Debian Codegraph @

crypto_kem/6688128pcf/avx/vec128_mul_asm.S

raw
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 vec128_mul_asm
6
7 #include "crypto_asm_hidden.h"
8
9 #define vec128_mul_asm CRYPTO_SHARED_NAMESPACE(vec128_mul_asm)
10 #define _vec128_mul_asm _CRYPTO_SHARED_NAMESPACE(vec128_mul_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 b0
43
44 # qhasm: reg256 b1
45
46 # qhasm: reg256 b2
47
48 # qhasm: reg256 b3
49
50 # qhasm: reg256 b4
51
52 # qhasm: reg256 b5
53
54 # qhasm: reg256 b6
55
56 # qhasm: reg256 b7
57
58 # qhasm: reg256 b8
59
60 # qhasm: reg256 b9
61
62 # qhasm: reg256 b10
63
64 # qhasm: reg256 b11
65
66 # qhasm: reg256 b12
67
68 # qhasm: reg256 a0
69
70 # qhasm: reg256 a1
71
72 # qhasm: reg256 a2
73
74 # qhasm: reg256 a3
75
76 # qhasm: reg256 a4
77
78 # qhasm: reg256 a5
79
80 # qhasm: reg256 a6
81
82 # qhasm: reg256 r0
83
84 # qhasm: reg256 r1
85
86 # qhasm: reg256 r2
87
88 # qhasm: reg256 r3
89
90 # qhasm: reg256 r4
91
92 # qhasm: reg256 r5
93
94 # qhasm: reg256 r6
95
96 # qhasm: reg256 r7
97
98 # qhasm: reg256 r8
99
100 # qhasm: reg256 r9
101
102 # qhasm: reg256 r10
103
104 # qhasm: reg256 r11
105
106 # qhasm: reg256 r12
107
108 # qhasm: reg256 r13
109
110 # qhasm: reg256 r14
111
112 # qhasm: reg256 r15
113
114 # qhasm: reg256 r16
115
116 # qhasm: reg256 r17
117
118 # qhasm: reg256 r18
119
120 # qhasm: reg256 r19
121
122 # qhasm: reg256 r20
123
124 # qhasm: reg256 r21
125
126 # qhasm: reg256 r22
127
128 # qhasm: reg256 r23
129
130 # qhasm: reg256 r24
131
132 # qhasm: reg256 r
133
134 # qhasm: reg128 h0
135
136 # qhasm: reg128 h1
137
138 # qhasm: reg128 h2
139
140 # qhasm: reg128 h3
141
142 # qhasm: reg128 h4
143
144 # qhasm: reg128 h5
145
146 # qhasm: reg128 h6
147
148 # qhasm: reg128 h7
149
150 # qhasm: reg128 h8
151
152 # qhasm: reg128 h9
153
154 # qhasm: reg128 h10
155
156 # qhasm: reg128 h11
157
158 # qhasm: reg128 h12
159
160 # qhasm: reg128 h13
161
162 # qhasm: reg128 h14
163
164 # qhasm: reg128 h15
165
166 # qhasm: reg128 h16
167
168 # qhasm: reg128 h17
169
170 # qhasm: reg128 h18
171
172 # qhasm: reg128 h19
173
174 # qhasm: reg128 h20
175
176 # qhasm: reg128 h21
177
178 # qhasm: reg128 h22
179
180 # qhasm: reg128 h23
181
182 # qhasm: reg128 h24
183
184 # qhasm: stack4864 buf
185
186 # qhasm: int64 ptr
187
188 # qhasm: int64 tmp
189
190 # qhasm: enter vec128_mul_asm
191 .p2align 5
192 ASM_HIDDEN _vec128_mul_asm
193 ASM_HIDDEN vec128_mul_asm
194 .global _vec128_mul_asm
195 .global vec128_mul_asm
196 _vec128_mul_asm:
197 vec128_mul_asm:
198 mov %rsp,%r11
199 AND $31,%r11
200 add $608,%r11
201 sub %r11,%rsp
202
203 # qhasm: ptr = &buf
204 # asm 1: leaq <buf=stack4864#1,>ptr=int64#5
205 # asm 2: leaq <buf=0(%rsp),>ptr=%r8
206 leaq 0(%rsp),%r8
207
208 # qhasm: tmp = input_3
209 # asm 1: mov <input_3=int64#4,>tmp=int64#6
210 # asm 2: mov <input_3=%rcx,>tmp=%r9
211 mov %rcx,%r9
212
213 # qhasm: tmp *= 12
214 # asm 1: imulq $12,<tmp=int64#6,>tmp=int64#6
215 # asm 2: imulq $12,<tmp=%r9,>tmp=%r9
216 imulq $12,%r9,%r9
217
218 # qhasm: input_2 += tmp
219 # asm 1: add <tmp=int64#6,<input_2=int64#3
220 # asm 2: add <tmp=%r9,<input_2=%rdx
221 add %r9,%rdx
222
223 # qhasm: b12 = mem128[ input_2 + 0 ] x2
224 # asm 1: vbroadcasti128 0(<input_2=int64#3), >b12=reg256#1
225 # asm 2: vbroadcasti128 0(<input_2=%rdx), >b12=%ymm0
226 vbroadcasti128 0(%rdx), %ymm0
227
228 # qhasm: input_2 -= input_3
229 # asm 1: sub <input_3=int64#4,<input_2=int64#3
230 # asm 2: sub <input_3=%rcx,<input_2=%rdx
231 sub %rcx,%rdx
232
233 # qhasm: a6 = a6 ^ a6
234 # asm 1: vpxor <a6=reg256#2,<a6=reg256#2,>a6=reg256#2
235 # asm 2: vpxor <a6=%ymm1,<a6=%ymm1,>a6=%ymm1
236 vpxor %ymm1,%ymm1,%ymm1
237
238 # qhasm: a6[0] = mem128[ input_1 + 96 ]
239 # asm 1: vinsertf128 $0x0,96(<input_1=int64#2),<a6=reg256#2,<a6=reg256#2
240 # asm 2: vinsertf128 $0x0,96(<input_1=%rsi),<a6=%ymm1,<a6=%ymm1
241 vinsertf128 $0x0,96(%rsi),%ymm1,%ymm1
242
243 # qhasm: r18 = b12 & a6
244 # asm 1: vpand <b12=reg256#1,<a6=reg256#2,>r18=reg256#3
245 # asm 2: vpand <b12=%ymm0,<a6=%ymm1,>r18=%ymm2
246 vpand %ymm0,%ymm1,%ymm2
247
248 # qhasm: mem256[ ptr + 576 ] = r18
249 # asm 1: vmovupd <r18=reg256#3,576(<ptr=int64#5)
250 # asm 2: vmovupd <r18=%ymm2,576(<ptr=%r8)
251 vmovupd %ymm2,576(%r8)
252
253 # qhasm: a5[0] = mem128[ input_1 + 80 ]
254 # asm 1: vinsertf128 $0x0,80(<input_1=int64#2),<a5=reg256#3,<a5=reg256#3
255 # asm 2: vinsertf128 $0x0,80(<input_1=%rsi),<a5=%ymm2,<a5=%ymm2
256 vinsertf128 $0x0,80(%rsi),%ymm2,%ymm2
257
258 # qhasm: a5[1] = mem128[ input_1 + 192 ]
259 # asm 1: vinsertf128 $0x1,192(<input_1=int64#2),<a5=reg256#3,<a5=reg256#3
260 # asm 2: vinsertf128 $0x1,192(<input_1=%rsi),<a5=%ymm2,<a5=%ymm2
261 vinsertf128 $0x1,192(%rsi),%ymm2,%ymm2
262
263 # qhasm: r17 = b12 & a5
264 # asm 1: vpand <b12=reg256#1,<a5=reg256#3,>r17=reg256#4
265 # asm 2: vpand <b12=%ymm0,<a5=%ymm2,>r17=%ymm3
266 vpand %ymm0,%ymm2,%ymm3
267
268 # qhasm: a4[0] = mem128[ input_1 + 64 ]
269 # asm 1: vinsertf128 $0x0,64(<input_1=int64#2),<a4=reg256#5,<a4=reg256#5
270 # asm 2: vinsertf128 $0x0,64(<input_1=%rsi),<a4=%ymm4,<a4=%ymm4
271 vinsertf128 $0x0,64(%rsi),%ymm4,%ymm4
272
273 # qhasm: a4[1] = mem128[ input_1 + 176 ]
274 # asm 1: vinsertf128 $0x1,176(<input_1=int64#2),<a4=reg256#5,<a4=reg256#5
275 # asm 2: vinsertf128 $0x1,176(<input_1=%rsi),<a4=%ymm4,<a4=%ymm4
276 vinsertf128 $0x1,176(%rsi),%ymm4,%ymm4
277
278 # qhasm: r16 = b12 & a4
279 # asm 1: vpand <b12=reg256#1,<a4=reg256#5,>r16=reg256#6
280 # asm 2: vpand <b12=%ymm0,<a4=%ymm4,>r16=%ymm5
281 vpand %ymm0,%ymm4,%ymm5
282
283 # qhasm: a3[0] = mem128[ input_1 + 48 ]
284 # asm 1: vinsertf128 $0x0,48(<input_1=int64#2),<a3=reg256#7,<a3=reg256#7
285 # asm 2: vinsertf128 $0x0,48(<input_1=%rsi),<a3=%ymm6,<a3=%ymm6
286 vinsertf128 $0x0,48(%rsi),%ymm6,%ymm6
287
288 # qhasm: a3[1] = mem128[ input_1 + 160 ]
289 # asm 1: vinsertf128 $0x1,160(<input_1=int64#2),<a3=reg256#7,<a3=reg256#7
290 # asm 2: vinsertf128 $0x1,160(<input_1=%rsi),<a3=%ymm6,<a3=%ymm6
291 vinsertf128 $0x1,160(%rsi),%ymm6,%ymm6
292
293 # qhasm: r15 = b12 & a3
294 # asm 1: vpand <b12=reg256#1,<a3=reg256#7,>r15=reg256#8
295 # asm 2: vpand <b12=%ymm0,<a3=%ymm6,>r15=%ymm7
296 vpand %ymm0,%ymm6,%ymm7
297
298 # qhasm: a2[0] = mem128[ input_1 + 32 ]
299 # asm 1: vinsertf128 $0x0,32(<input_1=int64#2),<a2=reg256#9,<a2=reg256#9
300 # asm 2: vinsertf128 $0x0,32(<input_1=%rsi),<a2=%ymm8,<a2=%ymm8
301 vinsertf128 $0x0,32(%rsi),%ymm8,%ymm8
302
303 # qhasm: a2[1] = mem128[ input_1 + 144 ]
304 # asm 1: vinsertf128 $0x1,144(<input_1=int64#2),<a2=reg256#9,<a2=reg256#9
305 # asm 2: vinsertf128 $0x1,144(<input_1=%rsi),<a2=%ymm8,<a2=%ymm8
306 vinsertf128 $0x1,144(%rsi),%ymm8,%ymm8
307
308 # qhasm: r14 = b12 & a2
309 # asm 1: vpand <b12=reg256#1,<a2=reg256#9,>r14=reg256#10
310 # asm 2: vpand <b12=%ymm0,<a2=%ymm8,>r14=%ymm9
311 vpand %ymm0,%ymm8,%ymm9
312
313 # qhasm: a1[0] = mem128[ input_1 + 16 ]
314 # asm 1: vinsertf128 $0x0,16(<input_1=int64#2),<a1=reg256#11,<a1=reg256#11
315 # asm 2: vinsertf128 $0x0,16(<input_1=%rsi),<a1=%ymm10,<a1=%ymm10
316 vinsertf128 $0x0,16(%rsi),%ymm10,%ymm10
317
318 # qhasm: a1[1] = mem128[ input_1 + 128 ]
319 # asm 1: vinsertf128 $0x1,128(<input_1=int64#2),<a1=reg256#11,<a1=reg256#11
320 # asm 2: vinsertf128 $0x1,128(<input_1=%rsi),<a1=%ymm10,<a1=%ymm10
321 vinsertf128 $0x1,128(%rsi),%ymm10,%ymm10
322
323 # qhasm: r13 = b12 & a1
324 # asm 1: vpand <b12=reg256#1,<a1=reg256#11,>r13=reg256#12
325 # asm 2: vpand <b12=%ymm0,<a1=%ymm10,>r13=%ymm11
326 vpand %ymm0,%ymm10,%ymm11
327
328 # qhasm: a0[0] = mem128[ input_1 + 0 ]
329 # asm 1: vinsertf128 $0x0,0(<input_1=int64#2),<a0=reg256#13,<a0=reg256#13
330 # asm 2: vinsertf128 $0x0,0(<input_1=%rsi),<a0=%ymm12,<a0=%ymm12
331 vinsertf128 $0x0,0(%rsi),%ymm12,%ymm12
332
333 # qhasm: a0[1] = mem128[ input_1 + 112 ]
334 # asm 1: vinsertf128 $0x1,112(<input_1=int64#2),<a0=reg256#13,<a0=reg256#13
335 # asm 2: vinsertf128 $0x1,112(<input_1=%rsi),<a0=%ymm12,<a0=%ymm12
336 vinsertf128 $0x1,112(%rsi),%ymm12,%ymm12
337
338 # qhasm: r12 = b12 & a0
339 # asm 1: vpand <b12=reg256#1,<a0=reg256#13,>r12=reg256#1
340 # asm 2: vpand <b12=%ymm0,<a0=%ymm12,>r12=%ymm0
341 vpand %ymm0,%ymm12,%ymm0
342
343 # qhasm: b11 = mem128[ input_2 + 0 ] x2
344 # asm 1: vbroadcasti128 0(<input_2=int64#3), >b11=reg256#14
345 # asm 2: vbroadcasti128 0(<input_2=%rdx), >b11=%ymm13
346 vbroadcasti128 0(%rdx), %ymm13
347
348 # qhasm: input_2 -= input_3
349 # asm 1: sub <input_3=int64#4,<input_2=int64#3
350 # asm 2: sub <input_3=%rcx,<input_2=%rdx
351 sub %rcx,%rdx
352
353 # qhasm: r = b11 & a6
354 # asm 1: vpand <b11=reg256#14,<a6=reg256#2,>r=reg256#15
355 # asm 2: vpand <b11=%ymm13,<a6=%ymm1,>r=%ymm14
356 vpand %ymm13,%ymm1,%ymm14
357
358 # qhasm: r17 ^= r
359 # asm 1: vpxor <r=reg256#15,<r17=reg256#4,<r17=reg256#4
360 # asm 2: vpxor <r=%ymm14,<r17=%ymm3,<r17=%ymm3
361 vpxor %ymm14,%ymm3,%ymm3
362
363 # qhasm: mem256[ ptr + 544 ] = r17
364 # asm 1: vmovupd <r17=reg256#4,544(<ptr=int64#5)
365 # asm 2: vmovupd <r17=%ymm3,544(<ptr=%r8)
366 vmovupd %ymm3,544(%r8)
367
368 # qhasm: r = b11 & a5
369 # asm 1: vpand <b11=reg256#14,<a5=reg256#3,>r=reg256#4
370 # asm 2: vpand <b11=%ymm13,<a5=%ymm2,>r=%ymm3
371 vpand %ymm13,%ymm2,%ymm3
372
373 # qhasm: r16 ^= r
374 # asm 1: vpxor <r=reg256#4,<r16=reg256#6,<r16=reg256#6
375 # asm 2: vpxor <r=%ymm3,<r16=%ymm5,<r16=%ymm5
376 vpxor %ymm3,%ymm5,%ymm5
377
378 # qhasm: r = b11 & a4
379 # asm 1: vpand <b11=reg256#14,<a4=reg256#5,>r=reg256#4
380 # asm 2: vpand <b11=%ymm13,<a4=%ymm4,>r=%ymm3
381 vpand %ymm13,%ymm4,%ymm3
382
383 # qhasm: r15 ^= r
384 # asm 1: vpxor <r=reg256#4,<r15=reg256#8,<r15=reg256#8
385 # asm 2: vpxor <r=%ymm3,<r15=%ymm7,<r15=%ymm7
386 vpxor %ymm3,%ymm7,%ymm7
387
388 # qhasm: r = b11 & a3
389 # asm 1: vpand <b11=reg256#14,<a3=reg256#7,>r=reg256#4
390 # asm 2: vpand <b11=%ymm13,<a3=%ymm6,>r=%ymm3
391 vpand %ymm13,%ymm6,%ymm3
392
393 # qhasm: r14 ^= r
394 # asm 1: vpxor <r=reg256#4,<r14=reg256#10,<r14=reg256#10
395 # asm 2: vpxor <r=%ymm3,<r14=%ymm9,<r14=%ymm9
396 vpxor %ymm3,%ymm9,%ymm9
397
398 # qhasm: r = b11 & a2
399 # asm 1: vpand <b11=reg256#14,<a2=reg256#9,>r=reg256#4
400 # asm 2: vpand <b11=%ymm13,<a2=%ymm8,>r=%ymm3
401 vpand %ymm13,%ymm8,%ymm3
402
403 # qhasm: r13 ^= r
404 # asm 1: vpxor <r=reg256#4,<r13=reg256#12,<r13=reg256#12
405 # asm 2: vpxor <r=%ymm3,<r13=%ymm11,<r13=%ymm11
406 vpxor %ymm3,%ymm11,%ymm11
407
408 # qhasm: r = b11 & a1
409 # asm 1: vpand <b11=reg256#14,<a1=reg256#11,>r=reg256#4
410 # asm 2: vpand <b11=%ymm13,<a1=%ymm10,>r=%ymm3
411 vpand %ymm13,%ymm10,%ymm3
412
413 # qhasm: r12 ^= r
414 # asm 1: vpxor <r=reg256#4,<r12=reg256#1,<r12=reg256#1
415 # asm 2: vpxor <r=%ymm3,<r12=%ymm0,<r12=%ymm0
416 vpxor %ymm3,%ymm0,%ymm0
417
418 # qhasm: r11 = b11 & a0
419 # asm 1: vpand <b11=reg256#14,<a0=reg256#13,>r11=reg256#4
420 # asm 2: vpand <b11=%ymm13,<a0=%ymm12,>r11=%ymm3
421 vpand %ymm13,%ymm12,%ymm3
422
423 # qhasm: b10 = mem128[ input_2 + 0 ] x2
424 # asm 1: vbroadcasti128 0(<input_2=int64#3), >b10=reg256#14
425 # asm 2: vbroadcasti128 0(<input_2=%rdx), >b10=%ymm13
426 vbroadcasti128 0(%rdx), %ymm13
427
428 # qhasm: input_2 -= input_3
429 # asm 1: sub <input_3=int64#4,<input_2=int64#3
430 # asm 2: sub <input_3=%rcx,<input_2=%rdx
431 sub %rcx,%rdx
432
433 # qhasm: r = b10 & a6
434 # asm 1: vpand <b10=reg256#14,<a6=reg256#2,>r=reg256#15
435 # asm 2: vpand <b10=%ymm13,<a6=%ymm1,>r=%ymm14
436 vpand %ymm13,%ymm1,%ymm14
437
438 # qhasm: r16 ^= r
439 # asm 1: vpxor <r=reg256#15,<r16=reg256#6,<r16=reg256#6
440 # asm 2: vpxor <r=%ymm14,<r16=%ymm5,<r16=%ymm5
441 vpxor %ymm14,%ymm5,%ymm5
442
443 # qhasm: mem256[ ptr + 512 ] = r16
444 # asm 1: vmovupd <r16=reg256#6,512(<ptr=int64#5)
445 # asm 2: vmovupd <r16=%ymm5,512(<ptr=%r8)
446 vmovupd %ymm5,512(%r8)
447
448 # qhasm: r = b10 & a5
449 # asm 1: vpand <b10=reg256#14,<a5=reg256#3,>r=reg256#6
450 # asm 2: vpand <b10=%ymm13,<a5=%ymm2,>r=%ymm5
451 vpand %ymm13,%ymm2,%ymm5
452
453 # qhasm: r15 ^= r
454 # asm 1: vpxor <r=reg256#6,<r15=reg256#8,<r15=reg256#8
455 # asm 2: vpxor <r=%ymm5,<r15=%ymm7,<r15=%ymm7
456 vpxor %ymm5,%ymm7,%ymm7
457
458 # qhasm: r = b10 & a4
459 # asm 1: vpand <b10=reg256#14,<a4=reg256#5,>r=reg256#6
460 # asm 2: vpand <b10=%ymm13,<a4=%ymm4,>r=%ymm5
461 vpand %ymm13,%ymm4,%ymm5
462
463 # qhasm: r14 ^= r
464 # asm 1: vpxor <r=reg256#6,<r14=reg256#10,<r14=reg256#10
465 # asm 2: vpxor <r=%ymm5,<r14=%ymm9,<r14=%ymm9
466 vpxor %ymm5,%ymm9,%ymm9
467
468 # qhasm: r = b10 & a3
469 # asm 1: vpand <b10=reg256#14,<a3=reg256#7,>r=reg256#6
470 # asm 2: vpand <b10=%ymm13,<a3=%ymm6,>r=%ymm5
471 vpand %ymm13,%ymm6,%ymm5
472
473 # qhasm: r13 ^= r
474 # asm 1: vpxor <r=reg256#6,<r13=reg256#12,<r13=reg256#12
475 # asm 2: vpxor <r=%ymm5,<r13=%ymm11,<r13=%ymm11
476 vpxor %ymm5,%ymm11,%ymm11
477
478 # qhasm: r = b10 & a2
479 # asm 1: vpand <b10=reg256#14,<a2=reg256#9,>r=reg256#6
480 # asm 2: vpand <b10=%ymm13,<a2=%ymm8,>r=%ymm5
481 vpand %ymm13,%ymm8,%ymm5
482
483 # qhasm: r12 ^= r
484 # asm 1: vpxor <r=reg256#6,<r12=reg256#1,<r12=reg256#1
485 # asm 2: vpxor <r=%ymm5,<r12=%ymm0,<r12=%ymm0
486 vpxor %ymm5,%ymm0,%ymm0
487
488 # qhasm: r = b10 & a1
489 # asm 1: vpand <b10=reg256#14,<a1=reg256#11,>r=reg256#6
490 # asm 2: vpand <b10=%ymm13,<a1=%ymm10,>r=%ymm5
491 vpand %ymm13,%ymm10,%ymm5
492
493 # qhasm: r11 ^= r
494 # asm 1: vpxor <r=reg256#6,<r11=reg256#4,<r11=reg256#4
495 # asm 2: vpxor <r=%ymm5,<r11=%ymm3,<r11=%ymm3
496 vpxor %ymm5,%ymm3,%ymm3
497
498 # qhasm: r10 = b10 & a0
499 # asm 1: vpand <b10=reg256#14,<a0=reg256#13,>r10=reg256#6
500 # asm 2: vpand <b10=%ymm13,<a0=%ymm12,>r10=%ymm5
501 vpand %ymm13,%ymm12,%ymm5
502
503 # qhasm: b9 = mem128[ input_2 + 0 ] x2
504 # asm 1: vbroadcasti128 0(<input_2=int64#3), >b9=reg256#14
505 # asm 2: vbroadcasti128 0(<input_2=%rdx), >b9=%ymm13
506 vbroadcasti128 0(%rdx), %ymm13
507
508 # qhasm: input_2 -= input_3
509 # asm 1: sub <input_3=int64#4,<input_2=int64#3
510 # asm 2: sub <input_3=%rcx,<input_2=%rdx
511 sub %rcx,%rdx
512
513 # qhasm: r = b9 & a6
514 # asm 1: vpand <b9=reg256#14,<a6=reg256#2,>r=reg256#15
515 # asm 2: vpand <b9=%ymm13,<a6=%ymm1,>r=%ymm14
516 vpand %ymm13,%ymm1,%ymm14
517
518 # qhasm: r15 ^= r
519 # asm 1: vpxor <r=reg256#15,<r15=reg256#8,<r15=reg256#8
520 # asm 2: vpxor <r=%ymm14,<r15=%ymm7,<r15=%ymm7
521 vpxor %ymm14,%ymm7,%ymm7
522
523 # qhasm: mem256[ ptr + 480 ] = r15
524 # asm 1: vmovupd <r15=reg256#8,480(<ptr=int64#5)
525 # asm 2: vmovupd <r15=%ymm7,480(<ptr=%r8)
526 vmovupd %ymm7,480(%r8)
527
528 # qhasm: r = b9 & a5
529 # asm 1: vpand <b9=reg256#14,<a5=reg256#3,>r=reg256#8
530 # asm 2: vpand <b9=%ymm13,<a5=%ymm2,>r=%ymm7
531 vpand %ymm13,%ymm2,%ymm7
532
533 # qhasm: r14 ^= r
534 # asm 1: vpxor <r=reg256#8,<r14=reg256#10,<r14=reg256#10
535 # asm 2: vpxor <r=%ymm7,<r14=%ymm9,<r14=%ymm9
536 vpxor %ymm7,%ymm9,%ymm9
537
538 # qhasm: r = b9 & a4
539 # asm 1: vpand <b9=reg256#14,<a4=reg256#5,>r=reg256#8
540 # asm 2: vpand <b9=%ymm13,<a4=%ymm4,>r=%ymm7
541 vpand %ymm13,%ymm4,%ymm7
542
543 # qhasm: r13 ^= r
544 # asm 1: vpxor <r=reg256#8,<r13=reg256#12,<r13=reg256#12
545 # asm 2: vpxor <r=%ymm7,<r13=%ymm11,<r13=%ymm11
546 vpxor %ymm7,%ymm11,%ymm11
547
548 # qhasm: r = b9 & a3
549 # asm 1: vpand <b9=reg256#14,<a3=reg256#7,>r=reg256#8
550 # asm 2: vpand <b9=%ymm13,<a3=%ymm6,>r=%ymm7
551 vpand %ymm13,%ymm6,%ymm7
552
553 # qhasm: r12 ^= r
554 # asm 1: vpxor <r=reg256#8,<r12=reg256#1,<r12=reg256#1
555 # asm 2: vpxor <r=%ymm7,<r12=%ymm0,<r12=%ymm0
556 vpxor %ymm7,%ymm0,%ymm0
557
558 # qhasm: r = b9 & a2
559 # asm 1: vpand <b9=reg256#14,<a2=reg256#9,>r=reg256#8
560 # asm 2: vpand <b9=%ymm13,<a2=%ymm8,>r=%ymm7
561 vpand %ymm13,%ymm8,%ymm7
562
563 # qhasm: r11 ^= r
564 # asm 1: vpxor <r=reg256#8,<r11=reg256#4,<r11=reg256#4
565 # asm 2: vpxor <r=%ymm7,<r11=%ymm3,<r11=%ymm3
566 vpxor %ymm7,%ymm3,%ymm3
567
568 # qhasm: r = b9 & a1
569 # asm 1: vpand <b9=reg256#14,<a1=reg256#11,>r=reg256#8
570 # asm 2: vpand <b9=%ymm13,<a1=%ymm10,>r=%ymm7
571 vpand %ymm13,%ymm10,%ymm7
572
573 # qhasm: r10 ^= r
574 # asm 1: vpxor <r=reg256#8,<r10=reg256#6,<r10=reg256#6
575 # asm 2: vpxor <r=%ymm7,<r10=%ymm5,<r10=%ymm5
576 vpxor %ymm7,%ymm5,%ymm5
577
578 # qhasm: r9 = b9 & a0
579 # asm 1: vpand <b9=reg256#14,<a0=reg256#13,>r9=reg256#8
580 # asm 2: vpand <b9=%ymm13,<a0=%ymm12,>r9=%ymm7
581 vpand %ymm13,%ymm12,%ymm7
582
583 # qhasm: b8 = mem128[ input_2 + 0 ] x2
584 # asm 1: vbroadcasti128 0(<input_2=int64#3), >b8=reg256#14
585 # asm 2: vbroadcasti128 0(<input_2=%rdx), >b8=%ymm13
586 vbroadcasti128 0(%rdx), %ymm13
587
588 # qhasm: input_2 -= input_3
589 # asm 1: sub <input_3=int64#4,<input_2=int64#3
590 # asm 2: sub <input_3=%rcx,<input_2=%rdx
591 sub %rcx,%rdx
592
593 # qhasm: r = b8 & a6
594 # asm 1: vpand <b8=reg256#14,<a6=reg256#2,>r=reg256#15
595 # asm 2: vpand <b8=%ymm13,<a6=%ymm1,>r=%ymm14
596 vpand %ymm13,%ymm1,%ymm14
597
598 # qhasm: r14 ^= r
599 # asm 1: vpxor <r=reg256#15,<r14=reg256#10,<r14=reg256#10
600 # asm 2: vpxor <r=%ymm14,<r14=%ymm9,<r14=%ymm9
601 vpxor %ymm14,%ymm9,%ymm9
602
603 # qhasm: mem256[ ptr + 448 ] = r14
604 # asm 1: vmovupd <r14=reg256#10,448(<ptr=int64#5)
605 # asm 2: vmovupd <r14=%ymm9,448(<ptr=%r8)
606 vmovupd %ymm9,448(%r8)
607
608 # qhasm: r = b8 & a5
609 # asm 1: vpand <b8=reg256#14,<a5=reg256#3,>r=reg256#10
610 # asm 2: vpand <b8=%ymm13,<a5=%ymm2,>r=%ymm9
611 vpand %ymm13,%ymm2,%ymm9
612
613 # qhasm: r13 ^= r
614 # asm 1: vpxor <r=reg256#10,<r13=reg256#12,<r13=reg256#12
615 # asm 2: vpxor <r=%ymm9,<r13=%ymm11,<r13=%ymm11
616 vpxor %ymm9,%ymm11,%ymm11
617
618 # qhasm: r = b8 & a4
619 # asm 1: vpand <b8=reg256#14,<a4=reg256#5,>r=reg256#10
620 # asm 2: vpand <b8=%ymm13,<a4=%ymm4,>r=%ymm9
621 vpand %ymm13,%ymm4,%ymm9
622
623 # qhasm: r12 ^= r
624 # asm 1: vpxor <r=reg256#10,<r12=reg256#1,<r12=reg256#1
625 # asm 2: vpxor <r=%ymm9,<r12=%ymm0,<r12=%ymm0
626 vpxor %ymm9,%ymm0,%ymm0
627
628 # qhasm: r = b8 & a3
629 # asm 1: vpand <b8=reg256#14,<a3=reg256#7,>r=reg256#10
630 # asm 2: vpand <b8=%ymm13,<a3=%ymm6,>r=%ymm9
631 vpand %ymm13,%ymm6,%ymm9
632
633 # qhasm: r11 ^= r
634 # asm 1: vpxor <r=reg256#10,<r11=reg256#4,<r11=reg256#4
635 # asm 2: vpxor <r=%ymm9,<r11=%ymm3,<r11=%ymm3
636 vpxor %ymm9,%ymm3,%ymm3
637
638 # qhasm: r = b8 & a2
639 # asm 1: vpand <b8=reg256#14,<a2=reg256#9,>r=reg256#10
640 # asm 2: vpand <b8=%ymm13,<a2=%ymm8,>r=%ymm9
641 vpand %ymm13,%ymm8,%ymm9
642
643 # qhasm: r10 ^= r
644 # asm 1: vpxor <r=reg256#10,<r10=reg256#6,<r10=reg256#6
645 # asm 2: vpxor <r=%ymm9,<r10=%ymm5,<r10=%ymm5
646 vpxor %ymm9,%ymm5,%ymm5
647
648 # qhasm: r = b8 & a1
649 # asm 1: vpand <b8=reg256#14,<a1=reg256#11,>r=reg256#10
650 # asm 2: vpand <b8=%ymm13,<a1=%ymm10,>r=%ymm9
651 vpand %ymm13,%ymm10,%ymm9
652
653 # qhasm: r9 ^= r
654 # asm 1: vpxor <r=reg256#10,<r9=reg256#8,<r9=reg256#8
655 # asm 2: vpxor <r=%ymm9,<r9=%ymm7,<r9=%ymm7
656 vpxor %ymm9,%ymm7,%ymm7
657
658 # qhasm: r8 = b8 & a0
659 # asm 1: vpand <b8=reg256#14,<a0=reg256#13,>r8=reg256#10
660 # asm 2: vpand <b8=%ymm13,<a0=%ymm12,>r8=%ymm9
661 vpand %ymm13,%ymm12,%ymm9
662
663 # qhasm: b7 = mem128[ input_2 + 0 ] x2
664 # asm 1: vbroadcasti128 0(<input_2=int64#3), >b7=reg256#14
665 # asm 2: vbroadcasti128 0(<input_2=%rdx), >b7=%ymm13
666 vbroadcasti128 0(%rdx), %ymm13
667
668 # qhasm: input_2 -= input_3
669 # asm 1: sub <input_3=int64#4,<input_2=int64#3
670 # asm 2: sub <input_3=%rcx,<input_2=%rdx
671 sub %rcx,%rdx
672
673 # qhasm: r = b7 & a6
674 # asm 1: vpand <b7=reg256#14,<a6=reg256#2,>r=reg256#15
675 # asm 2: vpand <b7=%ymm13,<a6=%ymm1,>r=%ymm14
676 vpand %ymm13,%ymm1,%ymm14
677
678 # qhasm: r13 ^= r
679 # asm 1: vpxor <r=reg256#15,<r13=reg256#12,<r13=reg256#12
680 # asm 2: vpxor <r=%ymm14,<r13=%ymm11,<r13=%ymm11
681 vpxor %ymm14,%ymm11,%ymm11
682
683 # qhasm: mem256[ ptr + 416 ] = r13
684 # asm 1: vmovupd <r13=reg256#12,416(<ptr=int64#5)
685 # asm 2: vmovupd <r13=%ymm11,416(<ptr=%r8)
686 vmovupd %ymm11,416(%r8)
687
688 # qhasm: r = b7 & a5
689 # asm 1: vpand <b7=reg256#14,<a5=reg256#3,>r=reg256#12
690 # asm 2: vpand <b7=%ymm13,<a5=%ymm2,>r=%ymm11
691 vpand %ymm13,%ymm2,%ymm11
692
693 # qhasm: r12 ^= r
694 # asm 1: vpxor <r=reg256#12,<r12=reg256#1,<r12=reg256#1
695 # asm 2: vpxor <r=%ymm11,<r12=%ymm0,<r12=%ymm0
696 vpxor %ymm11,%ymm0,%ymm0
697
698 # qhasm: r = b7 & a4
699 # asm 1: vpand <b7=reg256#14,<a4=reg256#5,>r=reg256#12
700 # asm 2: vpand <b7=%ymm13,<a4=%ymm4,>r=%ymm11
701 vpand %ymm13,%ymm4,%ymm11
702
703 # qhasm: r11 ^= r
704 # asm 1: vpxor <r=reg256#12,<r11=reg256#4,<r11=reg256#4
705 # asm 2: vpxor <r=%ymm11,<r11=%ymm3,<r11=%ymm3
706 vpxor %ymm11,%ymm3,%ymm3
707
708 # qhasm: r = b7 & a3
709 # asm 1: vpand <b7=reg256#14,<a3=reg256#7,>r=reg256#12
710 # asm 2: vpand <b7=%ymm13,<a3=%ymm6,>r=%ymm11
711 vpand %ymm13,%ymm6,%ymm11
712
713 # qhasm: r10 ^= r
714 # asm 1: vpxor <r=reg256#12,<r10=reg256#6,<r10=reg256#6
715 # asm 2: vpxor <r=%ymm11,<r10=%ymm5,<r10=%ymm5
716 vpxor %ymm11,%ymm5,%ymm5
717
718 # qhasm: r = b7 & a2
719 # asm 1: vpand <b7=reg256#14,<a2=reg256#9,>r=reg256#12
720 # asm 2: vpand <b7=%ymm13,<a2=%ymm8,>r=%ymm11
721 vpand %ymm13,%ymm8,%ymm11
722
723 # qhasm: r9 ^= r
724 # asm 1: vpxor <r=reg256#12,<r9=reg256#8,<r9=reg256#8
725 # asm 2: vpxor <r=%ymm11,<r9=%ymm7,<r9=%ymm7
726 vpxor %ymm11,%ymm7,%ymm7
727
728 # qhasm: r = b7 & a1
729 # asm 1: vpand <b7=reg256#14,<a1=reg256#11,>r=reg256#12
730 # asm 2: vpand <b7=%ymm13,<a1=%ymm10,>r=%ymm11
731 vpand %ymm13,%ymm10,%ymm11
732
733 # qhasm: r8 ^= r
734 # asm 1: vpxor <r=reg256#12,<r8=reg256#10,<r8=reg256#10
735 # asm 2: vpxor <r=%ymm11,<r8=%ymm9,<r8=%ymm9
736 vpxor %ymm11,%ymm9,%ymm9
737
738 # qhasm: r7 = b7 & a0
739 # asm 1: vpand <b7=reg256#14,<a0=reg256#13,>r7=reg256#12
740 # asm 2: vpand <b7=%ymm13,<a0=%ymm12,>r7=%ymm11
741 vpand %ymm13,%ymm12,%ymm11
742
743 # qhasm: b6 = mem128[ input_2 + 0 ] x2
744 # asm 1: vbroadcasti128 0(<input_2=int64#3), >b6=reg256#14
745 # asm 2: vbroadcasti128 0(<input_2=%rdx), >b6=%ymm13
746 vbroadcasti128 0(%rdx), %ymm13
747
748 # qhasm: input_2 -= input_3
749 # asm 1: sub <input_3=int64#4,<input_2=int64#3
750 # asm 2: sub <input_3=%rcx,<input_2=%rdx
751 sub %rcx,%rdx
752
753 # qhasm: r = b6 & a6
754 # asm 1: vpand <b6=reg256#14,<a6=reg256#2,>r=reg256#15
755 # asm 2: vpand <b6=%ymm13,<a6=%ymm1,>r=%ymm14
756 vpand %ymm13,%ymm1,%ymm14
757
758 # qhasm: r12 ^= r
759 # asm 1: vpxor <r=reg256#15,<r12=reg256#1,<r12=reg256#1
760 # asm 2: vpxor <r=%ymm14,<r12=%ymm0,<r12=%ymm0
761 vpxor %ymm14,%ymm0,%ymm0
762
763 # qhasm: mem256[ ptr + 384 ] = r12
764 # asm 1: vmovupd <r12=reg256#1,384(<ptr=int64#5)
765 # asm 2: vmovupd <r12=%ymm0,384(<ptr=%r8)
766 vmovupd %ymm0,384(%r8)
767
768 # qhasm: r = b6 & a5
769 # asm 1: vpand <b6=reg256#14,<a5=reg256#3,>r=reg256#1
770 # asm 2: vpand <b6=%ymm13,<a5=%ymm2,>r=%ymm0
771 vpand %ymm13,%ymm2,%ymm0
772
773 # qhasm: r11 ^= r
774 # asm 1: vpxor <r=reg256#1,<r11=reg256#4,<r11=reg256#4
775 # asm 2: vpxor <r=%ymm0,<r11=%ymm3,<r11=%ymm3
776 vpxor %ymm0,%ymm3,%ymm3
777
778 # qhasm: r = b6 & a4
779 # asm 1: vpand <b6=reg256#14,<a4=reg256#5,>r=reg256#1
780 # asm 2: vpand <b6=%ymm13,<a4=%ymm4,>r=%ymm0
781 vpand %ymm13,%ymm4,%ymm0
782
783 # qhasm: r10 ^= r
784 # asm 1: vpxor <r=reg256#1,<r10=reg256#6,<r10=reg256#6
785 # asm 2: vpxor <r=%ymm0,<r10=%ymm5,<r10=%ymm5
786 vpxor %ymm0,%ymm5,%ymm5
787
788 # qhasm: r = b6 & a3
789 # asm 1: vpand <b6=reg256#14,<a3=reg256#7,>r=reg256#1
790 # asm 2: vpand <b6=%ymm13,<a3=%ymm6,>r=%ymm0
791 vpand %ymm13,%ymm6,%ymm0
792
793 # qhasm: r9 ^= r
794 # asm 1: vpxor <r=reg256#1,<r9=reg256#8,<r9=reg256#8
795 # asm 2: vpxor <r=%ymm0,<r9=%ymm7,<r9=%ymm7
796 vpxor %ymm0,%ymm7,%ymm7
797
798 # qhasm: r = b6 & a2
799 # asm 1: vpand <b6=reg256#14,<a2=reg256#9,>r=reg256#1
800 # asm 2: vpand <b6=%ymm13,<a2=%ymm8,>r=%ymm0
801 vpand %ymm13,%ymm8,%ymm0
802
803 # qhasm: r8 ^= r
804 # asm 1: vpxor <r=reg256#1,<r8=reg256#10,<r8=reg256#10
805 # asm 2: vpxor <r=%ymm0,<r8=%ymm9,<r8=%ymm9
806 vpxor %ymm0,%ymm9,%ymm9
807
808 # qhasm: r = b6 & a1
809 # asm 1: vpand <b6=reg256#14,<a1=reg256#11,>r=reg256#1
810 # asm 2: vpand <b6=%ymm13,<a1=%ymm10,>r=%ymm0
811 vpand %ymm13,%ymm10,%ymm0
812
813 # qhasm: r7 ^= r
814 # asm 1: vpxor <r=reg256#1,<r7=reg256#12,<r7=reg256#12
815 # asm 2: vpxor <r=%ymm0,<r7=%ymm11,<r7=%ymm11
816 vpxor %ymm0,%ymm11,%ymm11
817
818 # qhasm: r6 = b6 & a0
819 # asm 1: vpand <b6=reg256#14,<a0=reg256#13,>r6=reg256#1
820 # asm 2: vpand <b6=%ymm13,<a0=%ymm12,>r6=%ymm0
821 vpand %ymm13,%ymm12,%ymm0
822
823 # qhasm: b5 = mem128[ input_2 + 0 ] x2
824 # asm 1: vbroadcasti128 0(<input_2=int64#3), >b5=reg256#14
825 # asm 2: vbroadcasti128 0(<input_2=%rdx), >b5=%ymm13
826 vbroadcasti128 0(%rdx), %ymm13
827
828 # qhasm: input_2 -= input_3
829 # asm 1: sub <input_3=int64#4,<input_2=int64#3
830 # asm 2: sub <input_3=%rcx,<input_2=%rdx
831 sub %rcx,%rdx
832
833 # qhasm: r = b5 & a6
834 # asm 1: vpand <b5=reg256#14,<a6=reg256#2,>r=reg256#15
835 # asm 2: vpand <b5=%ymm13,<a6=%ymm1,>r=%ymm14
836 vpand %ymm13,%ymm1,%ymm14
837
838 # qhasm: r11 ^= r
839 # asm 1: vpxor <r=reg256#15,<r11=reg256#4,<r11=reg256#4
840 # asm 2: vpxor <r=%ymm14,<r11=%ymm3,<r11=%ymm3
841 vpxor %ymm14,%ymm3,%ymm3
842
843 # qhasm: mem256[ ptr + 352 ] = r11
844 # asm 1: vmovupd <r11=reg256#4,352(<ptr=int64#5)
845 # asm 2: vmovupd <r11=%ymm3,352(<ptr=%r8)
846 vmovupd %ymm3,352(%r8)
847
848 # qhasm: r = b5 & a5
849 # asm 1: vpand <b5=reg256#14,<a5=reg256#3,>r=reg256#4
850 # asm 2: vpand <b5=%ymm13,<a5=%ymm2,>r=%ymm3
851 vpand %ymm13,%ymm2,%ymm3
852
853 # qhasm: r10 ^= r
854 # asm 1: vpxor <r=reg256#4,<r10=reg256#6,<r10=reg256#6
855 # asm 2: vpxor <r=%ymm3,<r10=%ymm5,<r10=%ymm5
856 vpxor %ymm3,%ymm5,%ymm5
857
858 # qhasm: r = b5 & a4
859 # asm 1: vpand <b5=reg256#14,<a4=reg256#5,>r=reg256#4
860 # asm 2: vpand <b5=%ymm13,<a4=%ymm4,>r=%ymm3
861 vpand %ymm13,%ymm4,%ymm3
862
863 # qhasm: r9 ^= r
864 # asm 1: vpxor <r=reg256#4,<r9=reg256#8,<r9=reg256#8
865 # asm 2: vpxor <r=%ymm3,<r9=%ymm7,<r9=%ymm7
866 vpxor %ymm3,%ymm7,%ymm7
867
868 # qhasm: r = b5 & a3
869 # asm 1: vpand <b5=reg256#14,<a3=reg256#7,>r=reg256#4
870 # asm 2: vpand <b5=%ymm13,<a3=%ymm6,>r=%ymm3
871 vpand %ymm13,%ymm6,%ymm3
872
873 # qhasm: r8 ^= r
874 # asm 1: vpxor <r=reg256#4,<r8=reg256#10,<r8=reg256#10
875 # asm 2: vpxor <r=%ymm3,<r8=%ymm9,<r8=%ymm9
876 vpxor %ymm3,%ymm9,%ymm9
877
878 # qhasm: r = b5 & a2
879 # asm 1: vpand <b5=reg256#14,<a2=reg256#9,>r=reg256#4
880 # asm 2: vpand <b5=%ymm13,<a2=%ymm8,>r=%ymm3
881 vpand %ymm13,%ymm8,%ymm3
882
883 # qhasm: r7 ^= r
884 # asm 1: vpxor <r=reg256#4,<r7=reg256#12,<r7=reg256#12
885 # asm 2: vpxor <r=%ymm3,<r7=%ymm11,<r7=%ymm11
886 vpxor %ymm3,%ymm11,%ymm11
887
888 # qhasm: r = b5 & a1
889 # asm 1: vpand <b5=reg256#14,<a1=reg256#11,>r=reg256#4
890 # asm 2: vpand <b5=%ymm13,<a1=%ymm10,>r=%ymm3
891 vpand %ymm13,%ymm10,%ymm3
892
893 # qhasm: r6 ^= r
894 # asm 1: vpxor <r=reg256#4,<r6=reg256#1,<r6=reg256#1
895 # asm 2: vpxor <r=%ymm3,<r6=%ymm0,<r6=%ymm0
896 vpxor %ymm3,%ymm0,%ymm0
897
898 # qhasm: r5 = b5 & a0
899 # asm 1: vpand <b5=reg256#14,<a0=reg256#13,>r5=reg256#4
900 # asm 2: vpand <b5=%ymm13,<a0=%ymm12,>r5=%ymm3
901 vpand %ymm13,%ymm12,%ymm3
902
903 # qhasm: b4 = mem128[ input_2 + 0 ] x2
904 # asm 1: vbroadcasti128 0(<input_2=int64#3), >b4=reg256#14
905 # asm 2: vbroadcasti128 0(<input_2=%rdx), >b4=%ymm13
906 vbroadcasti128 0(%rdx), %ymm13
907
908 # qhasm: input_2 -= input_3
909 # asm 1: sub <input_3=int64#4,<input_2=int64#3
910 # asm 2: sub <input_3=%rcx,<input_2=%rdx
911 sub %rcx,%rdx
912
913 # qhasm: r = b4 & a6
914 # asm 1: vpand <b4=reg256#14,<a6=reg256#2,>r=reg256#15
915 # asm 2: vpand <b4=%ymm13,<a6=%ymm1,>r=%ymm14
916 vpand %ymm13,%ymm1,%ymm14
917
918 # qhasm: r10 ^= r
919 # asm 1: vpxor <r=reg256#15,<r10=reg256#6,<r10=reg256#6
920 # asm 2: vpxor <r=%ymm14,<r10=%ymm5,<r10=%ymm5
921 vpxor %ymm14,%ymm5,%ymm5
922
923 # qhasm: mem256[ ptr + 320 ] = r10
924 # asm 1: vmovupd <r10=reg256#6,320(<ptr=int64#5)
925 # asm 2: vmovupd <r10=%ymm5,320(<ptr=%r8)
926 vmovupd %ymm5,320(%r8)
927
928 # qhasm: r = b4 & a5
929 # asm 1: vpand <b4=reg256#14,<a5=reg256#3,>r=reg256#6
930 # asm 2: vpand <b4=%ymm13,<a5=%ymm2,>r=%ymm5
931 vpand %ymm13,%ymm2,%ymm5
932
933 # qhasm: r9 ^= r
934 # asm 1: vpxor <r=reg256#6,<r9=reg256#8,<r9=reg256#8
935 # asm 2: vpxor <r=%ymm5,<r9=%ymm7,<r9=%ymm7
936 vpxor %ymm5,%ymm7,%ymm7
937
938 # qhasm: r = b4 & a4
939 # asm 1: vpand <b4=reg256#14,<a4=reg256#5,>r=reg256#6
940 # asm 2: vpand <b4=%ymm13,<a4=%ymm4,>r=%ymm5
941 vpand %ymm13,%ymm4,%ymm5
942
943 # qhasm: r8 ^= r
944 # asm 1: vpxor <r=reg256#6,<r8=reg256#10,<r8=reg256#10
945 # asm 2: vpxor <r=%ymm5,<r8=%ymm9,<r8=%ymm9
946 vpxor %ymm5,%ymm9,%ymm9
947
948 # qhasm: r = b4 & a3
949 # asm 1: vpand <b4=reg256#14,<a3=reg256#7,>r=reg256#6
950 # asm 2: vpand <b4=%ymm13,<a3=%ymm6,>r=%ymm5
951 vpand %ymm13,%ymm6,%ymm5
952
953 # qhasm: r7 ^= r
954 # asm 1: vpxor <r=reg256#6,<r7=reg256#12,<r7=reg256#12
955 # asm 2: vpxor <r=%ymm5,<r7=%ymm11,<r7=%ymm11
956 vpxor %ymm5,%ymm11,%ymm11
957
958 # qhasm: r = b4 & a2
959 # asm 1: vpand <b4=reg256#14,<a2=reg256#9,>r=reg256#6
960 # asm 2: vpand <b4=%ymm13,<a2=%ymm8,>r=%ymm5
961 vpand %ymm13,%ymm8,%ymm5
962
963 # qhasm: r6 ^= r
964 # asm 1: vpxor <r=reg256#6,<r6=reg256#1,<r6=reg256#1
965 # asm 2: vpxor <r=%ymm5,<r6=%ymm0,<r6=%ymm0
966 vpxor %ymm5,%ymm0,%ymm0
967
968 # qhasm: r = b4 & a1
969 # asm 1: vpand <b4=reg256#14,<a1=reg256#11,>r=reg256#6
970 # asm 2: vpand <b4=%ymm13,<a1=%ymm10,>r=%ymm5
971 vpand %ymm13,%ymm10,%ymm5
972
973 # qhasm: r5 ^= r
974 # asm 1: vpxor <r=reg256#6,<r5=reg256#4,<r5=reg256#4
975 # asm 2: vpxor <r=%ymm5,<r5=%ymm3,<r5=%ymm3
976 vpxor %ymm5,%ymm3,%ymm3
977
978 # qhasm: r4 = b4 & a0
979 # asm 1: vpand <b4=reg256#14,<a0=reg256#13,>r4=reg256#6
980 # asm 2: vpand <b4=%ymm13,<a0=%ymm12,>r4=%ymm5
981 vpand %ymm13,%ymm12,%ymm5
982
983 # qhasm: b3 = mem128[ input_2 + 0 ] x2
984 # asm 1: vbroadcasti128 0(<input_2=int64#3), >b3=reg256#14
985 # asm 2: vbroadcasti128 0(<input_2=%rdx), >b3=%ymm13
986 vbroadcasti128 0(%rdx), %ymm13
987
988 # qhasm: input_2 -= input_3
989 # asm 1: sub <input_3=int64#4,<input_2=int64#3
990 # asm 2: sub <input_3=%rcx,<input_2=%rdx
991 sub %rcx,%rdx
992
993 # qhasm: r = b3 & a6
994 # asm 1: vpand <b3=reg256#14,<a6=reg256#2,>r=reg256#15
995 # asm 2: vpand <b3=%ymm13,<a6=%ymm1,>r=%ymm14
996 vpand %ymm13,%ymm1,%ymm14
997
998 # qhasm: r9 ^= r
999 # asm 1: vpxor <r=reg256#15,<r9=reg256#8,<r9=reg256#8
1000 # asm 2: vpxor <r=%ymm14,<r9=%ymm7,<r9=%ymm7
1001 vpxor %ymm14,%ymm7,%ymm7
1002
1003 # qhasm: mem256[ ptr + 288 ] = r9
1004 # asm 1: vmovupd <r9=reg256#8,288(<ptr=int64#5)
1005 # asm 2: vmovupd <r9=%ymm7,288(<ptr=%r8)
1006 vmovupd %ymm7,288(%r8)
1007
1008 # qhasm: r = b3 & a5
1009 # asm 1: vpand <b3=reg256#14,<a5=reg256#3,>r=reg256#8
1010 # asm 2: vpand <b3=%ymm13,<a5=%ymm2,>r=%ymm7
1011 vpand %ymm13,%ymm2,%ymm7
1012
1013 # qhasm: r8 ^= r
1014 # asm 1: vpxor <r=reg256#8,<r8=reg256#10,<r8=reg256#10
1015 # asm 2: vpxor <r=%ymm7,<r8=%ymm9,<r8=%ymm9
1016 vpxor %ymm7,%ymm9,%ymm9
1017
1018 # qhasm: r = b3 & a4
1019 # asm 1: vpand <b3=reg256#14,<a4=reg256#5,>r=reg256#8
1020 # asm 2: vpand <b3=%ymm13,<a4=%ymm4,>r=%ymm7
1021 vpand %ymm13,%ymm4,%ymm7
1022
1023 # qhasm: r7 ^= r
1024 # asm 1: vpxor <r=reg256#8,<r7=reg256#12,<r7=reg256#12
1025 # asm 2: vpxor <r=%ymm7,<r7=%ymm11,<r7=%ymm11
1026 vpxor %ymm7,%ymm11,%ymm11
1027
1028 # qhasm: r = b3 & a3
1029 # asm 1: vpand <b3=reg256#14,<a3=reg256#7,>r=reg256#8
1030 # asm 2: vpand <b3=%ymm13,<a3=%ymm6,>r=%ymm7
1031 vpand %ymm13,%ymm6,%ymm7
1032
1033 # qhasm: r6 ^= r
1034 # asm 1: vpxor <r=reg256#8,<r6=reg256#1,<r6=reg256#1
1035 # asm 2: vpxor <r=%ymm7,<r6=%ymm0,<r6=%ymm0
1036 vpxor %ymm7,%ymm0,%ymm0
1037
1038 # qhasm: r = b3 & a2
1039 # asm 1: vpand <b3=reg256#14,<a2=reg256#9,>r=reg256#8
1040 # asm 2: vpand <b3=%ymm13,<a2=%ymm8,>r=%ymm7
1041 vpand %ymm13,%ymm8,%ymm7
1042
1043 # qhasm: r5 ^= r
1044 # asm 1: vpxor <r=reg256#8,<r5=reg256#4,<r5=reg256#4
1045 # asm 2: vpxor <r=%ymm7,<r5=%ymm3,<r5=%ymm3
1046 vpxor %ymm7,%ymm3,%ymm3
1047
1048 # qhasm: r = b3 & a1
1049 # asm 1: vpand <b3=reg256#14,<a1=reg256#11,>r=reg256#8
1050 # asm 2: vpand <b3=%ymm13,<a1=%ymm10,>r=%ymm7
1051 vpand %ymm13,%ymm10,%ymm7
1052
1053 # qhasm: r4 ^= r
1054 # asm 1: vpxor <r=reg256#8,<r4=reg256#6,<r4=reg256#6
1055 # asm 2: vpxor <r=%ymm7,<r4=%ymm5,<r4=%ymm5
1056 vpxor %ymm7,%ymm5,%ymm5
1057
1058 # qhasm: r3 = b3 & a0
1059 # asm 1: vpand <b3=reg256#14,<a0=reg256#13,>r3=reg256#8
1060 # asm 2: vpand <b3=%ymm13,<a0=%ymm12,>r3=%ymm7
1061 vpand %ymm13,%ymm12,%ymm7
1062
1063 # qhasm: b2 = mem128[ input_2 + 0 ] x2
1064 # asm 1: vbroadcasti128 0(<input_2=int64#3), >b2=reg256#14
1065 # asm 2: vbroadcasti128 0(<input_2=%rdx), >b2=%ymm13
1066 vbroadcasti128 0(%rdx), %ymm13
1067
1068 # qhasm: input_2 -= input_3
1069 # asm 1: sub <input_3=int64#4,<input_2=int64#3
1070 # asm 2: sub <input_3=%rcx,<input_2=%rdx
1071 sub %rcx,%rdx
1072
1073 # qhasm: r = b2 & a6
1074 # asm 1: vpand <b2=reg256#14,<a6=reg256#2,>r=reg256#15
1075 # asm 2: vpand <b2=%ymm13,<a6=%ymm1,>r=%ymm14
1076 vpand %ymm13,%ymm1,%ymm14
1077
1078 # qhasm: r8 ^= r
1079 # asm 1: vpxor <r=reg256#15,<r8=reg256#10,<r8=reg256#10
1080 # asm 2: vpxor <r=%ymm14,<r8=%ymm9,<r8=%ymm9
1081 vpxor %ymm14,%ymm9,%ymm9
1082
1083 # qhasm: mem256[ ptr + 256 ] = r8
1084 # asm 1: vmovupd <r8=reg256#10,256(<ptr=int64#5)
1085 # asm 2: vmovupd <r8=%ymm9,256(<ptr=%r8)
1086 vmovupd %ymm9,256(%r8)
1087
1088 # qhasm: r = b2 & a5
1089 # asm 1: vpand <b2=reg256#14,<a5=reg256#3,>r=reg256#10
1090 # asm 2: vpand <b2=%ymm13,<a5=%ymm2,>r=%ymm9
1091 vpand %ymm13,%ymm2,%ymm9
1092
1093 # qhasm: r7 ^= r
1094 # asm 1: vpxor <r=reg256#10,<r7=reg256#12,<r7=reg256#12
1095 # asm 2: vpxor <r=%ymm9,<r7=%ymm11,<r7=%ymm11
1096 vpxor %ymm9,%ymm11,%ymm11
1097
1098 # qhasm: r = b2 & a4
1099 # asm 1: vpand <b2=reg256#14,<a4=reg256#5,>r=reg256#10
1100 # asm 2: vpand <b2=%ymm13,<a4=%ymm4,>r=%ymm9
1101 vpand %ymm13,%ymm4,%ymm9
1102
1103 # qhasm: r6 ^= r
1104 # asm 1: vpxor <r=reg256#10,<r6=reg256#1,<r6=reg256#1
1105 # asm 2: vpxor <r=%ymm9,<r6=%ymm0,<r6=%ymm0
1106 vpxor %ymm9,%ymm0,%ymm0
1107
1108 # qhasm: r = b2 & a3
1109 # asm 1: vpand <b2=reg256#14,<a3=reg256#7,>r=reg256#10
1110 # asm 2: vpand <b2=%ymm13,<a3=%ymm6,>r=%ymm9
1111 vpand %ymm13,%ymm6,%ymm9
1112
1113 # qhasm: r5 ^= r
1114 # asm 1: vpxor <r=reg256#10,<r5=reg256#4,<r5=reg256#4
1115 # asm 2: vpxor <r=%ymm9,<r5=%ymm3,<r5=%ymm3
1116 vpxor %ymm9,%ymm3,%ymm3
1117
1118 # qhasm: r = b2 & a2
1119 # asm 1: vpand <b2=reg256#14,<a2=reg256#9,>r=reg256#10
1120 # asm 2: vpand <b2=%ymm13,<a2=%ymm8,>r=%ymm9
1121 vpand %ymm13,%ymm8,%ymm9
1122
1123 # qhasm: r4 ^= r
1124 # asm 1: vpxor <r=reg256#10,<r4=reg256#6,<r4=reg256#6
1125 # asm 2: vpxor <r=%ymm9,<r4=%ymm5,<r4=%ymm5
1126 vpxor %ymm9,%ymm5,%ymm5
1127
1128 # qhasm: r = b2 & a1
1129 # asm 1: vpand <b2=reg256#14,<a1=reg256#11,>r=reg256#10
1130 # asm 2: vpand <b2=%ymm13,<a1=%ymm10,>r=%ymm9
1131 vpand %ymm13,%ymm10,%ymm9
1132
1133 # qhasm: r3 ^= r
1134 # asm 1: vpxor <r=reg256#10,<r3=reg256#8,<r3=reg256#8
1135 # asm 2: vpxor <r=%ymm9,<r3=%ymm7,<r3=%ymm7
1136 vpxor %ymm9,%ymm7,%ymm7
1137
1138 # qhasm: r2 = b2 & a0
1139 # asm 1: vpand <b2=reg256#14,<a0=reg256#13,>r2=reg256#10
1140 # asm 2: vpand <b2=%ymm13,<a0=%ymm12,>r2=%ymm9
1141 vpand %ymm13,%ymm12,%ymm9
1142
1143 # qhasm: b1 = mem128[ input_2 + 0 ] x2
1144 # asm 1: vbroadcasti128 0(<input_2=int64#3), >b1=reg256#14
1145 # asm 2: vbroadcasti128 0(<input_2=%rdx), >b1=%ymm13
1146 vbroadcasti128 0(%rdx), %ymm13
1147
1148 # qhasm: input_2 -= input_3
1149 # asm 1: sub <input_3=int64#4,<input_2=int64#3
1150 # asm 2: sub <input_3=%rcx,<input_2=%rdx
1151 sub %rcx,%rdx
1152
1153 # qhasm: r = b1 & a6
1154 # asm 1: vpand <b1=reg256#14,<a6=reg256#2,>r=reg256#15
1155 # asm 2: vpand <b1=%ymm13,<a6=%ymm1,>r=%ymm14
1156 vpand %ymm13,%ymm1,%ymm14
1157
1158 # qhasm: r7 ^= r
1159 # asm 1: vpxor <r=reg256#15,<r7=reg256#12,<r7=reg256#12
1160 # asm 2: vpxor <r=%ymm14,<r7=%ymm11,<r7=%ymm11
1161 vpxor %ymm14,%ymm11,%ymm11
1162
1163 # qhasm: mem256[ ptr + 224 ] = r7
1164 # asm 1: vmovupd <r7=reg256#12,224(<ptr=int64#5)
1165 # asm 2: vmovupd <r7=%ymm11,224(<ptr=%r8)
1166 vmovupd %ymm11,224(%r8)
1167
1168 # qhasm: r = b1 & a5
1169 # asm 1: vpand <b1=reg256#14,<a5=reg256#3,>r=reg256#12
1170 # asm 2: vpand <b1=%ymm13,<a5=%ymm2,>r=%ymm11
1171 vpand %ymm13,%ymm2,%ymm11
1172
1173 # qhasm: r6 ^= r
1174 # asm 1: vpxor <r=reg256#12,<r6=reg256#1,<r6=reg256#1
1175 # asm 2: vpxor <r=%ymm11,<r6=%ymm0,<r6=%ymm0
1176 vpxor %ymm11,%ymm0,%ymm0
1177
1178 # qhasm: r = b1 & a4
1179 # asm 1: vpand <b1=reg256#14,<a4=reg256#5,>r=reg256#12
1180 # asm 2: vpand <b1=%ymm13,<a4=%ymm4,>r=%ymm11
1181 vpand %ymm13,%ymm4,%ymm11
1182
1183 # qhasm: r5 ^= r
1184 # asm 1: vpxor <r=reg256#12,<r5=reg256#4,<r5=reg256#4
1185 # asm 2: vpxor <r=%ymm11,<r5=%ymm3,<r5=%ymm3
1186 vpxor %ymm11,%ymm3,%ymm3
1187
1188 # qhasm: r = b1 & a3
1189 # asm 1: vpand <b1=reg256#14,<a3=reg256#7,>r=reg256#12
1190 # asm 2: vpand <b1=%ymm13,<a3=%ymm6,>r=%ymm11
1191 vpand %ymm13,%ymm6,%ymm11
1192
1193 # qhasm: r4 ^= r
1194 # asm 1: vpxor <r=reg256#12,<r4=reg256#6,<r4=reg256#6
1195 # asm 2: vpxor <r=%ymm11,<r4=%ymm5,<r4=%ymm5
1196 vpxor %ymm11,%ymm5,%ymm5
1197
1198 # qhasm: r = b1 & a2
1199 # asm 1: vpand <b1=reg256#14,<a2=reg256#9,>r=reg256#12
1200 # asm 2: vpand <b1=%ymm13,<a2=%ymm8,>r=%ymm11
1201 vpand %ymm13,%ymm8,%ymm11
1202
1203 # qhasm: r3 ^= r
1204 # asm 1: vpxor <r=reg256#12,<r3=reg256#8,<r3=reg256#8
1205 # asm 2: vpxor <r=%ymm11,<r3=%ymm7,<r3=%ymm7
1206 vpxor %ymm11,%ymm7,%ymm7
1207
1208 # qhasm: r = b1 & a1
1209 # asm 1: vpand <b1=reg256#14,<a1=reg256#11,>r=reg256#12
1210 # asm 2: vpand <b1=%ymm13,<a1=%ymm10,>r=%ymm11
1211 vpand %ymm13,%ymm10,%ymm11
1212
1213 # qhasm: r2 ^= r
1214 # asm 1: vpxor <r=reg256#12,<r2=reg256#10,<r2=reg256#10
1215 # asm 2: vpxor <r=%ymm11,<r2=%ymm9,<r2=%ymm9
1216 vpxor %ymm11,%ymm9,%ymm9
1217
1218 # qhasm: r1 = b1 & a0
1219 # asm 1: vpand <b1=reg256#14,<a0=reg256#13,>r1=reg256#12
1220 # asm 2: vpand <b1=%ymm13,<a0=%ymm12,>r1=%ymm11
1221 vpand %ymm13,%ymm12,%ymm11
1222
1223 # qhasm: b0 = mem128[ input_2 + 0 ] x2
1224 # asm 1: vbroadcasti128 0(<input_2=int64#3), >b0=reg256#14
1225 # asm 2: vbroadcasti128 0(<input_2=%rdx), >b0=%ymm13
1226 vbroadcasti128 0(%rdx), %ymm13
1227
1228 # qhasm: input_2 -= input_3
1229 # asm 1: sub <input_3=int64#4,<input_2=int64#3
1230 # asm 2: sub <input_3=%rcx,<input_2=%rdx
1231 sub %rcx,%rdx
1232
1233 # qhasm: r = b0 & a6
1234 # asm 1: vpand <b0=reg256#14,<a6=reg256#2,>r=reg256#2
1235 # asm 2: vpand <b0=%ymm13,<a6=%ymm1,>r=%ymm1
1236 vpand %ymm13,%ymm1,%ymm1
1237
1238 # qhasm: r6 ^= r
1239 # asm 1: vpxor <r=reg256#2,<r6=reg256#1,<r6=reg256#1
1240 # asm 2: vpxor <r=%ymm1,<r6=%ymm0,<r6=%ymm0
1241 vpxor %ymm1,%ymm0,%ymm0
1242
1243 # qhasm: mem256[ ptr + 192 ] = r6
1244 # asm 1: vmovupd <r6=reg256#1,192(<ptr=int64#5)
1245 # asm 2: vmovupd <r6=%ymm0,192(<ptr=%r8)
1246 vmovupd %ymm0,192(%r8)
1247
1248 # qhasm: r = b0 & a5
1249 # asm 1: vpand <b0=reg256#14,<a5=reg256#3,>r=reg256#1
1250 # asm 2: vpand <b0=%ymm13,<a5=%ymm2,>r=%ymm0
1251 vpand %ymm13,%ymm2,%ymm0
1252
1253 # qhasm: r5 ^= r
1254 # asm 1: vpxor <r=reg256#1,<r5=reg256#4,<r5=reg256#4
1255 # asm 2: vpxor <r=%ymm0,<r5=%ymm3,<r5=%ymm3
1256 vpxor %ymm0,%ymm3,%ymm3
1257
1258 # qhasm: r = b0 & a4
1259 # asm 1: vpand <b0=reg256#14,<a4=reg256#5,>r=reg256#1
1260 # asm 2: vpand <b0=%ymm13,<a4=%ymm4,>r=%ymm0
1261 vpand %ymm13,%ymm4,%ymm0
1262
1263 # qhasm: r4 ^= r
1264 # asm 1: vpxor <r=reg256#1,<r4=reg256#6,<r4=reg256#6
1265 # asm 2: vpxor <r=%ymm0,<r4=%ymm5,<r4=%ymm5
1266 vpxor %ymm0,%ymm5,%ymm5
1267
1268 # qhasm: r = b0 & a3
1269 # asm 1: vpand <b0=reg256#14,<a3=reg256#7,>r=reg256#1
1270 # asm 2: vpand <b0=%ymm13,<a3=%ymm6,>r=%ymm0
1271 vpand %ymm13,%ymm6,%ymm0
1272
1273 # qhasm: r3 ^= r
1274 # asm 1: vpxor <r=reg256#1,<r3=reg256#8,<r3=reg256#8
1275 # asm 2: vpxor <r=%ymm0,<r3=%ymm7,<r3=%ymm7
1276 vpxor %ymm0,%ymm7,%ymm7
1277
1278 # qhasm: r = b0 & a2
1279 # asm 1: vpand <b0=reg256#14,<a2=reg256#9,>r=reg256#1
1280 # asm 2: vpand <b0=%ymm13,<a2=%ymm8,>r=%ymm0
1281 vpand %ymm13,%ymm8,%ymm0
1282
1283 # qhasm: r2 ^= r
1284 # asm 1: vpxor <r=reg256#1,<r2=reg256#10,<r2=reg256#10
1285 # asm 2: vpxor <r=%ymm0,<r2=%ymm9,<r2=%ymm9
1286 vpxor %ymm0,%ymm9,%ymm9
1287
1288 # qhasm: r = b0 & a1
1289 # asm 1: vpand <b0=reg256#14,<a1=reg256#11,>r=reg256#1
1290 # asm 2: vpand <b0=%ymm13,<a1=%ymm10,>r=%ymm0
1291 vpand %ymm13,%ymm10,%ymm0
1292
1293 # qhasm: r1 ^= r
1294 # asm 1: vpxor <r=reg256#1,<r1=reg256#12,<r1=reg256#12
1295 # asm 2: vpxor <r=%ymm0,<r1=%ymm11,<r1=%ymm11
1296 vpxor %ymm0,%ymm11,%ymm11
1297
1298 # qhasm: r0 = b0 & a0
1299 # asm 1: vpand <b0=reg256#14,<a0=reg256#13,>r0=reg256#1
1300 # asm 2: vpand <b0=%ymm13,<a0=%ymm12,>r0=%ymm0
1301 vpand %ymm13,%ymm12,%ymm0
1302
1303 # qhasm: mem256[ ptr + 160 ] = r5
1304 # asm 1: vmovupd <r5=reg256#4,160(<ptr=int64#5)
1305 # asm 2: vmovupd <r5=%ymm3,160(<ptr=%r8)
1306 vmovupd %ymm3,160(%r8)
1307
1308 # qhasm: mem256[ ptr + 128 ] = r4
1309 # asm 1: vmovupd <r4=reg256#6,128(<ptr=int64#5)
1310 # asm 2: vmovupd <r4=%ymm5,128(<ptr=%r8)
1311 vmovupd %ymm5,128(%r8)
1312
1313 # qhasm: mem256[ ptr + 96 ] = r3
1314 # asm 1: vmovupd <r3=reg256#8,96(<ptr=int64#5)
1315 # asm 2: vmovupd <r3=%ymm7,96(<ptr=%r8)
1316 vmovupd %ymm7,96(%r8)
1317
1318 # qhasm: mem256[ ptr + 64 ] = r2
1319 # asm 1: vmovupd <r2=reg256#10,64(<ptr=int64#5)
1320 # asm 2: vmovupd <r2=%ymm9,64(<ptr=%r8)
1321 vmovupd %ymm9,64(%r8)
1322
1323 # qhasm: mem256[ ptr + 32 ] = r1
1324 # asm 1: vmovupd <r1=reg256#12,32(<ptr=int64#5)
1325 # asm 2: vmovupd <r1=%ymm11,32(<ptr=%r8)
1326 vmovupd %ymm11,32(%r8)
1327
1328 # qhasm: mem256[ ptr + 0 ] = r0
1329 # asm 1: vmovupd <r0=reg256#1,0(<ptr=int64#5)
1330 # asm 2: vmovupd <r0=%ymm0,0(<ptr=%r8)
1331 vmovupd %ymm0,0(%r8)
1332
1333 # qhasm: vzeroupper
1334 vzeroupper
1335
1336 # qhasm: h24 = mem128[ ptr + 560 ]
1337 # asm 1: movdqu 560(<ptr=int64#5),>h24=reg128#1
1338 # asm 2: movdqu 560(<ptr=%r8),>h24=%xmm0
1339 movdqu 560(%r8),%xmm0
1340
1341 # qhasm: h11 = h24
1342 # asm 1: movdqa <h24=reg128#1,>h11=reg128#2
1343 # asm 2: movdqa <h24=%xmm0,>h11=%xmm1
1344 movdqa %xmm0,%xmm1
1345
1346 # qhasm: h12 = h24
1347 # asm 1: movdqa <h24=reg128#1,>h12=reg128#3
1348 # asm 2: movdqa <h24=%xmm0,>h12=%xmm2
1349 movdqa %xmm0,%xmm2
1350
1351 # qhasm: h14 = h24
1352 # asm 1: movdqa <h24=reg128#1,>h14=reg128#4
1353 # asm 2: movdqa <h24=%xmm0,>h14=%xmm3
1354 movdqa %xmm0,%xmm3
1355
1356 # qhasm: h15 = h24
1357 # asm 1: movdqa <h24=reg128#1,>h15=reg128#1
1358 # asm 2: movdqa <h24=%xmm0,>h15=%xmm0
1359 movdqa %xmm0,%xmm0
1360
1361 # qhasm: h23 = mem128[ ptr + 528 ]
1362 # asm 1: movdqu 528(<ptr=int64#5),>h23=reg128#5
1363 # asm 2: movdqu 528(<ptr=%r8),>h23=%xmm4
1364 movdqu 528(%r8),%xmm4
1365
1366 # qhasm: h10 = h23
1367 # asm 1: movdqa <h23=reg128#5,>h10=reg128#6
1368 # asm 2: movdqa <h23=%xmm4,>h10=%xmm5
1369 movdqa %xmm4,%xmm5
1370
1371 # qhasm: h11 = h11 ^ h23
1372 # asm 1: vpxor <h23=reg128#5,<h11=reg128#2,>h11=reg128#2
1373 # asm 2: vpxor <h23=%xmm4,<h11=%xmm1,>h11=%xmm1
1374 vpxor %xmm4,%xmm1,%xmm1
1375
1376 # qhasm: h13 = h23
1377 # asm 1: movdqa <h23=reg128#5,>h13=reg128#7
1378 # asm 2: movdqa <h23=%xmm4,>h13=%xmm6
1379 movdqa %xmm4,%xmm6
1380
1381 # qhasm: h14 = h14 ^ h23
1382 # asm 1: vpxor <h23=reg128#5,<h14=reg128#4,>h14=reg128#4
1383 # asm 2: vpxor <h23=%xmm4,<h14=%xmm3,>h14=%xmm3
1384 vpxor %xmm4,%xmm3,%xmm3
1385
1386 # qhasm: h22 = mem128[ ptr + 496 ]
1387 # asm 1: movdqu 496(<ptr=int64#5),>h22=reg128#5
1388 # asm 2: movdqu 496(<ptr=%r8),>h22=%xmm4
1389 movdqu 496(%r8),%xmm4
1390
1391 # qhasm: h9 = h22
1392 # asm 1: movdqa <h22=reg128#5,>h9=reg128#8
1393 # asm 2: movdqa <h22=%xmm4,>h9=%xmm7
1394 movdqa %xmm4,%xmm7
1395
1396 # qhasm: h10 = h10 ^ h22
1397 # asm 1: vpxor <h22=reg128#5,<h10=reg128#6,>h10=reg128#6
1398 # asm 2: vpxor <h22=%xmm4,<h10=%xmm5,>h10=%xmm5
1399 vpxor %xmm4,%xmm5,%xmm5
1400
1401 # qhasm: h12 = h12 ^ h22
1402 # asm 1: vpxor <h22=reg128#5,<h12=reg128#3,>h12=reg128#3
1403 # asm 2: vpxor <h22=%xmm4,<h12=%xmm2,>h12=%xmm2
1404 vpxor %xmm4,%xmm2,%xmm2
1405
1406 # qhasm: h13 = h13 ^ h22
1407 # asm 1: vpxor <h22=reg128#5,<h13=reg128#7,>h13=reg128#5
1408 # asm 2: vpxor <h22=%xmm4,<h13=%xmm6,>h13=%xmm4
1409 vpxor %xmm4,%xmm6,%xmm4
1410
1411 # qhasm: h21 = mem128[ ptr + 464 ]
1412 # asm 1: movdqu 464(<ptr=int64#5),>h21=reg128#7
1413 # asm 2: movdqu 464(<ptr=%r8),>h21=%xmm6
1414 movdqu 464(%r8),%xmm6
1415
1416 # qhasm: h8 = h21
1417 # asm 1: movdqa <h21=reg128#7,>h8=reg128#9
1418 # asm 2: movdqa <h21=%xmm6,>h8=%xmm8
1419 movdqa %xmm6,%xmm8
1420
1421 # qhasm: h9 = h9 ^ h21
1422 # asm 1: vpxor <h21=reg128#7,<h9=reg128#8,>h9=reg128#8
1423 # asm 2: vpxor <h21=%xmm6,<h9=%xmm7,>h9=%xmm7
1424 vpxor %xmm6,%xmm7,%xmm7
1425
1426 # qhasm: h11 = h11 ^ h21
1427 # asm 1: vpxor <h21=reg128#7,<h11=reg128#2,>h11=reg128#2
1428 # asm 2: vpxor <h21=%xmm6,<h11=%xmm1,>h11=%xmm1
1429 vpxor %xmm6,%xmm1,%xmm1
1430
1431 # qhasm: h12 = h12 ^ h21
1432 # asm 1: vpxor <h21=reg128#7,<h12=reg128#3,>h12=reg128#3
1433 # asm 2: vpxor <h21=%xmm6,<h12=%xmm2,>h12=%xmm2
1434 vpxor %xmm6,%xmm2,%xmm2
1435
1436 # qhasm: h20 = mem128[ ptr + 432 ]
1437 # asm 1: movdqu 432(<ptr=int64#5),>h20=reg128#7
1438 # asm 2: movdqu 432(<ptr=%r8),>h20=%xmm6
1439 movdqu 432(%r8),%xmm6
1440
1441 # qhasm: h7 = h20
1442 # asm 1: movdqa <h20=reg128#7,>h7=reg128#10
1443 # asm 2: movdqa <h20=%xmm6,>h7=%xmm9
1444 movdqa %xmm6,%xmm9
1445
1446 # qhasm: h8 = h8 ^ h20
1447 # asm 1: vpxor <h20=reg128#7,<h8=reg128#9,>h8=reg128#9
1448 # asm 2: vpxor <h20=%xmm6,<h8=%xmm8,>h8=%xmm8
1449 vpxor %xmm6,%xmm8,%xmm8
1450
1451 # qhasm: h10 = h10 ^ h20
1452 # asm 1: vpxor <h20=reg128#7,<h10=reg128#6,>h10=reg128#6
1453 # asm 2: vpxor <h20=%xmm6,<h10=%xmm5,>h10=%xmm5
1454 vpxor %xmm6,%xmm5,%xmm5
1455
1456 # qhasm: h11 = h11 ^ h20
1457 # asm 1: vpxor <h20=reg128#7,<h11=reg128#2,>h11=reg128#2
1458 # asm 2: vpxor <h20=%xmm6,<h11=%xmm1,>h11=%xmm1
1459 vpxor %xmm6,%xmm1,%xmm1
1460
1461 # qhasm: h19 = mem128[ ptr + 400 ]
1462 # asm 1: movdqu 400(<ptr=int64#5),>h19=reg128#7
1463 # asm 2: movdqu 400(<ptr=%r8),>h19=%xmm6
1464 movdqu 400(%r8),%xmm6
1465
1466 # qhasm: h6 = h19
1467 # asm 1: movdqa <h19=reg128#7,>h6=reg128#11
1468 # asm 2: movdqa <h19=%xmm6,>h6=%xmm10
1469 movdqa %xmm6,%xmm10
1470
1471 # qhasm: h7 = h7 ^ h19
1472 # asm 1: vpxor <h19=reg128#7,<h7=reg128#10,>h7=reg128#10
1473 # asm 2: vpxor <h19=%xmm6,<h7=%xmm9,>h7=%xmm9
1474 vpxor %xmm6,%xmm9,%xmm9
1475
1476 # qhasm: h9 = h9 ^ h19
1477 # asm 1: vpxor <h19=reg128#7,<h9=reg128#8,>h9=reg128#8
1478 # asm 2: vpxor <h19=%xmm6,<h9=%xmm7,>h9=%xmm7
1479 vpxor %xmm6,%xmm7,%xmm7
1480
1481 # qhasm: h10 = h10 ^ h19
1482 # asm 1: vpxor <h19=reg128#7,<h10=reg128#6,>h10=reg128#6
1483 # asm 2: vpxor <h19=%xmm6,<h10=%xmm5,>h10=%xmm5
1484 vpxor %xmm6,%xmm5,%xmm5
1485
1486 # qhasm: h18 = mem128[ ptr + 368 ]
1487 # asm 1: movdqu 368(<ptr=int64#5),>h18=reg128#7
1488 # asm 2: movdqu 368(<ptr=%r8),>h18=%xmm6
1489 movdqu 368(%r8),%xmm6
1490
1491 # qhasm: h18 = h18 ^ mem128[ ptr + 576 ]
1492 # asm 1: vpxor 576(<ptr=int64#5),<h18=reg128#7,>h18=reg128#7
1493 # asm 2: vpxor 576(<ptr=%r8),<h18=%xmm6,>h18=%xmm6
1494 vpxor 576(%r8),%xmm6,%xmm6
1495
1496 # qhasm: h5 = h18
1497 # asm 1: movdqa <h18=reg128#7,>h5=reg128#12
1498 # asm 2: movdqa <h18=%xmm6,>h5=%xmm11
1499 movdqa %xmm6,%xmm11
1500
1501 # qhasm: h6 = h6 ^ h18
1502 # asm 1: vpxor <h18=reg128#7,<h6=reg128#11,>h6=reg128#11
1503 # asm 2: vpxor <h18=%xmm6,<h6=%xmm10,>h6=%xmm10
1504 vpxor %xmm6,%xmm10,%xmm10
1505
1506 # qhasm: h8 = h8 ^ h18
1507 # asm 1: vpxor <h18=reg128#7,<h8=reg128#9,>h8=reg128#9
1508 # asm 2: vpxor <h18=%xmm6,<h8=%xmm8,>h8=%xmm8
1509 vpxor %xmm6,%xmm8,%xmm8
1510
1511 # qhasm: h9 = h9 ^ h18
1512 # asm 1: vpxor <h18=reg128#7,<h9=reg128#8,>h9=reg128#7
1513 # asm 2: vpxor <h18=%xmm6,<h9=%xmm7,>h9=%xmm6
1514 vpxor %xmm6,%xmm7,%xmm6
1515
1516 # qhasm: h17 = mem128[ ptr + 336 ]
1517 # asm 1: movdqu 336(<ptr=int64#5),>h17=reg128#8
1518 # asm 2: movdqu 336(<ptr=%r8),>h17=%xmm7
1519 movdqu 336(%r8),%xmm7
1520
1521 # qhasm: h17 = h17 ^ mem128[ ptr + 544 ]
1522 # asm 1: vpxor 544(<ptr=int64#5),<h17=reg128#8,>h17=reg128#8
1523 # asm 2: vpxor 544(<ptr=%r8),<h17=%xmm7,>h17=%xmm7
1524 vpxor 544(%r8),%xmm7,%xmm7
1525
1526 # qhasm: h4 = h17
1527 # asm 1: movdqa <h17=reg128#8,>h4=reg128#13
1528 # asm 2: movdqa <h17=%xmm7,>h4=%xmm12
1529 movdqa %xmm7,%xmm12
1530
1531 # qhasm: h5 = h5 ^ h17
1532 # asm 1: vpxor <h17=reg128#8,<h5=reg128#12,>h5=reg128#12
1533 # asm 2: vpxor <h17=%xmm7,<h5=%xmm11,>h5=%xmm11
1534 vpxor %xmm7,%xmm11,%xmm11
1535
1536 # qhasm: h7 = h7 ^ h17
1537 # asm 1: vpxor <h17=reg128#8,<h7=reg128#10,>h7=reg128#10
1538 # asm 2: vpxor <h17=%xmm7,<h7=%xmm9,>h7=%xmm9
1539 vpxor %xmm7,%xmm9,%xmm9
1540
1541 # qhasm: h8 = h8 ^ h17
1542 # asm 1: vpxor <h17=reg128#8,<h8=reg128#9,>h8=reg128#8
1543 # asm 2: vpxor <h17=%xmm7,<h8=%xmm8,>h8=%xmm7
1544 vpxor %xmm7,%xmm8,%xmm7
1545
1546 # qhasm: h16 = mem128[ ptr + 304 ]
1547 # asm 1: movdqu 304(<ptr=int64#5),>h16=reg128#9
1548 # asm 2: movdqu 304(<ptr=%r8),>h16=%xmm8
1549 movdqu 304(%r8),%xmm8
1550
1551 # qhasm: h16 = h16 ^ mem128[ ptr + 512 ]
1552 # asm 1: vpxor 512(<ptr=int64#5),<h16=reg128#9,>h16=reg128#9
1553 # asm 2: vpxor 512(<ptr=%r8),<h16=%xmm8,>h16=%xmm8
1554 vpxor 512(%r8),%xmm8,%xmm8
1555
1556 # qhasm: h3 = h16
1557 # asm 1: movdqa <h16=reg128#9,>h3=reg128#14
1558 # asm 2: movdqa <h16=%xmm8,>h3=%xmm13
1559 movdqa %xmm8,%xmm13
1560
1561 # qhasm: h4 = h4 ^ h16
1562 # asm 1: vpxor <h16=reg128#9,<h4=reg128#13,>h4=reg128#13
1563 # asm 2: vpxor <h16=%xmm8,<h4=%xmm12,>h4=%xmm12
1564 vpxor %xmm8,%xmm12,%xmm12
1565
1566 # qhasm: h6 = h6 ^ h16
1567 # asm 1: vpxor <h16=reg128#9,<h6=reg128#11,>h6=reg128#11
1568 # asm 2: vpxor <h16=%xmm8,<h6=%xmm10,>h6=%xmm10
1569 vpxor %xmm8,%xmm10,%xmm10
1570
1571 # qhasm: h7 = h7 ^ h16
1572 # asm 1: vpxor <h16=reg128#9,<h7=reg128#10,>h7=reg128#9
1573 # asm 2: vpxor <h16=%xmm8,<h7=%xmm9,>h7=%xmm8
1574 vpxor %xmm8,%xmm9,%xmm8
1575
1576 # qhasm: h15 = h15 ^ mem128[ ptr + 272 ]
1577 # asm 1: vpxor 272(<ptr=int64#5),<h15=reg128#1,>h15=reg128#1
1578 # asm 2: vpxor 272(<ptr=%r8),<h15=%xmm0,>h15=%xmm0
1579 vpxor 272(%r8),%xmm0,%xmm0
1580
1581 # qhasm: h15 = h15 ^ mem128[ ptr + 480 ]
1582 # asm 1: vpxor 480(<ptr=int64#5),<h15=reg128#1,>h15=reg128#1
1583 # asm 2: vpxor 480(<ptr=%r8),<h15=%xmm0,>h15=%xmm0
1584 vpxor 480(%r8),%xmm0,%xmm0
1585
1586 # qhasm: h2 = h15
1587 # asm 1: movdqa <h15=reg128#1,>h2=reg128#10
1588 # asm 2: movdqa <h15=%xmm0,>h2=%xmm9
1589 movdqa %xmm0,%xmm9
1590
1591 # qhasm: h3 = h3 ^ h15
1592 # asm 1: vpxor <h15=reg128#1,<h3=reg128#14,>h3=reg128#14
1593 # asm 2: vpxor <h15=%xmm0,<h3=%xmm13,>h3=%xmm13
1594 vpxor %xmm0,%xmm13,%xmm13
1595
1596 # qhasm: h5 = h5 ^ h15
1597 # asm 1: vpxor <h15=reg128#1,<h5=reg128#12,>h5=reg128#12
1598 # asm 2: vpxor <h15=%xmm0,<h5=%xmm11,>h5=%xmm11
1599 vpxor %xmm0,%xmm11,%xmm11
1600
1601 # qhasm: h6 = h6 ^ h15
1602 # asm 1: vpxor <h15=reg128#1,<h6=reg128#11,>h6=reg128#1
1603 # asm 2: vpxor <h15=%xmm0,<h6=%xmm10,>h6=%xmm0
1604 vpxor %xmm0,%xmm10,%xmm0
1605
1606 # qhasm: h14 = h14 ^ mem128[ ptr + 240 ]
1607 # asm 1: vpxor 240(<ptr=int64#5),<h14=reg128#4,>h14=reg128#4
1608 # asm 2: vpxor 240(<ptr=%r8),<h14=%xmm3,>h14=%xmm3
1609 vpxor 240(%r8),%xmm3,%xmm3
1610
1611 # qhasm: h14 = h14 ^ mem128[ ptr + 448 ]
1612 # asm 1: vpxor 448(<ptr=int64#5),<h14=reg128#4,>h14=reg128#4
1613 # asm 2: vpxor 448(<ptr=%r8),<h14=%xmm3,>h14=%xmm3
1614 vpxor 448(%r8),%xmm3,%xmm3
1615
1616 # qhasm: h1 = h14
1617 # asm 1: movdqa <h14=reg128#4,>h1=reg128#11
1618 # asm 2: movdqa <h14=%xmm3,>h1=%xmm10
1619 movdqa %xmm3,%xmm10
1620
1621 # qhasm: h2 = h2 ^ h14
1622 # asm 1: vpxor <h14=reg128#4,<h2=reg128#10,>h2=reg128#10
1623 # asm 2: vpxor <h14=%xmm3,<h2=%xmm9,>h2=%xmm9
1624 vpxor %xmm3,%xmm9,%xmm9
1625
1626 # qhasm: h4 = h4 ^ h14
1627 # asm 1: vpxor <h14=reg128#4,<h4=reg128#13,>h4=reg128#13
1628 # asm 2: vpxor <h14=%xmm3,<h4=%xmm12,>h4=%xmm12
1629 vpxor %xmm3,%xmm12,%xmm12
1630
1631 # qhasm: h5 = h5 ^ h14
1632 # asm 1: vpxor <h14=reg128#4,<h5=reg128#12,>h5=reg128#4
1633 # asm 2: vpxor <h14=%xmm3,<h5=%xmm11,>h5=%xmm3
1634 vpxor %xmm3,%xmm11,%xmm3
1635
1636 # qhasm: h13 = h13 ^ mem128[ ptr + 208 ]
1637 # asm 1: vpxor 208(<ptr=int64#5),<h13=reg128#5,>h13=reg128#5
1638 # asm 2: vpxor 208(<ptr=%r8),<h13=%xmm4,>h13=%xmm4
1639 vpxor 208(%r8),%xmm4,%xmm4
1640
1641 # qhasm: h13 = h13 ^ mem128[ ptr + 416 ]
1642 # asm 1: vpxor 416(<ptr=int64#5),<h13=reg128#5,>h13=reg128#5
1643 # asm 2: vpxor 416(<ptr=%r8),<h13=%xmm4,>h13=%xmm4
1644 vpxor 416(%r8),%xmm4,%xmm4
1645
1646 # qhasm: h0 = h13
1647 # asm 1: movdqa <h13=reg128#5,>h0=reg128#12
1648 # asm 2: movdqa <h13=%xmm4,>h0=%xmm11
1649 movdqa %xmm4,%xmm11
1650
1651 # qhasm: h1 = h1 ^ h13
1652 # asm 1: vpxor <h13=reg128#5,<h1=reg128#11,>h1=reg128#11
1653 # asm 2: vpxor <h13=%xmm4,<h1=%xmm10,>h1=%xmm10
1654 vpxor %xmm4,%xmm10,%xmm10
1655
1656 # qhasm: h3 = h3 ^ h13
1657 # asm 1: vpxor <h13=reg128#5,<h3=reg128#14,>h3=reg128#14
1658 # asm 2: vpxor <h13=%xmm4,<h3=%xmm13,>h3=%xmm13
1659 vpxor %xmm4,%xmm13,%xmm13
1660
1661 # qhasm: h4 = h4 ^ h13
1662 # asm 1: vpxor <h13=reg128#5,<h4=reg128#13,>h4=reg128#5
1663 # asm 2: vpxor <h13=%xmm4,<h4=%xmm12,>h4=%xmm4
1664 vpxor %xmm4,%xmm12,%xmm4
1665
1666 # qhasm: h12 = h12 ^ mem128[ ptr + 384 ]
1667 # asm 1: vpxor 384(<ptr=int64#5),<h12=reg128#3,>h12=reg128#3
1668 # asm 2: vpxor 384(<ptr=%r8),<h12=%xmm2,>h12=%xmm2
1669 vpxor 384(%r8),%xmm2,%xmm2
1670
1671 # qhasm: h12 = h12 ^ mem128[ ptr + 176 ]
1672 # asm 1: vpxor 176(<ptr=int64#5),<h12=reg128#3,>h12=reg128#3
1673 # asm 2: vpxor 176(<ptr=%r8),<h12=%xmm2,>h12=%xmm2
1674 vpxor 176(%r8),%xmm2,%xmm2
1675
1676 # qhasm: mem128[ input_0 + 192 ] = h12
1677 # asm 1: movdqu <h12=reg128#3,192(<input_0=int64#1)
1678 # asm 2: movdqu <h12=%xmm2,192(<input_0=%rdi)
1679 movdqu %xmm2,192(%rdi)
1680
1681 # qhasm: h11 = h11 ^ mem128[ ptr + 352 ]
1682 # asm 1: vpxor 352(<ptr=int64#5),<h11=reg128#2,>h11=reg128#2
1683 # asm 2: vpxor 352(<ptr=%r8),<h11=%xmm1,>h11=%xmm1
1684 vpxor 352(%r8),%xmm1,%xmm1
1685
1686 # qhasm: h11 = h11 ^ mem128[ ptr + 144 ]
1687 # asm 1: vpxor 144(<ptr=int64#5),<h11=reg128#2,>h11=reg128#2
1688 # asm 2: vpxor 144(<ptr=%r8),<h11=%xmm1,>h11=%xmm1
1689 vpxor 144(%r8),%xmm1,%xmm1
1690
1691 # qhasm: mem128[ input_0 + 176 ] = h11
1692 # asm 1: movdqu <h11=reg128#2,176(<input_0=int64#1)
1693 # asm 2: movdqu <h11=%xmm1,176(<input_0=%rdi)
1694 movdqu %xmm1,176(%rdi)
1695
1696 # qhasm: h10 = h10 ^ mem128[ ptr + 320 ]
1697 # asm 1: vpxor 320(<ptr=int64#5),<h10=reg128#6,>h10=reg128#2
1698 # asm 2: vpxor 320(<ptr=%r8),<h10=%xmm5,>h10=%xmm1
1699 vpxor 320(%r8),%xmm5,%xmm1
1700
1701 # qhasm: h10 = h10 ^ mem128[ ptr + 112 ]
1702 # asm 1: vpxor 112(<ptr=int64#5),<h10=reg128#2,>h10=reg128#2
1703 # asm 2: vpxor 112(<ptr=%r8),<h10=%xmm1,>h10=%xmm1
1704 vpxor 112(%r8),%xmm1,%xmm1
1705
1706 # qhasm: mem128[ input_0 + 160 ] = h10
1707 # asm 1: movdqu <h10=reg128#2,160(<input_0=int64#1)
1708 # asm 2: movdqu <h10=%xmm1,160(<input_0=%rdi)
1709 movdqu %xmm1,160(%rdi)
1710
1711 # qhasm: h9 = h9 ^ mem128[ ptr + 288 ]
1712 # asm 1: vpxor 288(<ptr=int64#5),<h9=reg128#7,>h9=reg128#2
1713 # asm 2: vpxor 288(<ptr=%r8),<h9=%xmm6,>h9=%xmm1
1714 vpxor 288(%r8),%xmm6,%xmm1
1715
1716 # qhasm: h9 = h9 ^ mem128[ ptr + 80 ]
1717 # asm 1: vpxor 80(<ptr=int64#5),<h9=reg128#2,>h9=reg128#2
1718 # asm 2: vpxor 80(<ptr=%r8),<h9=%xmm1,>h9=%xmm1
1719 vpxor 80(%r8),%xmm1,%xmm1
1720
1721 # qhasm: mem128[ input_0 + 144 ] = h9
1722 # asm 1: movdqu <h9=reg128#2,144(<input_0=int64#1)
1723 # asm 2: movdqu <h9=%xmm1,144(<input_0=%rdi)
1724 movdqu %xmm1,144(%rdi)
1725
1726 # qhasm: h8 = h8 ^ mem128[ ptr + 256 ]
1727 # asm 1: vpxor 256(<ptr=int64#5),<h8=reg128#8,>h8=reg128#2
1728 # asm 2: vpxor 256(<ptr=%r8),<h8=%xmm7,>h8=%xmm1
1729 vpxor 256(%r8),%xmm7,%xmm1
1730
1731 # qhasm: h8 = h8 ^ mem128[ ptr + 48 ]
1732 # asm 1: vpxor 48(<ptr=int64#5),<h8=reg128#2,>h8=reg128#2
1733 # asm 2: vpxor 48(<ptr=%r8),<h8=%xmm1,>h8=%xmm1
1734 vpxor 48(%r8),%xmm1,%xmm1
1735
1736 # qhasm: mem128[ input_0 + 128 ] = h8
1737 # asm 1: movdqu <h8=reg128#2,128(<input_0=int64#1)
1738 # asm 2: movdqu <h8=%xmm1,128(<input_0=%rdi)
1739 movdqu %xmm1,128(%rdi)
1740
1741 # qhasm: h7 = h7 ^ mem128[ ptr + 224 ]
1742 # asm 1: vpxor 224(<ptr=int64#5),<h7=reg128#9,>h7=reg128#2
1743 # asm 2: vpxor 224(<ptr=%r8),<h7=%xmm8,>h7=%xmm1
1744 vpxor 224(%r8),%xmm8,%xmm1
1745
1746 # qhasm: h7 = h7 ^ mem128[ ptr + 16 ]
1747 # asm 1: vpxor 16(<ptr=int64#5),<h7=reg128#2,>h7=reg128#2
1748 # asm 2: vpxor 16(<ptr=%r8),<h7=%xmm1,>h7=%xmm1
1749 vpxor 16(%r8),%xmm1,%xmm1
1750
1751 # qhasm: mem128[ input_0 + 112 ] = h7
1752 # asm 1: movdqu <h7=reg128#2,112(<input_0=int64#1)
1753 # asm 2: movdqu <h7=%xmm1,112(<input_0=%rdi)
1754 movdqu %xmm1,112(%rdi)
1755
1756 # qhasm: h6 = h6 ^ mem128[ ptr + 192 ]
1757 # asm 1: vpxor 192(<ptr=int64#5),<h6=reg128#1,>h6=reg128#1
1758 # asm 2: vpxor 192(<ptr=%r8),<h6=%xmm0,>h6=%xmm0
1759 vpxor 192(%r8),%xmm0,%xmm0
1760
1761 # qhasm: mem128[ input_0 + 96 ] = h6
1762 # asm 1: movdqu <h6=reg128#1,96(<input_0=int64#1)
1763 # asm 2: movdqu <h6=%xmm0,96(<input_0=%rdi)
1764 movdqu %xmm0,96(%rdi)
1765
1766 # qhasm: h5 = h5 ^ mem128[ ptr + 160 ]
1767 # asm 1: vpxor 160(<ptr=int64#5),<h5=reg128#4,>h5=reg128#1
1768 # asm 2: vpxor 160(<ptr=%r8),<h5=%xmm3,>h5=%xmm0
1769 vpxor 160(%r8),%xmm3,%xmm0
1770
1771 # qhasm: mem128[ input_0 + 80 ] = h5
1772 # asm 1: movdqu <h5=reg128#1,80(<input_0=int64#1)
1773 # asm 2: movdqu <h5=%xmm0,80(<input_0=%rdi)
1774 movdqu %xmm0,80(%rdi)
1775
1776 # qhasm: h4 = h4 ^ mem128[ ptr + 128 ]
1777 # asm 1: vpxor 128(<ptr=int64#5),<h4=reg128#5,>h4=reg128#1
1778 # asm 2: vpxor 128(<ptr=%r8),<h4=%xmm4,>h4=%xmm0
1779 vpxor 128(%r8),%xmm4,%xmm0
1780
1781 # qhasm: mem128[ input_0 + 64 ] = h4
1782 # asm 1: movdqu <h4=reg128#1,64(<input_0=int64#1)
1783 # asm 2: movdqu <h4=%xmm0,64(<input_0=%rdi)
1784 movdqu %xmm0,64(%rdi)
1785
1786 # qhasm: h3 = h3 ^ mem128[ ptr + 96 ]
1787 # asm 1: vpxor 96(<ptr=int64#5),<h3=reg128#14,>h3=reg128#1
1788 # asm 2: vpxor 96(<ptr=%r8),<h3=%xmm13,>h3=%xmm0
1789 vpxor 96(%r8),%xmm13,%xmm0
1790
1791 # qhasm: mem128[ input_0 + 48 ] = h3
1792 # asm 1: movdqu <h3=reg128#1,48(<input_0=int64#1)
1793 # asm 2: movdqu <h3=%xmm0,48(<input_0=%rdi)
1794 movdqu %xmm0,48(%rdi)
1795
1796 # qhasm: h2 = h2 ^ mem128[ ptr + 64 ]
1797 # asm 1: vpxor 64(<ptr=int64#5),<h2=reg128#10,>h2=reg128#1
1798 # asm 2: vpxor 64(<ptr=%r8),<h2=%xmm9,>h2=%xmm0
1799 vpxor 64(%r8),%xmm9,%xmm0
1800
1801 # qhasm: mem128[ input_0 + 32 ] = h2
1802 # asm 1: movdqu <h2=reg128#1,32(<input_0=int64#1)
1803 # asm 2: movdqu <h2=%xmm0,32(<input_0=%rdi)
1804 movdqu %xmm0,32(%rdi)
1805
1806 # qhasm: h1 = h1 ^ mem128[ ptr + 32 ]
1807 # asm 1: vpxor 32(<ptr=int64#5),<h1=reg128#11,>h1=reg128#1
1808 # asm 2: vpxor 32(<ptr=%r8),<h1=%xmm10,>h1=%xmm0
1809 vpxor 32(%r8),%xmm10,%xmm0
1810
1811 # qhasm: mem128[ input_0 + 16 ] = h1
1812 # asm 1: movdqu <h1=reg128#1,16(<input_0=int64#1)
1813 # asm 2: movdqu <h1=%xmm0,16(<input_0=%rdi)
1814 movdqu %xmm0,16(%rdi)
1815
1816 # qhasm: h0 = h0 ^ mem128[ ptr + 0 ]
1817 # asm 1: vpxor 0(<ptr=int64#5),<h0=reg128#12,>h0=reg128#1
1818 # asm 2: vpxor 0(<ptr=%r8),<h0=%xmm11,>h0=%xmm0
1819 vpxor 0(%r8),%xmm11,%xmm0
1820
1821 # qhasm: mem128[ input_0 + 0 ] = h0
1822 # asm 1: movdqu <h0=reg128#1,0(<input_0=int64#1)
1823 # asm 2: movdqu <h0=%xmm0,0(<input_0=%rdi)
1824 movdqu %xmm0,0(%rdi)
1825
1826 # qhasm: return
1827 add %r11,%rsp
1828 ret
1829 .section .note.GNU-stack,"",@progbits