T1+=K[round] | |
| 1997 | ||
| 1998 | xor %r13d,%eax | |
| 1999 | ror $9,%r13d | |
| 2000 | or %edx,%r14d # a|c | |
| 2001 | ||
| 2002 | xor %r13d,%eax # h=Sigma0(a) | |
| 2003 | and %edx,%r15d # a&c | |
| 2004 | add %r12d,%r8d # d+=T1 | |
| 2005 | ||
| 2006 | and %ecx,%r14d # (a|c)&b | |
| 2007 | add %r12d,%eax # h+=T1 | |
| 2008 | ||
| 2009 | or %r15d,%r14d # Maj(a,b,c)=((a|c)&b)|(a&c) | |
| 2010 | lea 1(%rdi),%rdi # round++ | |
| 2011 | ||
| 2012 | add %r14d,%eax # h+=Maj(a,b,c) | |
| 2013 | cmp $64,%rdi | |
| 2014 | jb .Lrounds_16_xx | |
| 2015 | ||
| 2016 | mov 16*4+0*8(%rsp),%rdi | |
| 2017 | lea 16*4(%rsi),%rsi | |
| 2018 | ||
| 2019 | add 4*0(%rdi),%eax | |
| 2020 | add 4*1(%rdi),%ebx | |
| 2021 | add 4*2(%rdi),%ecx | |
| 2022 | add 4*3(%rdi),%edx | |
| 2023 | add 4*4(%rdi),%r8d | |
| 2024 | add 4*5(%rdi),%r9d | |
| 2025 | add 4*6(%rdi),%r10d | |
| 2026 | add 4*7(%rdi),%r11d | |
| 2027 | ||
| 2028 | cmp 16*4+2*8(%rsp),%rsi | |
| 2029 | ||
| 2030 | mov %eax,4*0(%rdi) | |
| 2031 | mov %ebx,4*1(%rdi) | |
| 2032 | mov %ecx,4*2(%rdi) | |
| 2033 | mov %edx,4*3(%rdi) | |
| 2034 | mov %r8d,4*4(%rdi) | |
| 2035 | mov %r9d,4*5(%rdi) | |
| 2036 | mov %r10d,4*6(%rdi) | |
| 2037 | mov %r11d,4*7(%rdi) | |
| 2038 | jb .Lloop | |
| 2039 | ||
| 2040 | mov 16*4+3*8(%rsp),%rsp | |
| a9c93ac5 | 2041 | .cfi_def_cfa %rsp,56 |
| 0b04990a | 2042 | pop %r15 |
| a9c93ac5 AF |
2043 | .cfi_adjust_cfa_offset -8 |
| 2044 | .cfi_restore %r15 | |
| 0b04990a | 2045 | pop %r14 |
| a9c93ac5 AF |
2046 | .cfi_adjust_cfa_offset -8 |
| 2047 | .cfi_restore %r14 | |
| 0b04990a | 2048 | pop %r13 |
| a9c93ac5 AF |
2049 | .cfi_adjust_cfa_offset -8 |
| 2050 | .cfi_restore %r13 | |
| 0b04990a | 2051 | pop %r12 |
| a9c93ac5 AF |
2052 | .cfi_adjust_cfa_offset -8 |
| 2053 | .cfi_restore %r12 | |
| 0b04990a | 2054 | pop %rbp |
| a9c93ac5 AF |
2055 | .cfi_adjust_cfa_offset -8 |
| 2056 | .cfi_restore %rbp | |
| 0b04990a | 2057 | pop %rbx |
| a9c93ac5 AF |
2058 | .cfi_adjust_cfa_offset -8 |
| 2059 | .cfi_restore %rbx | |
| 0b04990a TC |
2060 | |
| 2061 | ret | |
| a9c93ac5 | 2062 | .cfi_endproc |
| 0b04990a TC |
2063 | SET_SIZE(SHA256TransformBlocks) |
| 2064 | ||
| 18168da7 | 2065 | .section .rodata |
| 0b04990a TC |
2066 | .align 64 |
| 2067 | .type K256,@object | |
| 2068 | K256: | |
| 2069 | .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 | |
| 2070 | .long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 | |
| 2071 | .long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 | |
| 2072 | .long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 | |
| 2073 | .long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc | |
| 2074 | .long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da | |
| 2075 | .long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 | |
| 2076 | .long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 | |
| 2077 | .long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 | |
| 2078 | .long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 | |
| 2079 | .long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 | |
| 2080 | .long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 | |
| 2081 | .long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 | |
| 2082 | .long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 | |
| 2083 | .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 | |
| 2084 | .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 | |
| 2085 | #endif /* !lint && !__lint */ | |
| a3600a10 JZ |
2086 | |
| 2087 | #ifdef __ELF__ | |
| 2088 | .section .note.GNU-stack,"",%progbits | |
| 2089 | #endif |