| 1 |
// 20240504 djb: add note.GNU-stack |
| 2 |
// 20221231 djb: port hidden to macos; tnx thom wiggers |
| 3 |
// 20221230 djb: add linker line |
| 4 |
|
| 5 |
// linker define vec_mul_sp_asm |
| 6 |
|
| 7 |
#include "crypto_asm_hidden.h" |
| 8 |
|
| 9 |
#define vec_mul_sp_asm CRYPTO_SHARED_NAMESPACE(vec_mul_sp_asm) |
| 10 |
#define _vec_mul_sp_asm _CRYPTO_SHARED_NAMESPACE(vec_mul_sp_asm) |
| 11 |
|
| 12 |
# qhasm: int64 input_0 |
| 13 |
|
| 14 |
# qhasm: int64 input_1 |
| 15 |
|
| 16 |
# qhasm: int64 input_2 |
| 17 |
|
| 18 |
# qhasm: int64 input_3 |
| 19 |
|
| 20 |
# qhasm: int64 input_4 |
| 21 |
|
| 22 |
# qhasm: int64 input_5 |
| 23 |
|
| 24 |
# qhasm: stack64 input_6 |
| 25 |
|
| 26 |
# qhasm: stack64 input_7 |
| 27 |
|
| 28 |
# qhasm: int64 caller_r11 |
| 29 |
|
| 30 |
# qhasm: int64 caller_r12 |
| 31 |
|
| 32 |
# qhasm: int64 caller_r13 |
| 33 |
|
| 34 |
# qhasm: int64 caller_r14 |
| 35 |
|
| 36 |
# qhasm: int64 caller_r15 |
| 37 |
|
| 38 |
# qhasm: int64 caller_rbx |
| 39 |
|
| 40 |
# qhasm: int64 caller_rbp |
| 41 |
|
| 42 |
# qhasm: reg256 s0 |
| 43 |
|
| 44 |
# qhasm: reg256 s1 |
| 45 |
|
| 46 |
# qhasm: reg256 s2 |
| 47 |
|
| 48 |
# qhasm: reg256 s3 |
| 49 |
|
| 50 |
# qhasm: reg256 s4 |
| 51 |
|
| 52 |
# qhasm: reg256 s5 |
| 53 |
|
| 54 |
# qhasm: reg256 b0 |
| 55 |
|
| 56 |
# qhasm: reg256 b1 |
| 57 |
|
| 58 |
# qhasm: reg256 b2 |
| 59 |
|
| 60 |
# qhasm: reg256 b3 |
| 61 |
|
| 62 |
# qhasm: reg256 b4 |
| 63 |
|
| 64 |
# qhasm: reg256 b5 |
| 65 |
|
| 66 |
# qhasm: reg256 a0 |
| 67 |
|
| 68 |
# qhasm: reg256 a1 |
| 69 |
|
| 70 |
# qhasm: reg256 a2 |
| 71 |
|
| 72 |
# qhasm: reg256 a3 |
| 73 |
|
| 74 |
# qhasm: reg256 a4 |
| 75 |
|
| 76 |
# qhasm: reg256 a5 |
| 77 |
|
| 78 |
# qhasm: reg256 r0 |
| 79 |
|
| 80 |
# qhasm: reg256 r1 |
| 81 |
|
| 82 |
# qhasm: reg256 r2 |
| 83 |
|
| 84 |
# qhasm: reg256 r3 |
| 85 |
|
| 86 |
# qhasm: reg256 r4 |
| 87 |
|
| 88 |
# qhasm: reg256 r5 |
| 89 |
|
| 90 |
# qhasm: reg256 r6 |
| 91 |
|
| 92 |
# qhasm: reg256 r7 |
| 93 |
|
| 94 |
# qhasm: reg256 r8 |
| 95 |
|
| 96 |
# qhasm: reg256 r9 |
| 97 |
|
| 98 |
# qhasm: reg256 r10 |
| 99 |
|
| 100 |
# qhasm: reg256 r11 |
| 101 |
|
| 102 |
# qhasm: reg256 r12 |
| 103 |
|
| 104 |
# qhasm: reg256 r13 |
| 105 |
|
| 106 |
# qhasm: reg256 r14 |
| 107 |
|
| 108 |
# qhasm: reg256 r15 |
| 109 |
|
| 110 |
# qhasm: reg256 r16 |
| 111 |
|
| 112 |
# qhasm: reg256 r17 |
| 113 |
|
| 114 |
# qhasm: reg256 r18 |
| 115 |
|
| 116 |
# qhasm: reg256 r19 |
| 117 |
|
| 118 |
# qhasm: reg256 r20 |
| 119 |
|
| 120 |
# qhasm: reg256 r21 |
| 121 |
|
| 122 |
# qhasm: reg256 r22 |
| 123 |
|
| 124 |
# qhasm: reg256 r |
| 125 |
|
| 126 |
# qhasm: int64 h0 |
| 127 |
|
| 128 |
# qhasm: int64 h1 |
| 129 |
|
| 130 |
# qhasm: int64 h2 |
| 131 |
|
| 132 |
# qhasm: int64 h3 |
| 133 |
|
| 134 |
# qhasm: int64 h4 |
| 135 |
|
| 136 |
# qhasm: int64 h5 |
| 137 |
|
| 138 |
# qhasm: int64 h6 |
| 139 |
|
| 140 |
# qhasm: int64 h7 |
| 141 |
|
| 142 |
# qhasm: int64 h8 |
| 143 |
|
| 144 |
# qhasm: int64 h9 |
| 145 |
|
| 146 |
# qhasm: int64 h10 |
| 147 |
|
| 148 |
# qhasm: int64 h11 |
| 149 |
|
| 150 |
# qhasm: int64 h12 |
| 151 |
|
| 152 |
# qhasm: int64 h13 |
| 153 |
|
| 154 |
# qhasm: int64 h14 |
| 155 |
|
| 156 |
# qhasm: int64 h15 |
| 157 |
|
| 158 |
# qhasm: int64 h16 |
| 159 |
|
| 160 |
# qhasm: int64 h17 |
| 161 |
|
| 162 |
# qhasm: int64 h18 |
| 163 |
|
| 164 |
# qhasm: int64 h19 |
| 165 |
|
| 166 |
# qhasm: int64 h20 |
| 167 |
|
| 168 |
# qhasm: int64 h21 |
| 169 |
|
| 170 |
# qhasm: int64 h22 |
| 171 |
|
| 172 |
# qhasm: stack4864 buf |
| 173 |
|
| 174 |
# qhasm: int64 ptr |
| 175 |
|
| 176 |
# qhasm: int64 tmp |
| 177 |
|
| 178 |
# qhasm: stack64 r11_stack |
| 179 |
|
| 180 |
# qhasm: stack64 r12_stack |
| 181 |
|
| 182 |
# qhasm: stack64 r13_stack |
| 183 |
|
| 184 |
# qhasm: stack64 r14_stack |
| 185 |
|
| 186 |
# qhasm: stack64 r15_stack |
| 187 |
|
| 188 |
# qhasm: stack64 rbx_stack |
| 189 |
|
| 190 |
# qhasm: stack64 rbp_stack |
| 191 |
|
| 192 |
# qhasm: enter vec_mul_sp_asm |
| 193 |
.p2align 5 |
| 194 |
ASM_HIDDEN _vec_mul_sp_asm |
| 195 |
ASM_HIDDEN vec_mul_sp_asm |
| 196 |
.global _vec_mul_sp_asm |
| 197 |
.global vec_mul_sp_asm |
| 198 |
_vec_mul_sp_asm: |
| 199 |
vec_mul_sp_asm: |
| 200 |
mov %rsp,%r11 |
| 201 |
AND $31,%r11 |
| 202 |
add $672,%r11 |
| 203 |
sub %r11,%rsp |
| 204 |
|
| 205 |
# qhasm: r11_stack = caller_r11 |
| 206 |
# asm 1: movq <caller_r11=int64#9,>r11_stack=stack64#1 |
| 207 |
# asm 2: movq <caller_r11=%r11,>r11_stack=608(%rsp) |
| 208 |
movq %r11,608(%rsp) |
| 209 |
|
| 210 |
# qhasm: r12_stack = caller_r12 |
| 211 |
# asm 1: movq <caller_r12=int64#10,>r12_stack=stack64#2 |
| 212 |
# asm 2: movq <caller_r12=%r12,>r12_stack=616(%rsp) |
| 213 |
movq %r12,616(%rsp) |
| 214 |
|
| 215 |
# qhasm: r13_stack = caller_r13 |
| 216 |
# asm 1: movq <caller_r13=int64#11,>r13_stack=stack64#3 |
| 217 |
# asm 2: movq <caller_r13=%r13,>r13_stack=624(%rsp) |
| 218 |
movq %r13,624(%rsp) |
| 219 |
|
| 220 |
# qhasm: r14_stack = caller_r14 |
| 221 |
# asm 1: movq <caller_r14=int64#12,>r14_stack=stack64#4 |
| 222 |
# asm 2: movq <caller_r14=%r14,>r14_stack=632(%rsp) |
| 223 |
movq %r14,632(%rsp) |
| 224 |
|
| 225 |
# qhasm: r15_stack = caller_r15 |
| 226 |
# asm 1: movq <caller_r15=int64#13,>r15_stack=stack64#5 |
| 227 |
# asm 2: movq <caller_r15=%r15,>r15_stack=640(%rsp) |
| 228 |
movq %r15,640(%rsp) |
| 229 |
|
| 230 |
# qhasm: rbx_stack = caller_rbx |
| 231 |
# asm 1: movq <caller_rbx=int64#14,>rbx_stack=stack64#6 |
| 232 |
# asm 2: movq <caller_rbx=%rbx,>rbx_stack=648(%rsp) |
| 233 |
movq %rbx,648(%rsp) |
| 234 |
|
| 235 |
# qhasm: ptr = &buf |
| 236 |
# asm 1: leaq <buf=stack4864#1,>ptr=int64#4 |
| 237 |
# asm 2: leaq <buf=0(%rsp),>ptr=%rcx |
| 238 |
leaq 0(%rsp),%rcx |
| 239 |
|
| 240 |
# qhasm: s0 = mem256[ input_1 + 0 ] |
| 241 |
# asm 1: vmovupd 0(<input_1=int64#2),>s0=reg256#1 |
| 242 |
# asm 2: vmovupd 0(<input_1=%rsi),>s0=%ymm0 |
| 243 |
vmovupd 0(%rsi),%ymm0 |
| 244 |
|
| 245 |
# qhasm: s1 = mem256[ input_1 + 32 ] |
| 246 |
# asm 1: vmovupd 32(<input_1=int64#2),>s1=reg256#2 |
| 247 |
# asm 2: vmovupd 32(<input_1=%rsi),>s1=%ymm1 |
| 248 |
vmovupd 32(%rsi),%ymm1 |
| 249 |
|
| 250 |
# qhasm: s2 = mem256[ input_1 + 64 ] |
| 251 |
# asm 1: vmovupd 64(<input_1=int64#2),>s2=reg256#3 |
| 252 |
# asm 2: vmovupd 64(<input_1=%rsi),>s2=%ymm2 |
| 253 |
vmovupd 64(%rsi),%ymm2 |
| 254 |
|
| 255 |
# qhasm: a5[0,1,2,3] = s2[2,2,3,3] |
| 256 |
# asm 1: vpermq $0xfa,<s2=reg256#3,>a5=reg256#4 |
| 257 |
# asm 2: vpermq $0xfa,<s2=%ymm2,>a5=%ymm3 |
| 258 |
vpermq $0xfa,%ymm2,%ymm3 |
| 259 |
|
| 260 |
# qhasm: r = mem256[ input_2 + 160 ] |
| 261 |
# asm 1: vmovupd 160(<input_2=int64#3),>r=reg256#5 |
| 262 |
# asm 2: vmovupd 160(<input_2=%rdx),>r=%ymm4 |
| 263 |
vmovupd 160(%rdx),%ymm4 |
| 264 |
|
| 265 |
# qhasm: b5[0,1,2,3] = r[1,3,1,3] |
| 266 |
# asm 1: vpermq $0xdd,<r=reg256#5,>b5=reg256#5 |
| 267 |
# asm 2: vpermq $0xdd,<r=%ymm4,>b5=%ymm4 |
| 268 |
vpermq $0xdd,%ymm4,%ymm4 |
| 269 |
|
| 270 |
# qhasm: r10 = a5 & b5 |
| 271 |
# asm 1: vpand <a5=reg256#4,<b5=reg256#5,>r10=reg256#6 |
| 272 |
# asm 2: vpand <a5=%ymm3,<b5=%ymm4,>r10=%ymm5 |
| 273 |
vpand %ymm3,%ymm4,%ymm5 |
| 274 |
|
| 275 |
# qhasm: mem256[ ptr + 320 ] = r10 |
| 276 |
# asm 1: vmovupd <r10=reg256#6,320(<ptr=int64#4) |
| 277 |
# asm 2: vmovupd <r10=%ymm5,320(<ptr=%rcx) |
| 278 |
vmovupd %ymm5,320(%rcx) |
| 279 |
|
| 280 |
# qhasm: r = mem256[ input_2 + 128 ] |
| 281 |
# asm 1: vmovupd 128(<input_2=int64#3),>r=reg256#6 |
| 282 |
# asm 2: vmovupd 128(<input_2=%rdx),>r=%ymm5 |
| 283 |
vmovupd 128(%rdx),%ymm5 |
| 284 |
|
| 285 |
# qhasm: b4[0,1,2,3] = r[1,3,1,3] |
| 286 |
# asm 1: vpermq $0xdd,<r=reg256#6,>b4=reg256#6 |
| 287 |
# asm 2: vpermq $0xdd,<r=%ymm5,>b4=%ymm5 |
| 288 |
vpermq $0xdd,%ymm5,%ymm5 |
| 289 |
|
| 290 |
# qhasm: r9 = a5 & b4 |
| 291 |
# asm 1: vpand <a5=reg256#4,<b4=reg256#6,>r9=reg256#7 |
| 292 |
# asm 2: vpand <a5=%ymm3,<b4=%ymm5,>r9=%ymm6 |
| 293 |
vpand %ymm3,%ymm5,%ymm6 |
| 294 |
|
| 295 |
# qhasm: r = mem256[ input_2 + 96 ] |
| 296 |
# asm 1: vmovupd 96(<input_2=int64#3),>r=reg256#8 |
| 297 |
# asm 2: vmovupd 96(<input_2=%rdx),>r=%ymm7 |
| 298 |
vmovupd 96(%rdx),%ymm7 |
| 299 |
|
| 300 |
# qhasm: b3[0,1,2,3] = r[1,3,1,3] |
| 301 |
# asm 1: vpermq $0xdd,<r=reg256#8,>b3=reg256#8 |
| 302 |
# asm 2: vpermq $0xdd,<r=%ymm7,>b3=%ymm7 |
| 303 |
vpermq $0xdd,%ymm7,%ymm7 |
| 304 |
|
| 305 |
# qhasm: r8 = a5 & b3 |
| 306 |
# asm 1: vpand <a5=reg256#4,<b3=reg256#8,>r8=reg256#9 |
| 307 |
# asm 2: vpand <a5=%ymm3,<b3=%ymm7,>r8=%ymm8 |
| 308 |
vpand %ymm3,%ymm7,%ymm8 |
| 309 |
|
| 310 |
# qhasm: r = mem256[ input_2 + 64 ] |
| 311 |
# asm 1: vmovupd 64(<input_2=int64#3),>r=reg256#10 |
| 312 |
# asm 2: vmovupd 64(<input_2=%rdx),>r=%ymm9 |
| 313 |
vmovupd 64(%rdx),%ymm9 |
| 314 |
|
| 315 |
# qhasm: b2[0,1,2,3] = r[1,3,1,3] |
| 316 |
# asm 1: vpermq $0xdd,<r=reg256#10,>b2=reg256#10 |
| 317 |
# asm 2: vpermq $0xdd,<r=%ymm9,>b2=%ymm9 |
| 318 |
vpermq $0xdd,%ymm9,%ymm9 |
| 319 |
|
| 320 |
# qhasm: r7 = a5 & b2 |
| 321 |
# asm 1: vpand <a5=reg256#4,<b2=reg256#10,>r7=reg256#11 |
| 322 |
# asm 2: vpand <a5=%ymm3,<b2=%ymm9,>r7=%ymm10 |
| 323 |
vpand %ymm3,%ymm9,%ymm10 |
| 324 |
|
| 325 |
# qhasm: r = mem256[ input_2 + 32 ] |
| 326 |
# asm 1: vmovupd 32(<input_2=int64#3),>r=reg256#12 |
| 327 |
# asm 2: vmovupd 32(<input_2=%rdx),>r=%ymm11 |
| 328 |
vmovupd 32(%rdx),%ymm11 |
| 329 |
|
| 330 |
# qhasm: b1[0,1,2,3] = r[1,3,1,3] |
| 331 |
# asm 1: vpermq $0xdd,<r=reg256#12,>b1=reg256#12 |
| 332 |
# asm 2: vpermq $0xdd,<r=%ymm11,>b1=%ymm11 |
| 333 |
vpermq $0xdd,%ymm11,%ymm11 |
| 334 |
|
| 335 |
# qhasm: r6 = a5 & b1 |
| 336 |
# asm 1: vpand <a5=reg256#4,<b1=reg256#12,>r6=reg256#13 |
| 337 |
# asm 2: vpand <a5=%ymm3,<b1=%ymm11,>r6=%ymm12 |
| 338 |
vpand %ymm3,%ymm11,%ymm12 |
| 339 |
|
| 340 |
# qhasm: r = mem256[ input_2 + 0 ] |
| 341 |
# asm 1: vmovupd 0(<input_2=int64#3),>r=reg256#14 |
| 342 |
# asm 2: vmovupd 0(<input_2=%rdx),>r=%ymm13 |
| 343 |
vmovupd 0(%rdx),%ymm13 |
| 344 |
|
| 345 |
# qhasm: b0[0,1,2,3] = r[1,3,1,3] |
| 346 |
# asm 1: vpermq $0xdd,<r=reg256#14,>b0=reg256#14 |
| 347 |
# asm 2: vpermq $0xdd,<r=%ymm13,>b0=%ymm13 |
| 348 |
vpermq $0xdd,%ymm13,%ymm13 |
| 349 |
|
| 350 |
# qhasm: r5 = a5 & b0 |
| 351 |
# asm 1: vpand <a5=reg256#4,<b0=reg256#14,>r5=reg256#4 |
| 352 |
# asm 2: vpand <a5=%ymm3,<b0=%ymm13,>r5=%ymm3 |
| 353 |
vpand %ymm3,%ymm13,%ymm3 |
| 354 |
|
| 355 |
# qhasm: a4[0,1,2,3] = s2[0,0,1,1] |
| 356 |
# asm 1: vpermq $0x50,<s2=reg256#3,>a4=reg256#3 |
| 357 |
# asm 2: vpermq $0x50,<s2=%ymm2,>a4=%ymm2 |
| 358 |
vpermq $0x50,%ymm2,%ymm2 |
| 359 |
|
| 360 |
# qhasm: r = a4 & b5 |
| 361 |
# asm 1: vpand <a4=reg256#3,<b5=reg256#5,>r=reg256#15 |
| 362 |
# asm 2: vpand <a4=%ymm2,<b5=%ymm4,>r=%ymm14 |
| 363 |
vpand %ymm2,%ymm4,%ymm14 |
| 364 |
|
| 365 |
# qhasm: r9 ^= r |
| 366 |
# asm 1: vpxor <r=reg256#15,<r9=reg256#7,<r9=reg256#7 |
| 367 |
# asm 2: vpxor <r=%ymm14,<r9=%ymm6,<r9=%ymm6 |
| 368 |
vpxor %ymm14,%ymm6,%ymm6 |
| 369 |
|
| 370 |
# qhasm: mem256[ ptr + 288 ] = r9 |
| 371 |
# asm 1: vmovupd <r9=reg256#7,288(<ptr=int64#4) |
| 372 |
# asm 2: vmovupd <r9=%ymm6,288(<ptr=%rcx) |
| 373 |
vmovupd %ymm6,288(%rcx) |
| 374 |
|
| 375 |
# qhasm: r = a4 & b4 |
| 376 |
# asm 1: vpand <a4=reg256#3,<b4=reg256#6,>r=reg256#7 |
| 377 |
# asm 2: vpand <a4=%ymm2,<b4=%ymm5,>r=%ymm6 |
| 378 |
vpand %ymm2,%ymm5,%ymm6 |
| 379 |
|
| 380 |
# qhasm: r8 ^= r |
| 381 |
# asm 1: vpxor <r=reg256#7,<r8=reg256#9,<r8=reg256#9 |
| 382 |
# asm 2: vpxor <r=%ymm6,<r8=%ymm8,<r8=%ymm8 |
| 383 |
vpxor %ymm6,%ymm8,%ymm8 |
| 384 |
|
| 385 |
# qhasm: r = a4 & b3 |
| 386 |
# asm 1: vpand <a4=reg256#3,<b3=reg256#8,>r=reg256#7 |
| 387 |
# asm 2: vpand <a4=%ymm2,<b3=%ymm7,>r=%ymm6 |
| 388 |
vpand %ymm2,%ymm7,%ymm6 |
| 389 |
|
| 390 |
# qhasm: r7 ^= r |
| 391 |
# asm 1: vpxor <r=reg256#7,<r7=reg256#11,<r7=reg256#11 |
| 392 |
# asm 2: vpxor <r=%ymm6,<r7=%ymm10,<r7=%ymm10 |
| 393 |
vpxor %ymm6,%ymm10,%ymm10 |
| 394 |
|
| 395 |
# qhasm: r = a4 & b2 |
| 396 |
# asm 1: vpand <a4=reg256#3,<b2=reg256#10,>r=reg256#7 |
| 397 |
# asm 2: vpand <a4=%ymm2,<b2=%ymm9,>r=%ymm6 |
| 398 |
vpand %ymm2,%ymm9,%ymm6 |
| 399 |
|
| 400 |
# qhasm: r6 ^= r |
| 401 |
# asm 1: vpxor <r=reg256#7,<r6=reg256#13,<r6=reg256#13 |
| 402 |
# asm 2: vpxor <r=%ymm6,<r6=%ymm12,<r6=%ymm12 |
| 403 |
vpxor %ymm6,%ymm12,%ymm12 |
| 404 |
|
| 405 |
# qhasm: r = a4 & b1 |
| 406 |
# asm 1: vpand <a4=reg256#3,<b1=reg256#12,>r=reg256#7 |
| 407 |
# asm 2: vpand <a4=%ymm2,<b1=%ymm11,>r=%ymm6 |
| 408 |
vpand %ymm2,%ymm11,%ymm6 |
| 409 |
|
| 410 |
# qhasm: r5 ^= r |
| 411 |
# asm 1: vpxor <r=reg256#7,<r5=reg256#4,<r5=reg256#4 |
| 412 |
# asm 2: vpxor <r=%ymm6,<r5=%ymm3,<r5=%ymm3 |
| 413 |
vpxor %ymm6,%ymm3,%ymm3 |
| 414 |
|
| 415 |
# qhasm: r4 = a4 & b0 |
| 416 |
# asm 1: vpand <a4=reg256#3,<b0=reg256#14,>r4=reg256#3 |
| 417 |
# asm 2: vpand <a4=%ymm2,<b0=%ymm13,>r4=%ymm2 |
| 418 |
vpand %ymm2,%ymm13,%ymm2 |
| 419 |
|
| 420 |
# qhasm: a3[0,1,2,3] = s1[2,2,3,3] |
| 421 |
# asm 1: vpermq $0xfa,<s1=reg256#2,>a3=reg256#7 |
| 422 |
# asm 2: vpermq $0xfa,<s1=%ymm1,>a3=%ymm6 |
| 423 |
vpermq $0xfa,%ymm1,%ymm6 |
| 424 |
|
| 425 |
# qhasm: r = a3 & b5 |
| 426 |
# asm 1: vpand <a3=reg256#7,<b5=reg256#5,>r=reg256#15 |
| 427 |
# asm 2: vpand <a3=%ymm6,<b5=%ymm4,>r=%ymm14 |
| 428 |
vpand %ymm6,%ymm4,%ymm14 |
| 429 |
|
| 430 |
# qhasm: r8 ^= r |
| 431 |
# asm 1: vpxor <r=reg256#15,<r8=reg256#9,<r8=reg256#9 |
| 432 |
# asm 2: vpxor <r=%ymm14,<r8=%ymm8,<r8=%ymm8 |
| 433 |
vpxor %ymm14,%ymm8,%ymm8 |
| 434 |
|
| 435 |
# qhasm: mem256[ ptr + 256 ] = r8 |
| 436 |
# asm 1: vmovupd <r8=reg256#9,256(<ptr=int64#4) |
| 437 |
# asm 2: vmovupd <r8=%ymm8,256(<ptr=%rcx) |
| 438 |
vmovupd %ymm8,256(%rcx) |
| 439 |
|
| 440 |
# qhasm: r = a3 & b4 |
| 441 |
# asm 1: vpand <a3=reg256#7,<b4=reg256#6,>r=reg256#9 |
| 442 |
# asm 2: vpand <a3=%ymm6,<b4=%ymm5,>r=%ymm8 |
| 443 |
vpand %ymm6,%ymm5,%ymm8 |
| 444 |
|
| 445 |
# qhasm: r7 ^= r |
| 446 |
# asm 1: vpxor <r=reg256#9,<r7=reg256#11,<r7=reg256#11 |
| 447 |
# asm 2: vpxor <r=%ymm8,<r7=%ymm10,<r7=%ymm10 |
| 448 |
vpxor %ymm8,%ymm10,%ymm10 |
| 449 |
|
| 450 |
# qhasm: r = a3 & b3 |
| 451 |
# asm 1: vpand <a3=reg256#7,<b3=reg256#8,>r=reg256#9 |
| 452 |
# asm 2: vpand <a3=%ymm6,<b3=%ymm7,>r=%ymm8 |
| 453 |
vpand %ymm6,%ymm7,%ymm8 |
| 454 |
|
| 455 |
# qhasm: r6 ^= r |
| 456 |
# asm 1: vpxor <r=reg256#9,<r6=reg256#13,<r6=reg256#13 |
| 457 |
# asm 2: vpxor <r=%ymm8,<r6=%ymm12,<r6=%ymm12 |
| 458 |
vpxor %ymm8,%ymm12,%ymm12 |
| 459 |
|
| 460 |
# qhasm: r = a3 & b2 |
| 461 |
# asm 1: vpand <a3=reg256#7,<b2=reg256#10,>r=reg256#9 |
| 462 |
# asm 2: vpand <a3=%ymm6,<b2=%ymm9,>r=%ymm8 |
| 463 |
vpand %ymm6,%ymm9,%ymm8 |
| 464 |
|
| 465 |
# qhasm: r5 ^= r |
| 466 |
# asm 1: vpxor <r=reg256#9,<r5=reg256#4,<r5=reg256#4 |
| 467 |
# asm 2: vpxor <r=%ymm8,<r5=%ymm3,<r5=%ymm3 |
| 468 |
vpxor %ymm8,%ymm3,%ymm3 |
| 469 |
|
| 470 |
# qhasm: r = a3 & b1 |
| 471 |
# asm 1: vpand <a3=reg256#7,<b1=reg256#12,>r=reg256#9 |
| 472 |
# asm 2: vpand <a3=%ymm6,<b1=%ymm11,>r=%ymm8 |
| 473 |
vpand %ymm6,%ymm11,%ymm8 |
| 474 |
|
| 475 |
# qhasm: r4 ^= r |
| 476 |
# asm 1: vpxor <r=reg256#9,<r4=reg256#3,<r4=reg256#3 |
| 477 |
# asm 2: vpxor <r=%ymm8,<r4=%ymm2,<r4=%ymm2 |
| 478 |
vpxor %ymm8,%ymm2,%ymm2 |
| 479 |
|
| 480 |
# qhasm: r3 = a3 & b0 |
| 481 |
# asm 1: vpand <a3=reg256#7,<b0=reg256#14,>r3=reg256#7 |
| 482 |
# asm 2: vpand <a3=%ymm6,<b0=%ymm13,>r3=%ymm6 |
| 483 |
vpand %ymm6,%ymm13,%ymm6 |
| 484 |
|
| 485 |
# qhasm: a2[0,1,2,3] = s1[0,0,1,1] |
| 486 |
# asm 1: vpermq $0x50,<s1=reg256#2,>a2=reg256#2 |
| 487 |
# asm 2: vpermq $0x50,<s1=%ymm1,>a2=%ymm1 |
| 488 |
vpermq $0x50,%ymm1,%ymm1 |
| 489 |
|
| 490 |
# qhasm: r = a2 & b5 |
| 491 |
# asm 1: vpand <a2=reg256#2,<b5=reg256#5,>r=reg256#9 |
| 492 |
# asm 2: vpand <a2=%ymm1,<b5=%ymm4,>r=%ymm8 |
| 493 |
vpand %ymm1,%ymm4,%ymm8 |
| 494 |
|
| 495 |
# qhasm: r7 ^= r |
| 496 |
# asm 1: vpxor <r=reg256#9,<r7=reg256#11,<r7=reg256#11 |
| 497 |
# asm 2: vpxor <r=%ymm8,<r7=%ymm10,<r7=%ymm10 |
| 498 |
vpxor %ymm8,%ymm10,%ymm10 |
| 499 |
|
| 500 |
# qhasm: mem256[ ptr + 224 ] = r7 |
| 501 |
# asm 1: vmovupd <r7=reg256#11,224(<ptr=int64#4) |
| 502 |
# asm 2: vmovupd <r7=%ymm10,224(<ptr=%rcx) |
| 503 |
vmovupd %ymm10,224(%rcx) |
| 504 |
|
| 505 |
# qhasm: r = a2 & b4 |
| 506 |
# asm 1: vpand <a2=reg256#2,<b4=reg256#6,>r=reg256#9 |
| 507 |
# asm 2: vpand <a2=%ymm1,<b4=%ymm5,>r=%ymm8 |
| 508 |
vpand %ymm1,%ymm5,%ymm8 |
| 509 |
|
| 510 |
# qhasm: r6 ^= r |
| 511 |
# asm 1: vpxor <r=reg256#9,<r6=reg256#13,<r6=reg256#13 |
| 512 |
# asm 2: vpxor <r=%ymm8,<r6=%ymm12,<r6=%ymm12 |
| 513 |
vpxor %ymm8,%ymm12,%ymm12 |
| 514 |
|
| 515 |
# qhasm: r = a2 & b3 |
| 516 |
# asm 1: vpand <a2=reg256#2,<b3=reg256#8,>r=reg256#9 |
| 517 |
# asm 2: vpand <a2=%ymm1,<b3=%ymm7,>r=%ymm8 |
| 518 |
vpand %ymm1,%ymm7,%ymm8 |
| 519 |
|
| 520 |
# qhasm: r5 ^= r |
| 521 |
# asm 1: vpxor <r=reg256#9,<r5=reg256#4,<r5=reg256#4 |
| 522 |
# asm 2: vpxor <r=%ymm8,<r5=%ymm3,<r5=%ymm3 |
| 523 |
vpxor %ymm8,%ymm3,%ymm3 |
| 524 |
|
| 525 |
# qhasm: r = a2 & b2 |
| 526 |
# asm 1: vpand <a2=reg256#2,<b2=reg256#10,>r=reg256#9 |
| 527 |
# asm 2: vpand <a2=%ymm1,<b2=%ymm9,>r=%ymm8 |
| 528 |
vpand %ymm1,%ymm9,%ymm8 |
| 529 |
|
| 530 |
# qhasm: r4 ^= r |
| 531 |
# asm 1: vpxor <r=reg256#9,<r4=reg256#3,<r4=reg256#3 |
| 532 |
# asm 2: vpxor <r=%ymm8,<r4=%ymm2,<r4=%ymm2 |
| 533 |
vpxor %ymm8,%ymm2,%ymm2 |
| 534 |
|
| 535 |
# qhasm: r = a2 & b1 |
| 536 |
# asm 1: vpand <a2=reg256#2,<b1=reg256#12,>r=reg256#9 |
| 537 |
# asm 2: vpand <a2=%ymm1,<b1=%ymm11,>r=%ymm8 |
| 538 |
vpand %ymm1,%ymm11,%ymm8 |
| 539 |
|
| 540 |
# qhasm: r3 ^= r |
| 541 |
# asm 1: vpxor <r=reg256#9,<r3=reg256#7,<r3=reg256#7 |
| 542 |
# asm 2: vpxor <r=%ymm8,<r3=%ymm6,<r3=%ymm6 |
| 543 |
vpxor %ymm8,%ymm6,%ymm6 |
| 544 |
|
| 545 |
# qhasm: r2 = a2 & b0 |
| 546 |
# asm 1: vpand <a2=reg256#2,<b0=reg256#14,>r2=reg256#2 |
| 547 |
# asm 2: vpand <a2=%ymm1,<b0=%ymm13,>r2=%ymm1 |
| 548 |
vpand %ymm1,%ymm13,%ymm1 |
| 549 |
|
| 550 |
# qhasm: a1[0,1,2,3] = s0[2,2,3,3] |
| 551 |
# asm 1: vpermq $0xfa,<s0=reg256#1,>a1=reg256#9 |
| 552 |
# asm 2: vpermq $0xfa,<s0=%ymm0,>a1=%ymm8 |
| 553 |
vpermq $0xfa,%ymm0,%ymm8 |
| 554 |
|
| 555 |
# qhasm: r = a1 & b5 |
| 556 |
# asm 1: vpand <a1=reg256#9,<b5=reg256#5,>r=reg256#11 |
| 557 |
# asm 2: vpand <a1=%ymm8,<b5=%ymm4,>r=%ymm10 |
| 558 |
vpand %ymm8,%ymm4,%ymm10 |
| 559 |
|
| 560 |
# qhasm: r6 ^= r |
| 561 |
# asm 1: vpxor <r=reg256#11,<r6=reg256#13,<r6=reg256#13 |
| 562 |
# asm 2: vpxor <r=%ymm10,<r6=%ymm12,<r6=%ymm12 |
| 563 |
vpxor %ymm10,%ymm12,%ymm12 |
| 564 |
|
| 565 |
# qhasm: mem256[ ptr + 192 ] = r6 |
| 566 |
# asm 1: vmovupd <r6=reg256#13,192(<ptr=int64#4) |
| 567 |
# asm 2: vmovupd <r6=%ymm12,192(<ptr=%rcx) |
| 568 |
vmovupd %ymm12,192(%rcx) |
| 569 |
|
| 570 |
# qhasm: r = a1 & b4 |
| 571 |
# asm 1: vpand <a1=reg256#9,<b4=reg256#6,>r=reg256#11 |
| 572 |
# asm 2: vpand <a1=%ymm8,<b4=%ymm5,>r=%ymm10 |
| 573 |
vpand %ymm8,%ymm5,%ymm10 |
| 574 |
|
| 575 |
# qhasm: r5 ^= r |
| 576 |
# asm 1: vpxor <r=reg256#11,<r5=reg256#4,<r5=reg256#4 |
| 577 |
# asm 2: vpxor <r=%ymm10,<r5=%ymm3,<r5=%ymm3 |
| 578 |
vpxor %ymm10,%ymm3,%ymm3 |
| 579 |
|
| 580 |
# qhasm: r = a1 & b3 |
| 581 |
# asm 1: vpand <a1=reg256#9,<b3=reg256#8,>r=reg256#11 |
| 582 |
# asm 2: vpand <a1=%ymm8,<b3=%ymm7,>r=%ymm10 |
| 583 |
vpand %ymm8,%ymm7,%ymm10 |
| 584 |
|
| 585 |
# qhasm: r4 ^= r |
| 586 |
# asm 1: vpxor <r=reg256#11,<r4=reg256#3,<r4=reg256#3 |
| 587 |
# asm 2: vpxor <r=%ymm10,<r4=%ymm2,<r4=%ymm2 |
| 588 |
vpxor %ymm10,%ymm2,%ymm2 |
| 589 |
|
| 590 |
# qhasm: r = a1 & b2 |
| 591 |
# asm 1: vpand <a1=reg256#9,<b2=reg256#10,>r=reg256#11 |
| 592 |
# asm 2: vpand <a1=%ymm8,<b2=%ymm9,>r=%ymm10 |
| 593 |
vpand %ymm8,%ymm9,%ymm10 |
| 594 |
|
| 595 |
# qhasm: r3 ^= r |
| 596 |
# asm 1: vpxor <r=reg256#11,<r3=reg256#7,<r3=reg256#7 |
| 597 |
# asm 2: vpxor <r=%ymm10,<r3=%ymm6,<r3=%ymm6 |
| 598 |
vpxor %ymm10,%ymm6,%ymm6 |
| 599 |
|
| 600 |
# qhasm: r = a1 & b1 |
| 601 |
# asm 1: vpand <a1=reg256#9,<b1=reg256#12,>r=reg256#11 |
| 602 |
# asm 2: vpand <a1=%ymm8,<b1=%ymm11,>r=%ymm10 |
| 603 |
vpand %ymm8,%ymm11,%ymm10 |
| 604 |
|
| 605 |
# qhasm: r2 ^= r |
| 606 |
# asm 1: vpxor <r=reg256#11,<r2=reg256#2,<r2=reg256#2 |
| 607 |
# asm 2: vpxor <r=%ymm10,<r2=%ymm1,<r2=%ymm1 |
| 608 |
vpxor %ymm10,%ymm1,%ymm1 |
| 609 |
|
| 610 |
# qhasm: r1 = a1 & b0 |
| 611 |
# asm 1: vpand <a1=reg256#9,<b0=reg256#14,>r1=reg256#9 |
| 612 |
# asm 2: vpand <a1=%ymm8,<b0=%ymm13,>r1=%ymm8 |
| 613 |
vpand %ymm8,%ymm13,%ymm8 |
| 614 |
|
| 615 |
# qhasm: a0[0,1,2,3] = s0[0,0,1,1] |
| 616 |
# asm 1: vpermq $0x50,<s0=reg256#1,>a0=reg256#1 |
| 617 |
# asm 2: vpermq $0x50,<s0=%ymm0,>a0=%ymm0 |
| 618 |
vpermq $0x50,%ymm0,%ymm0 |
| 619 |
|
| 620 |
# qhasm: r = a0 & b5 |
| 621 |
# asm 1: vpand <a0=reg256#1,<b5=reg256#5,>r=reg256#5 |
| 622 |
# asm 2: vpand <a0=%ymm0,<b5=%ymm4,>r=%ymm4 |
| 623 |
vpand %ymm0,%ymm4,%ymm4 |
| 624 |
|
| 625 |
# qhasm: r5 ^= r |
| 626 |
# asm 1: vpxor <r=reg256#5,<r5=reg256#4,<r5=reg256#4 |
| 627 |
# asm 2: vpxor <r=%ymm4,<r5=%ymm3,<r5=%ymm3 |
| 628 |
vpxor %ymm4,%ymm3,%ymm3 |
| 629 |
|
| 630 |
# qhasm: mem256[ ptr + 160 ] = r5 |
| 631 |
# asm 1: vmovupd <r5=reg256#4,160(<ptr=int64#4) |
| 632 |
# asm 2: vmovupd <r5=%ymm3,160(<ptr=%rcx) |
| 633 |
vmovupd %ymm3,160(%rcx) |
| 634 |
|
| 635 |
# qhasm: r = a0 & b4 |
| 636 |
# asm 1: vpand <a0=reg256#1,<b4=reg256#6,>r=reg256#4 |
| 637 |
# asm 2: vpand <a0=%ymm0,<b4=%ymm5,>r=%ymm3 |
| 638 |
vpand %ymm0,%ymm5,%ymm3 |
| 639 |
|
| 640 |
# qhasm: r4 ^= r |
| 641 |
# asm 1: vpxor <r=reg256#4,<r4=reg256#3,<r4=reg256#3 |
| 642 |
# asm 2: vpxor <r=%ymm3,<r4=%ymm2,<r4=%ymm2 |
| 643 |
vpxor %ymm3,%ymm2,%ymm2 |
| 644 |
|
| 645 |
# qhasm: r = a0 & b3 |
| 646 |
# asm 1: vpand <a0=reg256#1,<b3=reg256#8,>r=reg256#4 |
| 647 |
# asm 2: vpand <a0=%ymm0,<b3=%ymm7,>r=%ymm3 |
| 648 |
vpand %ymm0,%ymm7,%ymm3 |
| 649 |
|
| 650 |
# qhasm: r3 ^= r |
| 651 |
# asm 1: vpxor <r=reg256#4,<r3=reg256#7,<r3=reg256#7 |
| 652 |
# asm 2: vpxor <r=%ymm3,<r3=%ymm6,<r3=%ymm6 |
| 653 |
vpxor %ymm3,%ymm6,%ymm6 |
| 654 |
|
| 655 |
# qhasm: r = a0 & b2 |
| 656 |
# asm 1: vpand <a0=reg256#1,<b2=reg256#10,>r=reg256#4 |
| 657 |
# asm 2: vpand <a0=%ymm0,<b2=%ymm9,>r=%ymm3 |
| 658 |
vpand %ymm0,%ymm9,%ymm3 |
| 659 |
|
| 660 |
# qhasm: r2 ^= r |
| 661 |
# asm 1: vpxor <r=reg256#4,<r2=reg256#2,<r2=reg256#2 |
| 662 |
# asm 2: vpxor <r=%ymm3,<r2=%ymm1,<r2=%ymm1 |
| 663 |
vpxor %ymm3,%ymm1,%ymm1 |
| 664 |
|
| 665 |
# qhasm: r = a0 & b1 |
| 666 |
# asm 1: vpand <a0=reg256#1,<b1=reg256#12,>r=reg256#4 |
| 667 |
# asm 2: vpand <a0=%ymm0,<b1=%ymm11,>r=%ymm3 |
| 668 |
vpand %ymm0,%ymm11,%ymm3 |
| 669 |
|
| 670 |
# qhasm: r1 ^= r |
| 671 |
# asm 1: vpxor <r=reg256#4,<r1=reg256#9,<r1=reg256#9 |
| 672 |
# asm 2: vpxor <r=%ymm3,<r1=%ymm8,<r1=%ymm8 |
| 673 |
vpxor %ymm3,%ymm8,%ymm8 |
| 674 |
|
| 675 |
# qhasm: r0 = a0 & b0 |
| 676 |
# asm 1: vpand <a0=reg256#1,<b0=reg256#14,>r0=reg256#1 |
| 677 |
# asm 2: vpand <a0=%ymm0,<b0=%ymm13,>r0=%ymm0 |
| 678 |
vpand %ymm0,%ymm13,%ymm0 |
| 679 |
|
| 680 |
# qhasm: mem256[ ptr + 128 ] = r4 |
| 681 |
# asm 1: vmovupd <r4=reg256#3,128(<ptr=int64#4) |
| 682 |
# asm 2: vmovupd <r4=%ymm2,128(<ptr=%rcx) |
| 683 |
vmovupd %ymm2,128(%rcx) |
| 684 |
|
| 685 |
# qhasm: mem256[ ptr + 96 ] = r3 |
| 686 |
# asm 1: vmovupd <r3=reg256#7,96(<ptr=int64#4) |
| 687 |
# asm 2: vmovupd <r3=%ymm6,96(<ptr=%rcx) |
| 688 |
vmovupd %ymm6,96(%rcx) |
| 689 |
|
| 690 |
# qhasm: mem256[ ptr + 64 ] = r2 |
| 691 |
# asm 1: vmovupd <r2=reg256#2,64(<ptr=int64#4) |
| 692 |
# asm 2: vmovupd <r2=%ymm1,64(<ptr=%rcx) |
| 693 |
vmovupd %ymm1,64(%rcx) |
| 694 |
|
| 695 |
# qhasm: mem256[ ptr + 32 ] = r1 |
| 696 |
# asm 1: vmovupd <r1=reg256#9,32(<ptr=int64#4) |
| 697 |
# asm 2: vmovupd <r1=%ymm8,32(<ptr=%rcx) |
| 698 |
vmovupd %ymm8,32(%rcx) |
| 699 |
|
| 700 |
# qhasm: mem256[ ptr + 0 ] = r0 |
| 701 |
# asm 1: vmovupd <r0=reg256#1,0(<ptr=int64#4) |
| 702 |
# asm 2: vmovupd <r0=%ymm0,0(<ptr=%rcx) |
| 703 |
vmovupd %ymm0,0(%rcx) |
| 704 |
|
| 705 |
# qhasm: h22 = mem64[ ptr + 344 ] |
| 706 |
# asm 1: movq 344(<ptr=int64#4),>h22=int64#2 |
| 707 |
# asm 2: movq 344(<ptr=%rcx),>h22=%rsi |
| 708 |
movq 344(%rcx),%rsi |
| 709 |
|
| 710 |
# qhasm: h13 = h22 |
| 711 |
# asm 1: mov <h22=int64#2,>h13=int64#3 |
| 712 |
# asm 2: mov <h22=%rsi,>h13=%rdx |
| 713 |
mov %rsi,%rdx |
| 714 |
|
| 715 |
# qhasm: h10 = h22 |
| 716 |
# asm 1: mov <h22=int64#2,>h10=int64#2 |
| 717 |
# asm 2: mov <h22=%rsi,>h10=%rsi |
| 718 |
mov %rsi,%rsi |
| 719 |
|
| 720 |
# qhasm: h21 = mem64[ ptr + 336 ] |
| 721 |
# asm 1: movq 336(<ptr=int64#4),>h21=int64#5 |
| 722 |
# asm 2: movq 336(<ptr=%rcx),>h21=%r8 |
| 723 |
movq 336(%rcx),%r8 |
| 724 |
|
| 725 |
# qhasm: h21 ^= *(uint64 *) ( ptr + 328 ) |
| 726 |
# asm 1: xorq 328(<ptr=int64#4),<h21=int64#5 |
| 727 |
# asm 2: xorq 328(<ptr=%rcx),<h21=%r8 |
| 728 |
xorq 328(%rcx),%r8 |
| 729 |
|
| 730 |
# qhasm: h12 = h21 |
| 731 |
# asm 1: mov <h21=int64#5,>h12=int64#6 |
| 732 |
# asm 2: mov <h21=%r8,>h12=%r9 |
| 733 |
mov %r8,%r9 |
| 734 |
|
| 735 |
# qhasm: h9 = h21 |
| 736 |
# asm 1: mov <h21=int64#5,>h9=int64#5 |
| 737 |
# asm 2: mov <h21=%r8,>h9=%r8 |
| 738 |
mov %r8,%r8 |
| 739 |
|
| 740 |
# qhasm: h20 = mem64[ ptr + 312 ] |
| 741 |
# asm 1: movq 312(<ptr=int64#4),>h20=int64#7 |
| 742 |
# asm 2: movq 312(<ptr=%rcx),>h20=%rax |
| 743 |
movq 312(%rcx),%rax |
| 744 |
|
| 745 |
# qhasm: h20 ^= *(uint64 *) ( ptr + 320 ) |
| 746 |
# asm 1: xorq 320(<ptr=int64#4),<h20=int64#7 |
| 747 |
# asm 2: xorq 320(<ptr=%rcx),<h20=%rax |
| 748 |
xorq 320(%rcx),%rax |
| 749 |
|
| 750 |
# qhasm: h11 = h20 |
| 751 |
# asm 1: mov <h20=int64#7,>h11=int64#8 |
| 752 |
# asm 2: mov <h20=%rax,>h11=%r10 |
| 753 |
mov %rax,%r10 |
| 754 |
|
| 755 |
# qhasm: h8 = h20 |
| 756 |
# asm 1: mov <h20=int64#7,>h8=int64#7 |
| 757 |
# asm 2: mov <h20=%rax,>h8=%rax |
| 758 |
mov %rax,%rax |
| 759 |
|
| 760 |
# qhasm: h19 = mem64[ ptr + 304 ] |
| 761 |
# asm 1: movq 304(<ptr=int64#4),>h19=int64#9 |
| 762 |
# asm 2: movq 304(<ptr=%rcx),>h19=%r11 |
| 763 |
movq 304(%rcx),%r11 |
| 764 |
|
| 765 |
# qhasm: h19 ^= *(uint64 *) ( ptr + 296 ) |
| 766 |
# asm 1: xorq 296(<ptr=int64#4),<h19=int64#9 |
| 767 |
# asm 2: xorq 296(<ptr=%rcx),<h19=%r11 |
| 768 |
xorq 296(%rcx),%r11 |
| 769 |
|
| 770 |
# qhasm: h10 ^= h19 |
| 771 |
# asm 1: XOR <h19=int64#9,<h10=int64#2 |
| 772 |
# asm 2: XOR <h19=%r11,<h10=%rsi |
| 773 |
XOR %r11,%rsi |
| 774 |
|
| 775 |
# qhasm: h7 = h19 |
| 776 |
# asm 1: mov <h19=int64#9,>h7=int64#9 |
| 777 |
# asm 2: mov <h19=%r11,>h7=%r11 |
| 778 |
mov %r11,%r11 |
| 779 |
|
| 780 |
# qhasm: h18 = mem64[ ptr + 280 ] |
| 781 |
# asm 1: movq 280(<ptr=int64#4),>h18=int64#10 |
| 782 |
# asm 2: movq 280(<ptr=%rcx),>h18=%r12 |
| 783 |
movq 280(%rcx),%r12 |
| 784 |
|
| 785 |
# qhasm: h18 ^= *(uint64 *) ( ptr + 288 ) |
| 786 |
# asm 1: xorq 288(<ptr=int64#4),<h18=int64#10 |
| 787 |
# asm 2: xorq 288(<ptr=%rcx),<h18=%r12 |
| 788 |
xorq 288(%rcx),%r12 |
| 789 |
|
| 790 |
# qhasm: h9 ^= h18 |
| 791 |
# asm 1: XOR <h18=int64#10,<h9=int64#5 |
| 792 |
# asm 2: XOR <h18=%r12,<h9=%r8 |
| 793 |
XOR %r12,%r8 |
| 794 |
|
| 795 |
# qhasm: h6 = h18 |
| 796 |
# asm 1: mov <h18=int64#10,>h6=int64#10 |
| 797 |
# asm 2: mov <h18=%r12,>h6=%r12 |
| 798 |
mov %r12,%r12 |
| 799 |
|
| 800 |
# qhasm: h17 = mem64[ ptr + 272 ] |
| 801 |
# asm 1: movq 272(<ptr=int64#4),>h17=int64#11 |
| 802 |
# asm 2: movq 272(<ptr=%rcx),>h17=%r13 |
| 803 |
movq 272(%rcx),%r13 |
| 804 |
|
| 805 |
# qhasm: h17 ^= *(uint64 *) ( ptr + 264 ) |
| 806 |
# asm 1: xorq 264(<ptr=int64#4),<h17=int64#11 |
| 807 |
# asm 2: xorq 264(<ptr=%rcx),<h17=%r13 |
| 808 |
xorq 264(%rcx),%r13 |
| 809 |
|
| 810 |
# qhasm: h8 ^= h17 |
| 811 |
# asm 1: XOR <h17=int64#11,<h8=int64#7 |
| 812 |
# asm 2: XOR <h17=%r13,<h8=%rax |
| 813 |
XOR %r13,%rax |
| 814 |
|
| 815 |
# qhasm: h5 = h17 |
| 816 |
# asm 1: mov <h17=int64#11,>h5=int64#11 |
| 817 |
# asm 2: mov <h17=%r13,>h5=%r13 |
| 818 |
mov %r13,%r13 |
| 819 |
|
| 820 |
# qhasm: h16 = mem64[ ptr + 248 ] |
| 821 |
# asm 1: movq 248(<ptr=int64#4),>h16=int64#12 |
| 822 |
# asm 2: movq 248(<ptr=%rcx),>h16=%r14 |
| 823 |
movq 248(%rcx),%r14 |
| 824 |
|
| 825 |
# qhasm: h16 ^= *(uint64 *) ( ptr + 256 ) |
| 826 |
# asm 1: xorq 256(<ptr=int64#4),<h16=int64#12 |
| 827 |
# asm 2: xorq 256(<ptr=%rcx),<h16=%r14 |
| 828 |
xorq 256(%rcx),%r14 |
| 829 |
|
| 830 |
# qhasm: h7 ^= h16 |
| 831 |
# asm 1: XOR <h16=int64#12,<h7=int64#9 |
| 832 |
# asm 2: XOR <h16=%r14,<h7=%r11 |
| 833 |
XOR %r14,%r11 |
| 834 |
|
| 835 |
# qhasm: h4 = h16 |
| 836 |
# asm 1: mov <h16=int64#12,>h4=int64#12 |
| 837 |
# asm 2: mov <h16=%r14,>h4=%r14 |
| 838 |
mov %r14,%r14 |
| 839 |
|
| 840 |
# qhasm: h15 = mem64[ ptr + 240 ] |
| 841 |
# asm 1: movq 240(<ptr=int64#4),>h15=int64#13 |
| 842 |
# asm 2: movq 240(<ptr=%rcx),>h15=%r15 |
| 843 |
movq 240(%rcx),%r15 |
| 844 |
|
| 845 |
# qhasm: h15 ^= *(uint64 *) ( ptr + 232 ) |
| 846 |
# asm 1: xorq 232(<ptr=int64#4),<h15=int64#13 |
| 847 |
# asm 2: xorq 232(<ptr=%rcx),<h15=%r15 |
| 848 |
xorq 232(%rcx),%r15 |
| 849 |
|
| 850 |
# qhasm: h6 ^= h15 |
| 851 |
# asm 1: XOR <h15=int64#13,<h6=int64#10 |
| 852 |
# asm 2: XOR <h15=%r15,<h6=%r12 |
| 853 |
XOR %r15,%r12 |
| 854 |
|
| 855 |
# qhasm: h3 = h15 |
| 856 |
# asm 1: mov <h15=int64#13,>h3=int64#13 |
| 857 |
# asm 2: mov <h15=%r15,>h3=%r15 |
| 858 |
mov %r15,%r15 |
| 859 |
|
| 860 |
# qhasm: h14 = mem64[ ptr + 216 ] |
| 861 |
# asm 1: movq 216(<ptr=int64#4),>h14=int64#14 |
| 862 |
# asm 2: movq 216(<ptr=%rcx),>h14=%rbx |
| 863 |
movq 216(%rcx),%rbx |
| 864 |
|
| 865 |
# qhasm: h14 ^= *(uint64 *) ( ptr + 224 ) |
| 866 |
# asm 1: xorq 224(<ptr=int64#4),<h14=int64#14 |
| 867 |
# asm 2: xorq 224(<ptr=%rcx),<h14=%rbx |
| 868 |
xorq 224(%rcx),%rbx |
| 869 |
|
| 870 |
# qhasm: h5 ^= h14 |
| 871 |
# asm 1: XOR <h14=int64#14,<h5=int64#11 |
| 872 |
# asm 2: XOR <h14=%rbx,<h5=%r13 |
| 873 |
XOR %rbx,%r13 |
| 874 |
|
| 875 |
# qhasm: h2 = h14 |
| 876 |
# asm 1: mov <h14=int64#14,>h2=int64#14 |
| 877 |
# asm 2: mov <h14=%rbx,>h2=%rbx |
| 878 |
mov %rbx,%rbx |
| 879 |
|
| 880 |
# qhasm: h13 ^= *(uint64 *) ( ptr + 208 ) |
| 881 |
# asm 1: xorq 208(<ptr=int64#4),<h13=int64#3 |
| 882 |
# asm 2: xorq 208(<ptr=%rcx),<h13=%rdx |
| 883 |
xorq 208(%rcx),%rdx |
| 884 |
|
| 885 |
# qhasm: h13 ^= *(uint64 *) ( ptr + 200 ) |
| 886 |
# asm 1: xorq 200(<ptr=int64#4),<h13=int64#3 |
| 887 |
# asm 2: xorq 200(<ptr=%rcx),<h13=%rdx |
| 888 |
xorq 200(%rcx),%rdx |
| 889 |
|
| 890 |
# qhasm: h4 ^= h13 |
| 891 |
# asm 1: XOR <h13=int64#3,<h4=int64#12 |
| 892 |
# asm 2: XOR <h13=%rdx,<h4=%r14 |
| 893 |
XOR %rdx,%r14 |
| 894 |
|
| 895 |
# qhasm: h1 = h13 |
| 896 |
# asm 1: mov <h13=int64#3,>h1=int64#3 |
| 897 |
# asm 2: mov <h13=%rdx,>h1=%rdx |
| 898 |
mov %rdx,%rdx |
| 899 |
|
| 900 |
# qhasm: h12 ^= *(uint64 *) ( ptr + 184 ) |
| 901 |
# asm 1: xorq 184(<ptr=int64#4),<h12=int64#6 |
| 902 |
# asm 2: xorq 184(<ptr=%rcx),<h12=%r9 |
| 903 |
xorq 184(%rcx),%r9 |
| 904 |
|
| 905 |
# qhasm: h12 ^= *(uint64 *) ( ptr + 192 ) |
| 906 |
# asm 1: xorq 192(<ptr=int64#4),<h12=int64#6 |
| 907 |
# asm 2: xorq 192(<ptr=%rcx),<h12=%r9 |
| 908 |
xorq 192(%rcx),%r9 |
| 909 |
|
| 910 |
# qhasm: h3 ^= h12 |
| 911 |
# asm 1: XOR <h12=int64#6,<h3=int64#13 |
| 912 |
# asm 2: XOR <h12=%r9,<h3=%r15 |
| 913 |
XOR %r9,%r15 |
| 914 |
|
| 915 |
# qhasm: h0 = h12 |
| 916 |
# asm 1: mov <h12=int64#6,>h0=int64#6 |
| 917 |
# asm 2: mov <h12=%r9,>h0=%r9 |
| 918 |
mov %r9,%r9 |
| 919 |
|
| 920 |
# qhasm: h11 ^= *(uint64 *) ( ptr + 176 ) |
| 921 |
# asm 1: xorq 176(<ptr=int64#4),<h11=int64#8 |
| 922 |
# asm 2: xorq 176(<ptr=%rcx),<h11=%r10 |
| 923 |
xorq 176(%rcx),%r10 |
| 924 |
|
| 925 |
# qhasm: h11 ^= *(uint64 *) ( ptr + 168 ) |
| 926 |
# asm 1: xorq 168(<ptr=int64#4),<h11=int64#8 |
| 927 |
# asm 2: xorq 168(<ptr=%rcx),<h11=%r10 |
| 928 |
xorq 168(%rcx),%r10 |
| 929 |
|
| 930 |
# qhasm: mem64[ input_0 + 88 ] = h11 |
| 931 |
# asm 1: movq <h11=int64#8,88(<input_0=int64#1) |
| 932 |
# asm 2: movq <h11=%r10,88(<input_0=%rdi) |
| 933 |
movq %r10,88(%rdi) |
| 934 |
|
| 935 |
# qhasm: h10 ^= *(uint64 *) ( ptr + 152 ) |
| 936 |
# asm 1: xorq 152(<ptr=int64#4),<h10=int64#2 |
| 937 |
# asm 2: xorq 152(<ptr=%rcx),<h10=%rsi |
| 938 |
xorq 152(%rcx),%rsi |
| 939 |
|
| 940 |
# qhasm: h10 ^= *(uint64 *) ( ptr + 160 ) |
| 941 |
# asm 1: xorq 160(<ptr=int64#4),<h10=int64#2 |
| 942 |
# asm 2: xorq 160(<ptr=%rcx),<h10=%rsi |
| 943 |
xorq 160(%rcx),%rsi |
| 944 |
|
| 945 |
# qhasm: mem64[ input_0 + 80 ] = h10 |
| 946 |
# asm 1: movq <h10=int64#2,80(<input_0=int64#1) |
| 947 |
# asm 2: movq <h10=%rsi,80(<input_0=%rdi) |
| 948 |
movq %rsi,80(%rdi) |
| 949 |
|
| 950 |
# qhasm: h9 ^= *(uint64 *) ( ptr + 144 ) |
| 951 |
# asm 1: xorq 144(<ptr=int64#4),<h9=int64#5 |
| 952 |
# asm 2: xorq 144(<ptr=%rcx),<h9=%r8 |
| 953 |
xorq 144(%rcx),%r8 |
| 954 |
|
| 955 |
# qhasm: h9 ^= *(uint64 *) ( ptr + 136 ) |
| 956 |
# asm 1: xorq 136(<ptr=int64#4),<h9=int64#5 |
| 957 |
# asm 2: xorq 136(<ptr=%rcx),<h9=%r8 |
| 958 |
xorq 136(%rcx),%r8 |
| 959 |
|
| 960 |
# qhasm: mem64[ input_0 + 72 ] = h9 |
| 961 |
# asm 1: movq <h9=int64#5,72(<input_0=int64#1) |
| 962 |
# asm 2: movq <h9=%r8,72(<input_0=%rdi) |
| 963 |
movq %r8,72(%rdi) |
| 964 |
|
| 965 |
# qhasm: h8 ^= *(uint64 *) ( ptr + 120 ) |
| 966 |
# asm 1: xorq 120(<ptr=int64#4),<h8=int64#7 |
| 967 |
# asm 2: xorq 120(<ptr=%rcx),<h8=%rax |
| 968 |
xorq 120(%rcx),%rax |
| 969 |
|
| 970 |
# qhasm: h8 ^= *(uint64 *) ( ptr + 128 ) |
| 971 |
# asm 1: xorq 128(<ptr=int64#4),<h8=int64#7 |
| 972 |
# asm 2: xorq 128(<ptr=%rcx),<h8=%rax |
| 973 |
xorq 128(%rcx),%rax |
| 974 |
|
| 975 |
# qhasm: mem64[ input_0 + 64 ] = h8 |
| 976 |
# asm 1: movq <h8=int64#7,64(<input_0=int64#1) |
| 977 |
# asm 2: movq <h8=%rax,64(<input_0=%rdi) |
| 978 |
movq %rax,64(%rdi) |
| 979 |
|
| 980 |
# qhasm: h7 ^= *(uint64 *) ( ptr + 112 ) |
| 981 |
# asm 1: xorq 112(<ptr=int64#4),<h7=int64#9 |
| 982 |
# asm 2: xorq 112(<ptr=%rcx),<h7=%r11 |
| 983 |
xorq 112(%rcx),%r11 |
| 984 |
|
| 985 |
# qhasm: h7 ^= *(uint64 *) ( ptr + 104 ) |
| 986 |
# asm 1: xorq 104(<ptr=int64#4),<h7=int64#9 |
| 987 |
# asm 2: xorq 104(<ptr=%rcx),<h7=%r11 |
| 988 |
xorq 104(%rcx),%r11 |
| 989 |
|
| 990 |
# qhasm: mem64[ input_0 + 56 ] = h7 |
| 991 |
# asm 1: movq <h7=int64#9,56(<input_0=int64#1) |
| 992 |
# asm 2: movq <h7=%r11,56(<input_0=%rdi) |
| 993 |
movq %r11,56(%rdi) |
| 994 |
|
| 995 |
# qhasm: h6 ^= *(uint64 *) ( ptr + 88 ) |
| 996 |
# asm 1: xorq 88(<ptr=int64#4),<h6=int64#10 |
| 997 |
# asm 2: xorq 88(<ptr=%rcx),<h6=%r12 |
| 998 |
xorq 88(%rcx),%r12 |
| 999 |
|
| 1000 |
# qhasm: h6 ^= *(uint64 *) ( ptr + 96 ) |
| 1001 |
# asm 1: xorq 96(<ptr=int64#4),<h6=int64#10 |
| 1002 |
# asm 2: xorq 96(<ptr=%rcx),<h6=%r12 |
| 1003 |
xorq 96(%rcx),%r12 |
| 1004 |
|
| 1005 |
# qhasm: mem64[ input_0 + 48 ] = h6 |
| 1006 |
# asm 1: movq <h6=int64#10,48(<input_0=int64#1) |
| 1007 |
# asm 2: movq <h6=%r12,48(<input_0=%rdi) |
| 1008 |
movq %r12,48(%rdi) |
| 1009 |
|
| 1010 |
# qhasm: h5 ^= *(uint64 *) ( ptr + 80 ) |
| 1011 |
# asm 1: xorq 80(<ptr=int64#4),<h5=int64#11 |
| 1012 |
# asm 2: xorq 80(<ptr=%rcx),<h5=%r13 |
| 1013 |
xorq 80(%rcx),%r13 |
| 1014 |
|
| 1015 |
# qhasm: h5 ^= *(uint64 *) ( ptr + 72 ) |
| 1016 |
# asm 1: xorq 72(<ptr=int64#4),<h5=int64#11 |
| 1017 |
# asm 2: xorq 72(<ptr=%rcx),<h5=%r13 |
| 1018 |
xorq 72(%rcx),%r13 |
| 1019 |
|
| 1020 |
# qhasm: mem64[ input_0 + 40 ] = h5 |
| 1021 |
# asm 1: movq <h5=int64#11,40(<input_0=int64#1) |
| 1022 |
# asm 2: movq <h5=%r13,40(<input_0=%rdi) |
| 1023 |
movq %r13,40(%rdi) |
| 1024 |
|
| 1025 |
# qhasm: h4 ^= *(uint64 *) ( ptr + 56 ) |
| 1026 |
# asm 1: xorq 56(<ptr=int64#4),<h4=int64#12 |
| 1027 |
# asm 2: xorq 56(<ptr=%rcx),<h4=%r14 |
| 1028 |
xorq 56(%rcx),%r14 |
| 1029 |
|
| 1030 |
# qhasm: h4 ^= *(uint64 *) ( ptr + 64 ) |
| 1031 |
# asm 1: xorq 64(<ptr=int64#4),<h4=int64#12 |
| 1032 |
# asm 2: xorq 64(<ptr=%rcx),<h4=%r14 |
| 1033 |
xorq 64(%rcx),%r14 |
| 1034 |
|
| 1035 |
# qhasm: mem64[ input_0 + 32 ] = h4 |
| 1036 |
# asm 1: movq <h4=int64#12,32(<input_0=int64#1) |
| 1037 |
# asm 2: movq <h4=%r14,32(<input_0=%rdi) |
| 1038 |
movq %r14,32(%rdi) |
| 1039 |
|
| 1040 |
# qhasm: h3 ^= *(uint64 *) ( ptr + 48 ) |
| 1041 |
# asm 1: xorq 48(<ptr=int64#4),<h3=int64#13 |
| 1042 |
# asm 2: xorq 48(<ptr=%rcx),<h3=%r15 |
| 1043 |
xorq 48(%rcx),%r15 |
| 1044 |
|
| 1045 |
# qhasm: h3 ^= *(uint64 *) ( ptr + 40 ) |
| 1046 |
# asm 1: xorq 40(<ptr=int64#4),<h3=int64#13 |
| 1047 |
# asm 2: xorq 40(<ptr=%rcx),<h3=%r15 |
| 1048 |
xorq 40(%rcx),%r15 |
| 1049 |
|
| 1050 |
# qhasm: mem64[ input_0 + 24 ] = h3 |
| 1051 |
# asm 1: movq <h3=int64#13,24(<input_0=int64#1) |
| 1052 |
# asm 2: movq <h3=%r15,24(<input_0=%rdi) |
| 1053 |
movq %r15,24(%rdi) |
| 1054 |
|
| 1055 |
# qhasm: h2 ^= *(uint64 *) ( ptr + 24 ) |
| 1056 |
# asm 1: xorq 24(<ptr=int64#4),<h2=int64#14 |
| 1057 |
# asm 2: xorq 24(<ptr=%rcx),<h2=%rbx |
| 1058 |
xorq 24(%rcx),%rbx |
| 1059 |
|
| 1060 |
# qhasm: h2 ^= *(uint64 *) ( ptr + 32 ) |
| 1061 |
# asm 1: xorq 32(<ptr=int64#4),<h2=int64#14 |
| 1062 |
# asm 2: xorq 32(<ptr=%rcx),<h2=%rbx |
| 1063 |
xorq 32(%rcx),%rbx |
| 1064 |
|
| 1065 |
# qhasm: mem64[ input_0 + 16 ] = h2 |
| 1066 |
# asm 1: movq <h2=int64#14,16(<input_0=int64#1) |
| 1067 |
# asm 2: movq <h2=%rbx,16(<input_0=%rdi) |
| 1068 |
movq %rbx,16(%rdi) |
| 1069 |
|
| 1070 |
# qhasm: h1 ^= *(uint64 *) ( ptr + 16 ) |
| 1071 |
# asm 1: xorq 16(<ptr=int64#4),<h1=int64#3 |
| 1072 |
# asm 2: xorq 16(<ptr=%rcx),<h1=%rdx |
| 1073 |
xorq 16(%rcx),%rdx |
| 1074 |
|
| 1075 |
# qhasm: h1 ^= *(uint64 *) ( ptr + 8 ) |
| 1076 |
# asm 1: xorq 8(<ptr=int64#4),<h1=int64#3 |
| 1077 |
# asm 2: xorq 8(<ptr=%rcx),<h1=%rdx |
| 1078 |
xorq 8(%rcx),%rdx |
| 1079 |
|
| 1080 |
# qhasm: mem64[ input_0 + 8 ] = h1 |
| 1081 |
# asm 1: movq <h1=int64#3,8(<input_0=int64#1) |
| 1082 |
# asm 2: movq <h1=%rdx,8(<input_0=%rdi) |
| 1083 |
movq %rdx,8(%rdi) |
| 1084 |
|
| 1085 |
# qhasm: h0 ^= *(uint64 *) ( ptr + 0 ) |
| 1086 |
# asm 1: xorq 0(<ptr=int64#4),<h0=int64#6 |
| 1087 |
# asm 2: xorq 0(<ptr=%rcx),<h0=%r9 |
| 1088 |
xorq 0(%rcx),%r9 |
| 1089 |
|
| 1090 |
# qhasm: mem64[ input_0 + 0 ] = h0 |
| 1091 |
# asm 1: movq <h0=int64#6,0(<input_0=int64#1) |
| 1092 |
# asm 2: movq <h0=%r9,0(<input_0=%rdi) |
| 1093 |
movq %r9,0(%rdi) |
| 1094 |
|
| 1095 |
# qhasm: caller_r11 = r11_stack |
| 1096 |
# asm 1: movq <r11_stack=stack64#1,>caller_r11=int64#9 |
| 1097 |
# asm 2: movq <r11_stack=608(%rsp),>caller_r11=%r11 |
| 1098 |
movq 608(%rsp),%r11 |
| 1099 |
|
| 1100 |
# qhasm: caller_r12 = r12_stack |
| 1101 |
# asm 1: movq <r12_stack=stack64#2,>caller_r12=int64#10 |
| 1102 |
# asm 2: movq <r12_stack=616(%rsp),>caller_r12=%r12 |
| 1103 |
movq 616(%rsp),%r12 |
| 1104 |
|
| 1105 |
# qhasm: caller_r13 = r13_stack |
| 1106 |
# asm 1: movq <r13_stack=stack64#3,>caller_r13=int64#11 |
| 1107 |
# asm 2: movq <r13_stack=624(%rsp),>caller_r13=%r13 |
| 1108 |
movq 624(%rsp),%r13 |
| 1109 |
|
| 1110 |
# qhasm: caller_r14 = r14_stack |
| 1111 |
# asm 1: movq <r14_stack=stack64#4,>caller_r14=int64#12 |
| 1112 |
# asm 2: movq <r14_stack=632(%rsp),>caller_r14=%r14 |
| 1113 |
movq 632(%rsp),%r14 |
| 1114 |
|
| 1115 |
# qhasm: caller_r15 = r15_stack |
| 1116 |
# asm 1: movq <r15_stack=stack64#5,>caller_r15=int64#13 |
| 1117 |
# asm 2: movq <r15_stack=640(%rsp),>caller_r15=%r15 |
| 1118 |
movq 640(%rsp),%r15 |
| 1119 |
|
| 1120 |
# qhasm: caller_rbx = rbx_stack |
| 1121 |
# asm 1: movq <rbx_stack=stack64#6,>caller_rbx=int64#14 |
| 1122 |
# asm 2: movq <rbx_stack=648(%rsp),>caller_rbx=%rbx |
| 1123 |
movq 648(%rsp),%rbx |
| 1124 |
|
| 1125 |
# qhasm: return |
| 1126 |
add %r11,%rsp |
| 1127 |
ret |
| 1128 |
.section .note.GNU-stack,"",@progbits |