1 // Copyright 2012 The Go Authors. All rights reserved. 2 // Use of this source code is governed by a BSD-style 3 // license that can be found in the LICENSE file. 4 5 // This code was translated into a form compatible with 6a from the public 6 // domain sources in SUPERCOP: http://bench.cr.yp.to/supercop.html 7 8 // +build amd64,!gccgo,!appengine 9 10 // func poly1305(out *[16]byte, m *byte, mlen uint64, key *[32]key) 11 TEXT poly1305(SB),0,$224-32 12 MOVQ out+0(FP),DI 13 MOVQ m+8(FP),SI 14 MOVQ mlen+16(FP),DX 15 MOVQ key+24(FP),CX 16 17 MOVQ SP,R11 18 MOVQ $31,R9 19 NOTQ R9 20 ANDQ R9,SP 21 ADDQ $32,SP 22 23 MOVQ R11,32(SP) 24 MOVQ R12,40(SP) 25 MOVQ R13,48(SP) 26 MOVQ R14,56(SP) 27 MOVQ R15,64(SP) 28 MOVQ BX,72(SP) 29 MOVQ BP,80(SP) 30 FLDCW ROUNDING(SB) 31 MOVL 0(CX),R8 32 MOVL 4(CX),R9 33 MOVL 8(CX),AX 34 MOVL 12(CX),R10 35 MOVQ DI,88(SP) 36 MOVQ CX,96(SP) 37 MOVL $0X43300000,108(SP) 38 MOVL $0X45300000,116(SP) 39 MOVL $0X47300000,124(SP) 40 MOVL $0X49300000,132(SP) 41 ANDL $0X0FFFFFFF,R8 42 ANDL $0X0FFFFFFC,R9 43 ANDL $0X0FFFFFFC,AX 44 ANDL $0X0FFFFFFC,R10 45 MOVL R8,104(SP) 46 MOVL R9,112(SP) 47 MOVL AX,120(SP) 48 MOVL R10,128(SP) 49 FMOVD 104(SP), F0 50 FSUBD DOFFSET0(SB), F0 51 FMOVD 112(SP), F0 52 FSUBD DOFFSET1(SB), F0 53 FMOVD 120(SP), F0 54 FSUBD DOFFSET2(SB), F0 55 FMOVD 128(SP), F0 56 FSUBD DOFFSET3(SB), F0 57 FXCHD F0, F3 58 FMOVDP F0, 136(SP) 59 FXCHD F0, F1 60 FMOVD F0, 144(SP) 61 FMULD SCALE(SB), F0 62 FMOVDP F0, 152(SP) 63 FMOVD F0, 160(SP) 64 FMULD SCALE(SB), F0 65 FMOVDP F0, 168(SP) 66 FMOVD F0, 176(SP) 67 FMULD SCALE(SB), F0 68 FMOVDP F0, 184(SP) 69 FLDZ 70 FLDZ 71 FLDZ 72 FLDZ 73 CMPQ DX,$16 74 JB ADDATMOST15BYTES 75 INITIALATLEAST16BYTES: 76 MOVL 12(SI),DI 77 MOVL 8(SI),CX 78 MOVL 4(SI),R8 79 MOVL 0(SI),R9 80 MOVL DI,128(SP) 81 MOVL CX,120(SP) 82 MOVL R8,112(SP) 83 MOVL R9,104(SP) 84 ADDQ $16,SI 85 SUBQ $16,DX 86 FXCHD F0, F3 87 FADDD 128(SP), F0 88 FSUBD DOFFSET3MINUSTWO128(SB), F0 89 FXCHD F0, F1 90 FADDD 112(SP), F0 91 FSUBD DOFFSET1(SB), F0 92 FXCHD F0, F2 93 FADDD 120(SP), F0 94 FSUBD DOFFSET2(SB), F0 95 FXCHD F0, F3 96 FADDD 104(SP), F0 97 FSUBD DOFFSET0(SB), F0 98 CMPQ DX,$16 99 JB MULTIPLYADDATMOST15BYTES 100 MULTIPLYADDATLEAST16BYTES: 101 MOVL 12(SI),DI 102 MOVL 8(SI),CX 103 MOVL 4(SI),R8 104 MOVL 0(SI),R9 105 MOVL DI,128(SP) 106 MOVL CX,120(SP) 107 MOVL R8,112(SP) 108 MOVL R9,104(SP) 109 ADDQ $16,SI 110 SUBQ $16,DX 111 FMOVD ALPHA130(SB), F0 112 FADDD F2,F0 113 FSUBD ALPHA130(SB), F0 114 FSUBD F0,F2 115 FMULD SCALE(SB), F0 116 FMOVD ALPHA32(SB), F0 117 FADDD F2,F0 118 FSUBD ALPHA32(SB), F0 119 FSUBD F0,F2 120 FXCHD F0, F2 121 FADDDP F0,F1 122 FMOVD ALPHA64(SB), F0 123 FADDD F4,F0 124 FSUBD ALPHA64(SB), F0 125 FSUBD F0,F4 126 FMOVD ALPHA96(SB), F0 127 FADDD F6,F0 128 FSUBD ALPHA96(SB), F0 129 FSUBD F0,F6 130 FXCHD F0, F6 131 FADDDP F0,F1 132 FXCHD F0, F3 133 FADDDP F0,F5 134 FXCHD F0, F3 135 FADDDP F0,F1 136 FMOVD 176(SP), F0 137 FMULD F3,F0 138 FMOVD 160(SP), F0 139 FMULD F4,F0 140 FMOVD 144(SP), F0 141 FMULD F5,F0 142 FMOVD 136(SP), F0 143 FMULDP F0,F6 144 FMOVD 160(SP), F0 145 FMULD F4,F0 146 FADDDP F0,F3 147 FMOVD 144(SP), F0 148 FMULD F4,F0 149 FADDDP F0,F2 150 FMOVD 136(SP), F0 151 FMULD F4,F0 152 FADDDP F0,F1 153 FMOVD 184(SP), F0 154 FMULDP F0,F4 155 FXCHD F0, F3 156 FADDDP F0,F5 157 FMOVD 144(SP), F0 158 FMULD F4,F0 159 FADDDP F0,F2 160 FMOVD 136(SP), F0 161 FMULD F4,F0 162 FADDDP F0,F1 163 FMOVD 184(SP), F0 164 FMULD F4,F0 165 FADDDP F0,F3 166 FMOVD 168(SP), F0 167 FMULDP F0,F4 168 FXCHD F0, F3 169 FADDDP F0,F4 170 FMOVD 136(SP), F0 171 FMULD F5,F0 172 FADDDP F0,F1 173 FXCHD F0, F3 174 FMOVD 184(SP), F0 175 FMULD F5,F0 176 FADDDP F0,F3 177 FXCHD F0, F1 178 FMOVD 168(SP), F0 179 FMULD F5,F0 180 FADDDP F0,F1 181 FMOVD 152(SP), F0 182 FMULDP F0,F5 183 FXCHD F0, F4 184 FADDDP F0,F1 185 CMPQ DX,$16 186 FXCHD F0, F2 187 FMOVD 128(SP), F0 188 FSUBD DOFFSET3MINUSTWO128(SB), F0 189 FADDDP F0,F1 190 FXCHD F0, F1 191 FMOVD 120(SP), F0 192 FSUBD DOFFSET2(SB), F0 193 FADDDP F0,F1 194 FXCHD F0, F3 195 FMOVD 112(SP), F0 196 FSUBD DOFFSET1(SB), F0 197 FADDDP F0,F1 198 FXCHD F0, F2 199 FMOVD 104(SP), F0 200 FSUBD DOFFSET0(SB), F0 201 FADDDP F0,F1 202 JAE MULTIPLYADDATLEAST16BYTES 203 MULTIPLYADDATMOST15BYTES: 204 FMOVD ALPHA130(SB), F0 205 FADDD F2,F0 206 FSUBD ALPHA130(SB), F0 207 FSUBD F0,F2 208 FMULD SCALE(SB), F0 209 FMOVD ALPHA32(SB), F0 210 FADDD F2,F0 211 FSUBD ALPHA32(SB), F0 212 FSUBD F0,F2 213 FMOVD ALPHA64(SB), F0 214 FADDD F5,F0 215 FSUBD ALPHA64(SB), F0 216 FSUBD F0,F5 217 FMOVD ALPHA96(SB), F0 218 FADDD F7,F0 219 FSUBD ALPHA96(SB), F0 220 FSUBD F0,F7 221 FXCHD F0, F7 222 FADDDP F0,F1 223 FXCHD F0, F5 224 FADDDP F0,F1 225 FXCHD F0, F3 226 FADDDP F0,F5 227 FADDDP F0,F1 228 FMOVD 176(SP), F0 229 FMULD F1,F0 230 FMOVD 160(SP), F0 231 FMULD F2,F0 232 FMOVD 144(SP), F0 233 FMULD F3,F0 234 FMOVD 136(SP), F0 235 FMULDP F0,F4 236 FMOVD 160(SP), F0 237 FMULD F5,F0 238 FADDDP F0,F3 239 FMOVD 144(SP), F0 240 FMULD F5,F0 241 FADDDP F0,F2 242 FMOVD 136(SP), F0 243 FMULD F5,F0 244 FADDDP F0,F1 245 FMOVD 184(SP), F0 246 FMULDP F0,F5 247 FXCHD F0, F4 248 FADDDP F0,F3 249 FMOVD 144(SP), F0 250 FMULD F5,F0 251 FADDDP F0,F2 252 FMOVD 136(SP), F0 253 FMULD F5,F0 254 FADDDP F0,F1 255 FMOVD 184(SP), F0 256 FMULD F5,F0 257 FADDDP F0,F4 258 FMOVD 168(SP), F0 259 FMULDP F0,F5 260 FXCHD F0, F4 261 FADDDP F0,F2 262 FMOVD 136(SP), F0 263 FMULD F5,F0 264 FADDDP F0,F1 265 FMOVD 184(SP), F0 266 FMULD F5,F0 267 FADDDP F0,F4 268 FMOVD 168(SP), F0 269 FMULD F5,F0 270 FADDDP F0,F3 271 FMOVD 152(SP), F0 272 FMULDP F0,F5 273 FXCHD F0, F4 274 FADDDP F0,F1 275 ADDATMOST15BYTES: 276 CMPQ DX,$0 277 JE NOMOREBYTES 278 MOVL $0,0(SP) 279 MOVL $0, 4 (SP) 280 MOVL $0, 8 (SP) 281 MOVL $0, 12 (SP) 282 LEAQ 0(SP),DI 283 MOVQ DX,CX 284 REP; MOVSB 285 MOVB $1,0(DI) 286 MOVL 12 (SP),DI 287 MOVL 8 (SP),SI 288 MOVL 4 (SP),DX 289 MOVL 0(SP),CX 290 MOVL DI,128(SP) 291 MOVL SI,120(SP) 292 MOVL DX,112(SP) 293 MOVL CX,104(SP) 294 FXCHD F0, F3 295 FADDD 128(SP), F0 296 FSUBD DOFFSET3(SB), F0 297 FXCHD F0, F2 298 FADDD 120(SP), F0 299 FSUBD DOFFSET2(SB), F0 300 FXCHD F0, F1 301 FADDD 112(SP), F0 302 FSUBD DOFFSET1(SB), F0 303 FXCHD F0, F3 304 FADDD 104(SP), F0 305 FSUBD DOFFSET0(SB), F0 306 FMOVD ALPHA130(SB), F0 307 FADDD F3,F0 308 FSUBD ALPHA130(SB), F0 309 FSUBD F0,F3 310 FMULD SCALE(SB), F0 311 FMOVD ALPHA32(SB), F0 312 FADDD F2,F0 313 FSUBD ALPHA32(SB), F0 314 FSUBD F0,F2 315 FMOVD ALPHA64(SB), F0 316 FADDD F6,F0 317 FSUBD ALPHA64(SB), F0 318 FSUBD F0,F6 319 FMOVD ALPHA96(SB), F0 320 FADDD F5,F0 321 FSUBD ALPHA96(SB), F0 322 FSUBD F0,F5 323 FXCHD F0, F4 324 FADDDP F0,F3 325 FXCHD F0, F6 326 FADDDP F0,F1 327 FXCHD F0, F3 328 FADDDP F0,F5 329 FXCHD F0, F3 330 FADDDP F0,F1 331 FMOVD 176(SP), F0 332 FMULD F3,F0 333 FMOVD 160(SP), F0 334 FMULD F4,F0 335 FMOVD 144(SP), F0 336 FMULD F5,F0 337 FMOVD 136(SP), F0 338 FMULDP F0,F6 339 FMOVD 160(SP), F0 340 FMULD F5,F0 341 FADDDP F0,F3 342 FMOVD 144(SP), F0 343 FMULD F5,F0 344 FADDDP F0,F2 345 FMOVD 136(SP), F0 346 FMULD F5,F0 347 FADDDP F0,F1 348 FMOVD 184(SP), F0 349 FMULDP F0,F5 350 FXCHD F0, F4 351 FADDDP F0,F5 352 FMOVD 144(SP), F0 353 FMULD F6,F0 354 FADDDP F0,F2 355 FMOVD 136(SP), F0 356 FMULD F6,F0 357 FADDDP F0,F1 358 FMOVD 184(SP), F0 359 FMULD F6,F0 360 FADDDP F0,F4 361 FMOVD 168(SP), F0 362 FMULDP F0,F6 363 FXCHD F0, F5 364 FADDDP F0,F4 365 FMOVD 136(SP), F0 366 FMULD F2,F0 367 FADDDP F0,F1 368 FMOVD 184(SP), F0 369 FMULD F2,F0 370 FADDDP F0,F5 371 FMOVD 168(SP), F0 372 FMULD F2,F0 373 FADDDP F0,F3 374 FMOVD 152(SP), F0 375 FMULDP F0,F2 376 FXCHD F0, F1 377 FADDDP F0,F3 378 FXCHD F0, F3 379 FXCHD F0, F2 380 NOMOREBYTES: 381 MOVL $0,R10 382 FMOVD ALPHA130(SB), F0 383 FADDD F4,F0 384 FSUBD ALPHA130(SB), F0 385 FSUBD F0,F4 386 FMULD SCALE(SB), F0 387 FMOVD ALPHA32(SB), F0 388 FADDD F2,F0 389 FSUBD ALPHA32(SB), F0 390 FSUBD F0,F2 391 FMOVD ALPHA64(SB), F0 392 FADDD F4,F0 393 FSUBD ALPHA64(SB), F0 394 FSUBD F0,F4 395 FMOVD ALPHA96(SB), F0 396 FADDD F6,F0 397 FSUBD ALPHA96(SB), F0 398 FXCHD F0, F6 399 FSUBD F6,F0 400 FXCHD F0, F4 401 FADDDP F0,F3 402 FXCHD F0, F4 403 FADDDP F0,F1 404 FXCHD F0, F2 405 FADDDP F0,F3 406 FXCHD F0, F4 407 FADDDP F0,F3 408 FXCHD F0, F3 409 FADDD HOFFSET0(SB), F0 410 FXCHD F0, F3 411 FADDD HOFFSET1(SB), F0 412 FXCHD F0, F1 413 FADDD HOFFSET2(SB), F0 414 FXCHD F0, F2 415 FADDD HOFFSET3(SB), F0 416 FXCHD F0, F3 417 FMOVDP F0, 104(SP) 418 FMOVDP F0, 112(SP) 419 FMOVDP F0, 120(SP) 420 FMOVDP F0, 128(SP) 421 MOVL 108(SP),DI 422 ANDL $63,DI 423 MOVL 116(SP),SI 424 ANDL $63,SI 425 MOVL 124(SP),DX 426 ANDL $63,DX 427 MOVL 132(SP),CX 428 ANDL $63,CX 429 MOVL 112(SP),R8 430 ADDL DI,R8 431 MOVQ R8,112(SP) 432 MOVL 120(SP),DI 433 ADCL SI,DI 434 MOVQ DI,120(SP) 435 MOVL 128(SP),DI 436 ADCL DX,DI 437 MOVQ DI,128(SP) 438 MOVL R10,DI 439 ADCL CX,DI 440 MOVQ DI,136(SP) 441 MOVQ $5,DI 442 MOVL 104(SP),SI 443 ADDL SI,DI 444 MOVQ DI,104(SP) 445 MOVL R10,DI 446 MOVQ 112(SP),DX 447 ADCL DX,DI 448 MOVQ DI,112(SP) 449 MOVL R10,DI 450 MOVQ 120(SP),CX 451 ADCL CX,DI 452 MOVQ DI,120(SP) 453 MOVL R10,DI 454 MOVQ 128(SP),R8 455 ADCL R8,DI 456 MOVQ DI,128(SP) 457 MOVQ $0XFFFFFFFC,DI 458 MOVQ 136(SP),R9 459 ADCL R9,DI 460 SARL $16,DI 461 MOVQ DI,R9 462 XORL $0XFFFFFFFF,R9 463 ANDQ DI,SI 464 MOVQ 104(SP),AX 465 ANDQ R9,AX 466 ORQ AX,SI 467 ANDQ DI,DX 468 MOVQ 112(SP),AX 469 ANDQ R9,AX 470 ORQ AX,DX 471 ANDQ DI,CX 472 MOVQ 120(SP),AX 473 ANDQ R9,AX 474 ORQ AX,CX 475 ANDQ DI,R8 476 MOVQ 128(SP),DI 477 ANDQ R9,DI 478 ORQ DI,R8 479 MOVQ 88(SP),DI 480 MOVQ 96(SP),R9 481 ADDL 16(R9),SI 482 ADCL 20(R9),DX 483 ADCL 24(R9),CX 484 ADCL 28(R9),R8 485 MOVL SI,0(DI) 486 MOVL DX,4(DI) 487 MOVL CX,8(DI) 488 MOVL R8,12(DI) 489 MOVQ 32(SP),R11 490 MOVQ 40(SP),R12 491 MOVQ 48(SP),R13 492 MOVQ 56(SP),R14 493 MOVQ 64(SP),R15 494 MOVQ 72(SP),BX 495 MOVQ 80(SP),BP 496 MOVQ R11,SP 497 RET 498
