Debian Codegraph @

crypto_kem/348864f/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 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: reg128 h0
127
128 # qhasm: reg128 h1
129
130 # qhasm: reg128 h2
131
132 # qhasm: reg128 h3
133
134 # qhasm: reg128 h4
135
136 # qhasm: reg128 h5
137
138 # qhasm: reg128 h6
139
140 # qhasm: reg128 h7
141
142 # qhasm: reg128 h8
143
144 # qhasm: reg128 h9
145
146 # qhasm: reg128 h10
147
148 # qhasm: reg128 h11
149
150 # qhasm: reg128 h12
151
152 # qhasm: reg128 h13
153
154 # qhasm: reg128 h14
155
156 # qhasm: reg128 h15
157
158 # qhasm: reg128 h16
159
160 # qhasm: reg128 h17
161
162 # qhasm: reg128 h18
163
164 # qhasm: reg128 h19
165
166 # qhasm: reg128 h20
167
168 # qhasm: reg128 h21
169
170 # qhasm: reg128 h22
171
172 # qhasm: stack4864 buf
173
174 # qhasm: int64 ptr
175
176 # qhasm: int64 tmp
177
178 # qhasm: enter vec128_mul_asm
179 .p2align 5
180 ASM_HIDDEN _vec128_mul_asm
181 ASM_HIDDEN vec128_mul_asm
182 .global _vec128_mul_asm
183 .global vec128_mul_asm
184 _vec128_mul_asm:
185 vec128_mul_asm:
186 mov %rsp,%r11
187 AND $31,%r11
188 add $608,%r11
189 sub %r11,%rsp
190
191 # qhasm: ptr = &buf
192 # asm 1: leaq <buf=stack4864#1,>ptr=int64#4
193 # asm 2: leaq <buf=0(%rsp),>ptr=%rcx
194 leaq 0(%rsp),%rcx
195
196 # qhasm: b11 = mem128[ input_2 + 176 ] x2
197 # asm 1: vbroadcasti128 176(<input_2=int64#3), >b11=reg256#1
198 # asm 2: vbroadcasti128 176(<input_2=%rdx), >b11=%ymm0
199 vbroadcasti128 176(%rdx), %ymm0
200
201 # qhasm: a5[0] = mem128[ input_1 + 80 ]
202 # asm 1: vinsertf128 $0x0,80(<input_1=int64#2),<a5=reg256#2,<a5=reg256#2
203 # asm 2: vinsertf128 $0x0,80(<input_1=%rsi),<a5=%ymm1,<a5=%ymm1
204 vinsertf128 $0x0,80(%rsi),%ymm1,%ymm1
205
206 # qhasm: a5[1] = mem128[ input_1 + 176 ]
207 # asm 1: vinsertf128 $0x1,176(<input_1=int64#2),<a5=reg256#2,<a5=reg256#2
208 # asm 2: vinsertf128 $0x1,176(<input_1=%rsi),<a5=%ymm1,<a5=%ymm1
209 vinsertf128 $0x1,176(%rsi),%ymm1,%ymm1
210
211 # qhasm: r16 = b11 & a5
212 # asm 1: vpand <b11=reg256#1,<a5=reg256#2,>r16=reg256#3
213 # asm 2: vpand <b11=%ymm0,<a5=%ymm1,>r16=%ymm2
214 vpand %ymm0,%ymm1,%ymm2
215
216 # qhasm: mem256[ ptr + 512 ] = r16
217 # asm 1: vmovupd <r16=reg256#3,512(<ptr=int64#4)
218 # asm 2: vmovupd <r16=%ymm2,512(<ptr=%rcx)
219 vmovupd %ymm2,512(%rcx)
220
221 # qhasm: a4[0] = mem128[ input_1 + 64 ]
222 # asm 1: vinsertf128 $0x0,64(<input_1=int64#2),<a4=reg256#3,<a4=reg256#3
223 # asm 2: vinsertf128 $0x0,64(<input_1=%rsi),<a4=%ymm2,<a4=%ymm2
224 vinsertf128 $0x0,64(%rsi),%ymm2,%ymm2
225
226 # qhasm: a4[1] = mem128[ input_1 + 160 ]
227 # asm 1: vinsertf128 $0x1,160(<input_1=int64#2),<a4=reg256#3,<a4=reg256#3
228 # asm 2: vinsertf128 $0x1,160(<input_1=%rsi),<a4=%ymm2,<a4=%ymm2
229 vinsertf128 $0x1,160(%rsi),%ymm2,%ymm2
230
231 # qhasm: r15 = b11 & a4
232 # asm 1: vpand <b11=reg256#1,<a4=reg256#3,>r15=reg256#4
233 # asm 2: vpand <b11=%ymm0,<a4=%ymm2,>r15=%ymm3
234 vpand %ymm0,%ymm2,%ymm3
235
236 # qhasm: a3[0] = mem128[ input_1 + 48 ]
237 # asm 1: vinsertf128 $0x0,48(<input_1=int64#2),<a3=reg256#5,<a3=reg256#5
238 # asm 2: vinsertf128 $0x0,48(<input_1=%rsi),<a3=%ymm4,<a3=%ymm4
239 vinsertf128 $0x0,48(%rsi),%ymm4,%ymm4
240
241 # qhasm: a3[1] = mem128[ input_1 + 144 ]
242 # asm 1: vinsertf128 $0x1,144(<input_1=int64#2),<a3=reg256#5,<a3=reg256#5
243 # asm 2: vinsertf128 $0x1,144(<input_1=%rsi),<a3=%ymm4,<a3=%ymm4
244 vinsertf128 $0x1,144(%rsi),%ymm4,%ymm4
245
246 # qhasm: r14 = b11 & a3
247 # asm 1: vpand <b11=reg256#1,<a3=reg256#5,>r14=reg256#6
248 # asm 2: vpand <b11=%ymm0,<a3=%ymm4,>r14=%ymm5
249 vpand %ymm0,%ymm4,%ymm5
250
251 # qhasm: a2[0] = mem128[ input_1 + 32 ]
252 # asm 1: vinsertf128 $0x0,32(<input_1=int64#2),<a2=reg256#7,<a2=reg256#7
253 # asm 2: vinsertf128 $0x0,32(<input_1=%rsi),<a2=%ymm6,<a2=%ymm6
254 vinsertf128 $0x0,32(%rsi),%ymm6,%ymm6
255
256 # qhasm: a2[1] = mem128[ input_1 + 128 ]
257 # asm 1: vinsertf128 $0x1,128(<input_1=int64#2),<a2=reg256#7,<a2=reg256#7
258 # asm 2: vinsertf128 $0x1,128(<input_1=%rsi),<a2=%ymm6,<a2=%ymm6
259 vinsertf128 $0x1,128(%rsi),%ymm6,%ymm6
260
261 # qhasm: r13 = b11 & a2
262 # asm 1: vpand <b11=reg256#1,<a2=reg256#7,>r13=reg256#8
263 # asm 2: vpand <b11=%ymm0,<a2=%ymm6,>r13=%ymm7
264 vpand %ymm0,%ymm6,%ymm7
265
266 # qhasm: a1[0] = mem128[ input_1 + 16 ]
267 # asm 1: vinsertf128 $0x0,16(<input_1=int64#2),<a1=reg256#9,<a1=reg256#9
268 # asm 2: vinsertf128 $0x0,16(<input_1=%rsi),<a1=%ymm8,<a1=%ymm8
269 vinsertf128 $0x0,16(%rsi),%ymm8,%ymm8
270
271 # qhasm: a1[1] = mem128[ input_1 + 112 ]
272 # asm 1: vinsertf128 $0x1,112(<input_1=int64#2),<a1=reg256#9,<a1=reg256#9
273 # asm 2: vinsertf128 $0x1,112(<input_1=%rsi),<a1=%ymm8,<a1=%ymm8
274 vinsertf128 $0x1,112(%rsi),%ymm8,%ymm8
275
276 # qhasm: r12 = b11 & a1
277 # asm 1: vpand <b11=reg256#1,<a1=reg256#9,>r12=reg256#10
278 # asm 2: vpand <b11=%ymm0,<a1=%ymm8,>r12=%ymm9
279 vpand %ymm0,%ymm8,%ymm9
280
281 # qhasm: a0[0] = mem128[ input_1 + 0 ]
282 # asm 1: vinsertf128 $0x0,0(<input_1=int64#2),<a0=reg256#11,<a0=reg256#11
283 # asm 2: vinsertf128 $0x0,0(<input_1=%rsi),<a0=%ymm10,<a0=%ymm10
284 vinsertf128 $0x0,0(%rsi),%ymm10,%ymm10
285
286 # qhasm: a0[1] = mem128[ input_1 + 96 ]
287 # asm 1: vinsertf128 $0x1,96(<input_1=int64#2),<a0=reg256#11,<a0=reg256#11
288 # asm 2: vinsertf128 $0x1,96(<input_1=%rsi),<a0=%ymm10,<a0=%ymm10
289 vinsertf128 $0x1,96(%rsi),%ymm10,%ymm10
290
291 # qhasm: r11 = b11 & a0
292 # asm 1: vpand <b11=reg256#1,<a0=reg256#11,>r11=reg256#1
293 # asm 2: vpand <b11=%ymm0,<a0=%ymm10,>r11=%ymm0
294 vpand %ymm0,%ymm10,%ymm0
295
296 # qhasm: b10 = mem128[ input_2 + 160 ] x2
297 # asm 1: vbroadcasti128 160(<input_2=int64#3), >b10=reg256#12
298 # asm 2: vbroadcasti128 160(<input_2=%rdx), >b10=%ymm11
299 vbroadcasti128 160(%rdx), %ymm11
300
301 # qhasm: r = b10 & a5
302 # asm 1: vpand <b10=reg256#12,<a5=reg256#2,>r=reg256#13
303 # asm 2: vpand <b10=%ymm11,<a5=%ymm1,>r=%ymm12
304 vpand %ymm11,%ymm1,%ymm12
305
306 # qhasm: r15 ^= r
307 # asm 1: vpxor <r=reg256#13,<r15=reg256#4,<r15=reg256#4
308 # asm 2: vpxor <r=%ymm12,<r15=%ymm3,<r15=%ymm3
309 vpxor %ymm12,%ymm3,%ymm3
310
311 # qhasm: mem256[ ptr + 480 ] = r15
312 # asm 1: vmovupd <r15=reg256#4,480(<ptr=int64#4)
313 # asm 2: vmovupd <r15=%ymm3,480(<ptr=%rcx)
314 vmovupd %ymm3,480(%rcx)
315
316 # qhasm: r = b10 & a4
317 # asm 1: vpand <b10=reg256#12,<a4=reg256#3,>r=reg256#4
318 # asm 2: vpand <b10=%ymm11,<a4=%ymm2,>r=%ymm3
319 vpand %ymm11,%ymm2,%ymm3
320
321 # qhasm: r14 ^= r
322 # asm 1: vpxor <r=reg256#4,<r14=reg256#6,<r14=reg256#6
323 # asm 2: vpxor <r=%ymm3,<r14=%ymm5,<r14=%ymm5
324 vpxor %ymm3,%ymm5,%ymm5
325
326 # qhasm: r = b10 & a3
327 # asm 1: vpand <b10=reg256#12,<a3=reg256#5,>r=reg256#4
328 # asm 2: vpand <b10=%ymm11,<a3=%ymm4,>r=%ymm3
329 vpand %ymm11,%ymm4,%ymm3
330
331 # qhasm: r13 ^= r
332 # asm 1: vpxor <r=reg256#4,<r13=reg256#8,<r13=reg256#8
333 # asm 2: vpxor <r=%ymm3,<r13=%ymm7,<r13=%ymm7
334 vpxor %ymm3,%ymm7,%ymm7
335
336 # qhasm: r = b10 & a2
337 # asm 1: vpand <b10=reg256#12,<a2=reg256#7,>r=reg256#4
338 # asm 2: vpand <b10=%ymm11,<a2=%ymm6,>r=%ymm3
339 vpand %ymm11,%ymm6,%ymm3
340
341 # qhasm: r12 ^= r
342 # asm 1: vpxor <r=reg256#4,<r12=reg256#10,<r12=reg256#10
343 # asm 2: vpxor <r=%ymm3,<r12=%ymm9,<r12=%ymm9
344 vpxor %ymm3,%ymm9,%ymm9
345
346 # qhasm: r = b10 & a1
347 # asm 1: vpand <b10=reg256#12,<a1=reg256#9,>r=reg256#4
348 # asm 2: vpand <b10=%ymm11,<a1=%ymm8,>r=%ymm3
349 vpand %ymm11,%ymm8,%ymm3
350
351 # qhasm: r11 ^= r
352 # asm 1: vpxor <r=reg256#4,<r11=reg256#1,<r11=reg256#1
353 # asm 2: vpxor <r=%ymm3,<r11=%ymm0,<r11=%ymm0
354 vpxor %ymm3,%ymm0,%ymm0
355
356 # qhasm: r10 = b10 & a0
357 # asm 1: vpand <b10=reg256#12,<a0=reg256#11,>r10=reg256#4
358 # asm 2: vpand <b10=%ymm11,<a0=%ymm10,>r10=%ymm3
359 vpand %ymm11,%ymm10,%ymm3
360
361 # qhasm: b9 = mem128[ input_2 + 144 ] x2
362 # asm 1: vbroadcasti128 144(<input_2=int64#3), >b9=reg256#12
363 # asm 2: vbroadcasti128 144(<input_2=%rdx), >b9=%ymm11
364 vbroadcasti128 144(%rdx), %ymm11
365
366 # qhasm: r = b9 & a5
367 # asm 1: vpand <b9=reg256#12,<a5=reg256#2,>r=reg256#13
368 # asm 2: vpand <b9=%ymm11,<a5=%ymm1,>r=%ymm12
369 vpand %ymm11,%ymm1,%ymm12
370
371 # qhasm: r14 ^= r
372 # asm 1: vpxor <r=reg256#13,<r14=reg256#6,<r14=reg256#6
373 # asm 2: vpxor <r=%ymm12,<r14=%ymm5,<r14=%ymm5
374 vpxor %ymm12,%ymm5,%ymm5
375
376 # qhasm: mem256[ ptr + 448 ] = r14
377 # asm 1: vmovupd <r14=reg256#6,448(<ptr=int64#4)
378 # asm 2: vmovupd <r14=%ymm5,448(<ptr=%rcx)
379 vmovupd %ymm5,448(%rcx)
380
381 # qhasm: r = b9 & a4
382 # asm 1: vpand <b9=reg256#12,<a4=reg256#3,>r=reg256#6
383 # asm 2: vpand <b9=%ymm11,<a4=%ymm2,>r=%ymm5
384 vpand %ymm11,%ymm2,%ymm5
385
386 # qhasm: r13 ^= r
387 # asm 1: vpxor <r=reg256#6,<r13=reg256#8,<r13=reg256#8
388 # asm 2: vpxor <r=%ymm5,<r13=%ymm7,<r13=%ymm7
389 vpxor %ymm5,%ymm7,%ymm7
390
391 # qhasm: r = b9 & a3
392 # asm 1: vpand <b9=reg256#12,<a3=reg256#5,>r=reg256#6
393 # asm 2: vpand <b9=%ymm11,<a3=%ymm4,>r=%ymm5
394 vpand %ymm11,%ymm4,%ymm5
395
396 # qhasm: r12 ^= r
397 # asm 1: vpxor <r=reg256#6,<r12=reg256#10,<r12=reg256#10
398 # asm 2: vpxor <r=%ymm5,<r12=%ymm9,<r12=%ymm9
399 vpxor %ymm5,%ymm9,%ymm9
400
401 # qhasm: r = b9 & a2
402 # asm 1: vpand <b9=reg256#12,<a2=reg256#7,>r=reg256#6
403 # asm 2: vpand <b9=%ymm11,<a2=%ymm6,>r=%ymm5
404 vpand %ymm11,%ymm6,%ymm5
405
406 # qhasm: r11 ^= r
407 # asm 1: vpxor <r=reg256#6,<r11=reg256#1,<r11=reg256#1
408 # asm 2: vpxor <r=%ymm5,<r11=%ymm0,<r11=%ymm0
409 vpxor %ymm5,%ymm0,%ymm0
410
411 # qhasm: r = b9 & a1
412 # asm 1: vpand <b9=reg256#12,<a1=reg256#9,>r=reg256#6
413 # asm 2: vpand <b9=%ymm11,<a1=%ymm8,>r=%ymm5
414 vpand %ymm11,%ymm8,%ymm5
415
416 # qhasm: r10 ^= r
417 # asm 1: vpxor <r=reg256#6,<r10=reg256#4,<r10=reg256#4
418 # asm 2: vpxor <r=%ymm5,<r10=%ymm3,<r10=%ymm3
419 vpxor %ymm5,%ymm3,%ymm3
420
421 # qhasm: r9 = b9 & a0
422 # asm 1: vpand <b9=reg256#12,<a0=reg256#11,>r9=reg256#6
423 # asm 2: vpand <b9=%ymm11,<a0=%ymm10,>r9=%ymm5
424 vpand %ymm11,%ymm10,%ymm5
425
426 # qhasm: b8 = mem128[ input_2 + 128 ] x2
427 # asm 1: vbroadcasti128 128(<input_2=int64#3), >b8=reg256#12
428 # asm 2: vbroadcasti128 128(<input_2=%rdx), >b8=%ymm11
429 vbroadcasti128 128(%rdx), %ymm11
430
431 # qhasm: r = b8 & a5
432 # asm 1: vpand <b8=reg256#12,<a5=reg256#2,>r=reg256#13
433 # asm 2: vpand <b8=%ymm11,<a5=%ymm1,>r=%ymm12
434 vpand %ymm11,%ymm1,%ymm12
435
436 # qhasm: r13 ^= r
437 # asm 1: vpxor <r=reg256#13,<r13=reg256#8,<r13=reg256#8
438 # asm 2: vpxor <r=%ymm12,<r13=%ymm7,<r13=%ymm7
439 vpxor %ymm12,%ymm7,%ymm7
440
441 # qhasm: mem256[ ptr + 416 ] = r13
442 # asm 1: vmovupd <r13=reg256#8,416(<ptr=int64#4)
443 # asm 2: vmovupd <r13=%ymm7,416(<ptr=%rcx)
444 vmovupd %ymm7,416(%rcx)
445
446 # qhasm: r = b8 & a4
447 # asm 1: vpand <b8=reg256#12,<a4=reg256#3,>r=reg256#8
448 # asm 2: vpand <b8=%ymm11,<a4=%ymm2,>r=%ymm7
449 vpand %ymm11,%ymm2,%ymm7
450
451 # qhasm: r12 ^= r
452 # asm 1: vpxor <r=reg256#8,<r12=reg256#10,<r12=reg256#10
453 # asm 2: vpxor <r=%ymm7,<r12=%ymm9,<r12=%ymm9
454 vpxor %ymm7,%ymm9,%ymm9
455
456 # qhasm: r = b8 & a3
457 # asm 1: vpand <b8=reg256#12,<a3=reg256#5,>r=reg256#8
458 # asm 2: vpand <b8=%ymm11,<a3=%ymm4,>r=%ymm7
459 vpand %ymm11,%ymm4,%ymm7
460
461 # qhasm: r11 ^= r
462 # asm 1: vpxor <r=reg256#8,<r11=reg256#1,<r11=reg256#1
463 # asm 2: vpxor <r=%ymm7,<r11=%ymm0,<r11=%ymm0
464 vpxor %ymm7,%ymm0,%ymm0
465
466 # qhasm: r = b8 & a2
467 # asm 1: vpand <b8=reg256#12,<a2=reg256#7,>r=reg256#8
468 # asm 2: vpand <b8=%ymm11,<a2=%ymm6,>r=%ymm7
469 vpand %ymm11,%ymm6,%ymm7
470
471 # qhasm: r10 ^= r
472 # asm 1: vpxor <r=reg256#8,<r10=reg256#4,<r10=reg256#4
473 # asm 2: vpxor <r=%ymm7,<r10=%ymm3,<r10=%ymm3
474 vpxor %ymm7,%ymm3,%ymm3
475
476 # qhasm: r = b8 & a1
477 # asm 1: vpand <b8=reg256#12,<a1=reg256#9,>r=reg256#8
478 # asm 2: vpand <b8=%ymm11,<a1=%ymm8,>r=%ymm7
479 vpand %ymm11,%ymm8,%ymm7
480
481 # qhasm: r9 ^= r
482 # asm 1: vpxor <r=reg256#8,<r9=reg256#6,<r9=reg256#6
483 # asm 2: vpxor <r=%ymm7,<r9=%ymm5,<r9=%ymm5
484 vpxor %ymm7,%ymm5,%ymm5
485
486 # qhasm: r8 = b8 & a0
487 # asm 1: vpand <b8=reg256#12,<a0=reg256#11,>r8=reg256#8
488 # asm 2: vpand <b8=%ymm11,<a0=%ymm10,>r8=%ymm7
489 vpand %ymm11,%ymm10,%ymm7
490
491 # qhasm: b7 = mem128[ input_2 + 112 ] x2
492 # asm 1: vbroadcasti128 112(<input_2=int64#3), >b7=reg256#12
493 # asm 2: vbroadcasti128 112(<input_2=%rdx), >b7=%ymm11
494 vbroadcasti128 112(%rdx), %ymm11
495
496 # qhasm: r = b7 & a5
497 # asm 1: vpand <b7=reg256#12,<a5=reg256#2,>r=reg256#13
498 # asm 2: vpand <b7=%ymm11,<a5=%ymm1,>r=%ymm12
499 vpand %ymm11,%ymm1,%ymm12
500
501 # qhasm: r12 ^= r
502 # asm 1: vpxor <r=reg256#13,<r12=reg256#10,<r12=reg256#10
503 # asm 2: vpxor <r=%ymm12,<r12=%ymm9,<r12=%ymm9
504 vpxor %ymm12,%ymm9,%ymm9
505
506 # qhasm: mem256[ ptr + 384 ] = r12
507 # asm 1: vmovupd <r12=reg256#10,384(<ptr=int64#4)
508 # asm 2: vmovupd <r12=%ymm9,384(<ptr=%rcx)
509 vmovupd %ymm9,384(%rcx)
510
511 # qhasm: r = b7 & a4
512 # asm 1: vpand <b7=reg256#12,<a4=reg256#3,>r=reg256#10
513 # asm 2: vpand <b7=%ymm11,<a4=%ymm2,>r=%ymm9
514 vpand %ymm11,%ymm2,%ymm9
515
516 # qhasm: r11 ^= r
517 # asm 1: vpxor <r=reg256#10,<r11=reg256#1,<r11=reg256#1
518 # asm 2: vpxor <r=%ymm9,<r11=%ymm0,<r11=%ymm0
519 vpxor %ymm9,%ymm0,%ymm0
520
521 # qhasm: r = b7 & a3
522 # asm 1: vpand <b7=reg256#12,<a3=reg256#5,>r=reg256#10
523 # asm 2: vpand <b7=%ymm11,<a3=%ymm4,>r=%ymm9
524 vpand %ymm11,%ymm4,%ymm9
525
526 # qhasm: r10 ^= r
527 # asm 1: vpxor <r=reg256#10,<r10=reg256#4,<r10=reg256#4
528 # asm 2: vpxor <r=%ymm9,<r10=%ymm3,<r10=%ymm3
529 vpxor %ymm9,%ymm3,%ymm3
530
531 # qhasm: r = b7 & a2
532 # asm 1: vpand <b7=reg256#12,<a2=reg256#7,>r=reg256#10
533 # asm 2: vpand <b7=%ymm11,<a2=%ymm6,>r=%ymm9
534 vpand %ymm11,%ymm6,%ymm9
535
536 # qhasm: r9 ^= r
537 # asm 1: vpxor <r=reg256#10,<r9=reg256#6,<r9=reg256#6
538 # asm 2: vpxor <r=%ymm9,<r9=%ymm5,<r9=%ymm5
539 vpxor %ymm9,%ymm5,%ymm5
540
541 # qhasm: r = b7 & a1
542 # asm 1: vpand <b7=reg256#12,<a1=reg256#9,>r=reg256#10
543 # asm 2: vpand <b7=%ymm11,<a1=%ymm8,>r=%ymm9
544 vpand %ymm11,%ymm8,%ymm9
545
546 # qhasm: r8 ^= r
547 # asm 1: vpxor <r=reg256#10,<r8=reg256#8,<r8=reg256#8
548 # asm 2: vpxor <r=%ymm9,<r8=%ymm7,<r8=%ymm7
549 vpxor %ymm9,%ymm7,%ymm7
550
551 # qhasm: r7 = b7 & a0
552 # asm 1: vpand <b7=reg256#12,<a0=reg256#11,>r7=reg256#10
553 # asm 2: vpand <b7=%ymm11,<a0=%ymm10,>r7=%ymm9
554 vpand %ymm11,%ymm10,%ymm9
555
556 # qhasm: b6 = mem128[ input_2 + 96 ] x2
557 # asm 1: vbroadcasti128 96(<input_2=int64#3), >b6=reg256#12
558 # asm 2: vbroadcasti128 96(<input_2=%rdx), >b6=%ymm11
559 vbroadcasti128 96(%rdx), %ymm11
560
561 # qhasm: r = b6 & a5
562 # asm 1: vpand <b6=reg256#12,<a5=reg256#2,>r=reg256#13
563 # asm 2: vpand <b6=%ymm11,<a5=%ymm1,>r=%ymm12
564 vpand %ymm11,%ymm1,%ymm12
565
566 # qhasm: r11 ^= r
567 # asm 1: vpxor <r=reg256#13,<r11=reg256#1,<r11=reg256#1
568 # asm 2: vpxor <r=%ymm12,<r11=%ymm0,<r11=%ymm0
569 vpxor %ymm12,%ymm0,%ymm0
570
571 # qhasm: mem256[ ptr + 352 ] = r11
572 # asm 1: vmovupd <r11=reg256#1,352(<ptr=int64#4)
573 # asm 2: vmovupd <r11=%ymm0,352(<ptr=%rcx)
574 vmovupd %ymm0,352(%rcx)
575
576 # qhasm: r = b6 & a4
577 # asm 1: vpand <b6=reg256#12,<a4=reg256#3,>r=reg256#1
578 # asm 2: vpand <b6=%ymm11,<a4=%ymm2,>r=%ymm0
579 vpand %ymm11,%ymm2,%ymm0
580
581 # qhasm: r10 ^= r
582 # asm 1: vpxor <r=reg256#1,<r10=reg256#4,<r10=reg256#4
583 # asm 2: vpxor <r=%ymm0,<r10=%ymm3,<r10=%ymm3
584 vpxor %ymm0,%ymm3,%ymm3
585
586 # qhasm: r = b6 & a3
587 # asm 1: vpand <b6=reg256#12,<a3=reg256#5,>r=reg256#1
588 # asm 2: vpand <b6=%ymm11,<a3=%ymm4,>r=%ymm0
589 vpand %ymm11,%ymm4,%ymm0
590
591 # qhasm: r9 ^= r
592 # asm 1: vpxor <r=reg256#1,<r9=reg256#6,<r9=reg256#6
593 # asm 2: vpxor <r=%ymm0,<r9=%ymm5,<r9=%ymm5
594 vpxor %ymm0,%ymm5,%ymm5
595
596 # qhasm: r = b6 & a2
597 # asm 1: vpand <b6=reg256#12,<a2=reg256#7,>r=reg256#1
598 # asm 2: vpand <b6=%ymm11,<a2=%ymm6,>r=%ymm0
599 vpand %ymm11,%ymm6,%ymm0
600
601 # qhasm: r8 ^= r
602 # asm 1: vpxor <r=reg256#1,<r8=reg256#8,<r8=reg256#8
603 # asm 2: vpxor <r=%ymm0,<r8=%ymm7,<r8=%ymm7
604 vpxor %ymm0,%ymm7,%ymm7
605
606 # qhasm: r = b6 & a1
607 # asm 1: vpand <b6=reg256#12,<a1=reg256#9,>r=reg256#1
608 # asm 2: vpand <b6=%ymm11,<a1=%ymm8,>r=%ymm0
609 vpand %ymm11,%ymm8,%ymm0
610
611 # qhasm: r7 ^= r
612 # asm 1: vpxor <r=reg256#1,<r7=reg256#10,<r7=reg256#10
613 # asm 2: vpxor <r=%ymm0,<r7=%ymm9,<r7=%ymm9
614 vpxor %ymm0,%ymm9,%ymm9
615
616 # qhasm: r6 = b6 & a0
617 # asm 1: vpand <b6=reg256#12,<a0=reg256#11,>r6=reg256#1
618 # asm 2: vpand <b6=%ymm11,<a0=%ymm10,>r6=%ymm0
619 vpand %ymm11,%ymm10,%ymm0
620
621 # qhasm: b5 = mem128[ input_2 + 80 ] x2
622 # asm 1: vbroadcasti128 80(<input_2=int64#3), >b5=reg256#12
623 # asm 2: vbroadcasti128 80(<input_2=%rdx), >b5=%ymm11
624 vbroadcasti128 80(%rdx), %ymm11
625
626 # qhasm: r = b5 & a5
627 # asm 1: vpand <b5=reg256#12,<a5=reg256#2,>r=reg256#13
628 # asm 2: vpand <b5=%ymm11,<a5=%ymm1,>r=%ymm12
629 vpand %ymm11,%ymm1,%ymm12
630
631 # qhasm: r10 ^= r
632 # asm 1: vpxor <r=reg256#13,<r10=reg256#4,<r10=reg256#4
633 # asm 2: vpxor <r=%ymm12,<r10=%ymm3,<r10=%ymm3
634 vpxor %ymm12,%ymm3,%ymm3
635
636 # qhasm: mem256[ ptr + 320 ] = r10
637 # asm 1: vmovupd <r10=reg256#4,320(<ptr=int64#4)
638 # asm 2: vmovupd <r10=%ymm3,320(<ptr=%rcx)
639 vmovupd %ymm3,320(%rcx)
640
641 # qhasm: r = b5 & a4
642 # asm 1: vpand <b5=reg256#12,<a4=reg256#3,>r=reg256#4
643 # asm 2: vpand <b5=%ymm11,<a4=%ymm2,>r=%ymm3
644 vpand %ymm11,%ymm2,%ymm3
645
646 # qhasm: r9 ^= r
647 # asm 1: vpxor <r=reg256#4,<r9=reg256#6,<r9=reg256#6
648 # asm 2: vpxor <r=%ymm3,<r9=%ymm5,<r9=%ymm5
649 vpxor %ymm3,%ymm5,%ymm5
650
651 # qhasm: r = b5 & a3
652 # asm 1: vpand <b5=reg256#12,<a3=reg256#5,>r=reg256#4
653 # asm 2: vpand <b5=%ymm11,<a3=%ymm4,>r=%ymm3
654 vpand %ymm11,%ymm4,%ymm3
655
656 # qhasm: r8 ^= r
657 # asm 1: vpxor <r=reg256#4,<r8=reg256#8,<r8=reg256#8
658 # asm 2: vpxor <r=%ymm3,<r8=%ymm7,<r8=%ymm7
659 vpxor %ymm3,%ymm7,%ymm7
660
661 # qhasm: r = b5 & a2
662 # asm 1: vpand <b5=reg256#12,<a2=reg256#7,>r=reg256#4
663 # asm 2: vpand <b5=%ymm11,<a2=%ymm6,>r=%ymm3
664 vpand %ymm11,%ymm6,%ymm3
665
666 # qhasm: r7 ^= r
667 # asm 1: vpxor <r=reg256#4,<r7=reg256#10,<r7=reg256#10
668 # asm 2: vpxor <r=%ymm3,<r7=%ymm9,<r7=%ymm9
669 vpxor %ymm3,%ymm9,%ymm9
670
671 # qhasm: r = b5 & a1
672 # asm 1: vpand <b5=reg256#12,<a1=reg256#9,>r=reg256#4
673 # asm 2: vpand <b5=%ymm11,<a1=%ymm8,>r=%ymm3
674 vpand %ymm11,%ymm8,%ymm3
675
676 # qhasm: r6 ^= r
677 # asm 1: vpxor <r=reg256#4,<r6=reg256#1,<r6=reg256#1
678 # asm 2: vpxor <r=%ymm3,<r6=%ymm0,<r6=%ymm0
679 vpxor %ymm3,%ymm0,%ymm0
680
681 # qhasm: r5 = b5 & a0
682 # asm 1: vpand <b5=reg256#12,<a0=reg256#11,>r5=reg256#4
683 # asm 2: vpand <b5=%ymm11,<a0=%ymm10,>r5=%ymm3
684 vpand %ymm11,%ymm10,%ymm3
685
686 # qhasm: b4 = mem128[ input_2 + 64 ] x2
687 # asm 1: vbroadcasti128 64(<input_2=int64#3), >b4=reg256#12
688 # asm 2: vbroadcasti128 64(<input_2=%rdx), >b4=%ymm11
689 vbroadcasti128 64(%rdx), %ymm11
690
691 # qhasm: r = b4 & a5
692 # asm 1: vpand <b4=reg256#12,<a5=reg256#2,>r=reg256#13
693 # asm 2: vpand <b4=%ymm11,<a5=%ymm1,>r=%ymm12
694 vpand %ymm11,%ymm1,%ymm12
695
696 # qhasm: r9 ^= r
697 # asm 1: vpxor <r=reg256#13,<r9=reg256#6,<r9=reg256#6
698 # asm 2: vpxor <r=%ymm12,<r9=%ymm5,<r9=%ymm5
699 vpxor %ymm12,%ymm5,%ymm5
700
701 # qhasm: mem256[ ptr + 288 ] = r9
702 # asm 1: vmovupd <r9=reg256#6,288(<ptr=int64#4)
703 # asm 2: vmovupd <r9=%ymm5,288(<ptr=%rcx)
704 vmovupd %ymm5,288(%rcx)
705
706 # qhasm: r = b4 & a4
707 # asm 1: vpand <b4=reg256#12,<a4=reg256#3,>r=reg256#6
708 # asm 2: vpand <b4=%ymm11,<a4=%ymm2,>r=%ymm5
709 vpand %ymm11,%ymm2,%ymm5
710
711 # qhasm: r8 ^= r
712 # asm 1: vpxor <r=reg256#6,<r8=reg256#8,<r8=reg256#8
713 # asm 2: vpxor <r=%ymm5,<r8=%ymm7,<r8=%ymm7
714 vpxor %ymm5,%ymm7,%ymm7
715
716 # qhasm: r = b4 & a3
717 # asm 1: vpand <b4=reg256#12,<a3=reg256#5,>r=reg256#6
718 # asm 2: vpand <b4=%ymm11,<a3=%ymm4,>r=%ymm5
719 vpand %ymm11,%ymm4,%ymm5
720
721 # qhasm: r7 ^= r
722 # asm 1: vpxor <r=reg256#6,<r7=reg256#10,<r7=reg256#10
723 # asm 2: vpxor <r=%ymm5,<r7=%ymm9,<r7=%ymm9
724 vpxor %ymm5,%ymm9,%ymm9
725
726 # qhasm: r = b4 & a2
727 # asm 1: vpand <b4=reg256#12,<a2=reg256#7,>r=reg256#6
728 # asm 2: vpand <b4=%ymm11,<a2=%ymm6,>r=%ymm5
729 vpand %ymm11,%ymm6,%ymm5
730
731 # qhasm: r6 ^= r
732 # asm 1: vpxor <r=reg256#6,<r6=reg256#1,<r6=reg256#1
733 # asm 2: vpxor <r=%ymm5,<r6=%ymm0,<r6=%ymm0
734 vpxor %ymm5,%ymm0,%ymm0
735
736 # qhasm: r = b4 & a1
737 # asm 1: vpand <b4=reg256#12,<a1=reg256#9,>r=reg256#6
738 # asm 2: vpand <b4=%ymm11,<a1=%ymm8,>r=%ymm5
739 vpand %ymm11,%ymm8,%ymm5
740
741 # qhasm: r5 ^= r
742 # asm 1: vpxor <r=reg256#6,<r5=reg256#4,<r5=reg256#4
743 # asm 2: vpxor <r=%ymm5,<r5=%ymm3,<r5=%ymm3
744 vpxor %ymm5,%ymm3,%ymm3
745
746 # qhasm: r4 = b4 & a0
747 # asm 1: vpand <b4=reg256#12,<a0=reg256#11,>r4=reg256#6
748 # asm 2: vpand <b4=%ymm11,<a0=%ymm10,>r4=%ymm5
749 vpand %ymm11,%ymm10,%ymm5
750
751 # qhasm: b3 = mem128[ input_2 + 48 ] x2
752 # asm 1: vbroadcasti128 48(<input_2=int64#3), >b3=reg256#12
753 # asm 2: vbroadcasti128 48(<input_2=%rdx), >b3=%ymm11
754 vbroadcasti128 48(%rdx), %ymm11
755
756 # qhasm: r = b3 & a5
757 # asm 1: vpand <b3=reg256#12,<a5=reg256#2,>r=reg256#13
758 # asm 2: vpand <b3=%ymm11,<a5=%ymm1,>r=%ymm12
759 vpand %ymm11,%ymm1,%ymm12
760
761 # qhasm: r8 ^= r
762 # asm 1: vpxor <r=reg256#13,<r8=reg256#8,<r8=reg256#8
763 # asm 2: vpxor <r=%ymm12,<r8=%ymm7,<r8=%ymm7
764 vpxor %ymm12,%ymm7,%ymm7
765
766 # qhasm: mem256[ ptr + 256 ] = r8
767 # asm 1: vmovupd <r8=reg256#8,256(<ptr=int64#4)
768 # asm 2: vmovupd <r8=%ymm7,256(<ptr=%rcx)
769 vmovupd %ymm7,256(%rcx)
770
771 # qhasm: r = b3 & a4
772 # asm 1: vpand <b3=reg256#12,<a4=reg256#3,>r=reg256#8
773 # asm 2: vpand <b3=%ymm11,<a4=%ymm2,>r=%ymm7
774 vpand %ymm11,%ymm2,%ymm7
775
776 # qhasm: r7 ^= r
777 # asm 1: vpxor <r=reg256#8,<r7=reg256#10,<r7=reg256#10
778 # asm 2: vpxor <r=%ymm7,<r7=%ymm9,<r7=%ymm9
779 vpxor %ymm7,%ymm9,%ymm9
780
781 # qhasm: r = b3 & a3
782 # asm 1: vpand <b3=reg256#12,<a3=reg256#5,>r=reg256#8
783 # asm 2: vpand <b3=%ymm11,<a3=%ymm4,>r=%ymm7
784 vpand %ymm11,%ymm4,%ymm7
785
786 # qhasm: r6 ^= r
787 # asm 1: vpxor <r=reg256#8,<r6=reg256#1,<r6=reg256#1
788 # asm 2: vpxor <r=%ymm7,<r6=%ymm0,<r6=%ymm0
789 vpxor %ymm7,%ymm0,%ymm0
790
791 # qhasm: r = b3 & a2
792 # asm 1: vpand <b3=reg256#12,<a2=reg256#7,>r=reg256#8
793 # asm 2: vpand <b3=%ymm11,<a2=%ymm6,>r=%ymm7
794 vpand %ymm11,%ymm6,%ymm7
795
796 # qhasm: r5 ^= r
797 # asm 1: vpxor <r=reg256#8,<r5=reg256#4,<r5=reg256#4
798 # asm 2: vpxor <r=%ymm7,<r5=%ymm3,<r5=%ymm3
799 vpxor %ymm7,%ymm3,%ymm3
800
801 # qhasm: r = b3 & a1
802 # asm 1: vpand <b3=reg256#12,<a1=reg256#9,>r=reg256#8
803 # asm 2: vpand <b3=%ymm11,<a1=%ymm8,>r=%ymm7
804 vpand %ymm11,%ymm8,%ymm7
805
806 # qhasm: r4 ^= r
807 # asm 1: vpxor <r=reg256#8,<r4=reg256#6,<r4=reg256#6
808 # asm 2: vpxor <r=%ymm7,<r4=%ymm5,<r4=%ymm5
809 vpxor %ymm7,%ymm5,%ymm5
810
811 # qhasm: r3 = b3 & a0
812 # asm 1: vpand <b3=reg256#12,<a0=reg256#11,>r3=reg256#8
813 # asm 2: vpand <b3=%ymm11,<a0=%ymm10,>r3=%ymm7
814 vpand %ymm11,%ymm10,%ymm7
815
816 # qhasm: b2 = mem128[ input_2 + 32 ] x2
817 # asm 1: vbroadcasti128 32(<input_2=int64#3), >b2=reg256#12
818 # asm 2: vbroadcasti128 32(<input_2=%rdx), >b2=%ymm11
819 vbroadcasti128 32(%rdx), %ymm11
820
821 # qhasm: r = b2 & a5
822 # asm 1: vpand <b2=reg256#12,<a5=reg256#2,>r=reg256#13
823 # asm 2: vpand <b2=%ymm11,<a5=%ymm1,>r=%ymm12
824 vpand %ymm11,%ymm1,%ymm12
825
826 # qhasm: r7 ^= r
827 # asm 1: vpxor <r=reg256#13,<r7=reg256#10,<r7=reg256#10
828 # asm 2: vpxor <r=%ymm12,<r7=%ymm9,<r7=%ymm9
829 vpxor %ymm12,%ymm9,%ymm9
830
831 # qhasm: mem256[ ptr + 224 ] = r7
832 # asm 1: vmovupd <r7=reg256#10,224(<ptr=int64#4)
833 # asm 2: vmovupd <r7=%ymm9,224(<ptr=%rcx)
834 vmovupd %ymm9,224(%rcx)
835
836 # qhasm: r = b2 & a4
837 # asm 1: vpand <b2=reg256#12,<a4=reg256#3,>r=reg256#10
838 # asm 2: vpand <b2=%ymm11,<a4=%ymm2,>r=%ymm9
839 vpand %ymm11,%ymm2,%ymm9
840
841 # qhasm: r6 ^= r
842 # asm 1: vpxor <r=reg256#10,<r6=reg256#1,<r6=reg256#1
843 # asm 2: vpxor <r=%ymm9,<r6=%ymm0,<r6=%ymm0
844 vpxor %ymm9,%ymm0,%ymm0
845
846 # qhasm: r = b2 & a3
847 # asm 1: vpand <b2=reg256#12,<a3=reg256#5,>r=reg256#10
848 # asm 2: vpand <b2=%ymm11,<a3=%ymm4,>r=%ymm9
849 vpand %ymm11,%ymm4,%ymm9
850
851 # qhasm: r5 ^= r
852 # asm 1: vpxor <r=reg256#10,<r5=reg256#4,<r5=reg256#4
853 # asm 2: vpxor <r=%ymm9,<r5=%ymm3,<r5=%ymm3
854 vpxor %ymm9,%ymm3,%ymm3
855
856 # qhasm: r = b2 & a2
857 # asm 1: vpand <b2=reg256#12,<a2=reg256#7,>r=reg256#10
858 # asm 2: vpand <b2=%ymm11,<a2=%ymm6,>r=%ymm9
859 vpand %ymm11,%ymm6,%ymm9
860
861 # qhasm: r4 ^= r
862 # asm 1: vpxor <r=reg256#10,<r4=reg256#6,<r4=reg256#6
863 # asm 2: vpxor <r=%ymm9,<r4=%ymm5,<r4=%ymm5
864 vpxor %ymm9,%ymm5,%ymm5
865
866 # qhasm: r = b2 & a1
867 # asm 1: vpand <b2=reg256#12,<a1=reg256#9,>r=reg256#10
868 # asm 2: vpand <b2=%ymm11,<a1=%ymm8,>r=%ymm9
869 vpand %ymm11,%ymm8,%ymm9
870
871 # qhasm: r3 ^= r
872 # asm 1: vpxor <r=reg256#10,<r3=reg256#8,<r3=reg256#8
873 # asm 2: vpxor <r=%ymm9,<r3=%ymm7,<r3=%ymm7
874 vpxor %ymm9,%ymm7,%ymm7
875
876 # qhasm: r2 = b2 & a0
877 # asm 1: vpand <b2=reg256#12,<a0=reg256#11,>r2=reg256#10
878 # asm 2: vpand <b2=%ymm11,<a0=%ymm10,>r2=%ymm9
879 vpand %ymm11,%ymm10,%ymm9
880
881 # qhasm: b1 = mem128[ input_2 + 16 ] x2
882 # asm 1: vbroadcasti128 16(<input_2=int64#3), >b1=reg256#12
883 # asm 2: vbroadcasti128 16(<input_2=%rdx), >b1=%ymm11
884 vbroadcasti128 16(%rdx), %ymm11
885
886 # qhasm: r = b1 & a5
887 # asm 1: vpand <b1=reg256#12,<a5=reg256#2,>r=reg256#13
888 # asm 2: vpand <b1=%ymm11,<a5=%ymm1,>r=%ymm12
889 vpand %ymm11,%ymm1,%ymm12
890
891 # qhasm: r6 ^= r
892 # asm 1: vpxor <r=reg256#13,<r6=reg256#1,<r6=reg256#1
893 # asm 2: vpxor <r=%ymm12,<r6=%ymm0,<r6=%ymm0
894 vpxor %ymm12,%ymm0,%ymm0
895
896 # qhasm: mem256[ ptr + 192 ] = r6
897 # asm 1: vmovupd <r6=reg256#1,192(<ptr=int64#4)
898 # asm 2: vmovupd <r6=%ymm0,192(<ptr=%rcx)
899 vmovupd %ymm0,192(%rcx)
900
901 # qhasm: r = b1 & a4
902 # asm 1: vpand <b1=reg256#12,<a4=reg256#3,>r=reg256#1
903 # asm 2: vpand <b1=%ymm11,<a4=%ymm2,>r=%ymm0
904 vpand %ymm11,%ymm2,%ymm0
905
906 # qhasm: r5 ^= r
907 # asm 1: vpxor <r=reg256#1,<r5=reg256#4,<r5=reg256#4
908 # asm 2: vpxor <r=%ymm0,<r5=%ymm3,<r5=%ymm3
909 vpxor %ymm0,%ymm3,%ymm3
910
911 # qhasm: r = b1 & a3
912 # asm 1: vpand <b1=reg256#12,<a3=reg256#5,>r=reg256#1
913 # asm 2: vpand <b1=%ymm11,<a3=%ymm4,>r=%ymm0
914 vpand %ymm11,%ymm4,%ymm0
915
916 # qhasm: r4 ^= r
917 # asm 1: vpxor <r=reg256#1,<r4=reg256#6,<r4=reg256#6
918 # asm 2: vpxor <r=%ymm0,<r4=%ymm5,<r4=%ymm5
919 vpxor %ymm0,%ymm5,%ymm5
920
921 # qhasm: r = b1 & a2
922 # asm 1: vpand <b1=reg256#12,<a2=reg256#7,>r=reg256#1
923 # asm 2: vpand <b1=%ymm11,<a2=%ymm6,>r=%ymm0
924 vpand %ymm11,%ymm6,%ymm0
925
926 # qhasm: r3 ^= r
927 # asm 1: vpxor <r=reg256#1,<r3=reg256#8,<r3=reg256#8
928 # asm 2: vpxor <r=%ymm0,<r3=%ymm7,<r3=%ymm7
929 vpxor %ymm0,%ymm7,%ymm7
930
931 # qhasm: r = b1 & a1
932 # asm 1: vpand <b1=reg256#12,<a1=reg256#9,>r=reg256#1
933 # asm 2: vpand <b1=%ymm11,<a1=%ymm8,>r=%ymm0
934 vpand %ymm11,%ymm8,%ymm0
935
936 # qhasm: r2 ^= r
937 # asm 1: vpxor <r=reg256#1,<r2=reg256#10,<r2=reg256#10
938 # asm 2: vpxor <r=%ymm0,<r2=%ymm9,<r2=%ymm9
939 vpxor %ymm0,%ymm9,%ymm9
940
941 # qhasm: r1 = b1 & a0
942 # asm 1: vpand <b1=reg256#12,<a0=reg256#11,>r1=reg256#1
943 # asm 2: vpand <b1=%ymm11,<a0=%ymm10,>r1=%ymm0
944 vpand %ymm11,%ymm10,%ymm0
945
946 # qhasm: b0 = mem128[ input_2 + 0 ] x2
947 # asm 1: vbroadcasti128 0(<input_2=int64#3), >b0=reg256#12
948 # asm 2: vbroadcasti128 0(<input_2=%rdx), >b0=%ymm11
949 vbroadcasti128 0(%rdx), %ymm11
950
951 # qhasm: r = b0 & a5
952 # asm 1: vpand <b0=reg256#12,<a5=reg256#2,>r=reg256#2
953 # asm 2: vpand <b0=%ymm11,<a5=%ymm1,>r=%ymm1
954 vpand %ymm11,%ymm1,%ymm1
955
956 # qhasm: r5 ^= r
957 # asm 1: vpxor <r=reg256#2,<r5=reg256#4,<r5=reg256#4
958 # asm 2: vpxor <r=%ymm1,<r5=%ymm3,<r5=%ymm3
959 vpxor %ymm1,%ymm3,%ymm3
960
961 # qhasm: mem256[ ptr + 160 ] = r5
962 # asm 1: vmovupd <r5=reg256#4,160(<ptr=int64#4)
963 # asm 2: vmovupd <r5=%ymm3,160(<ptr=%rcx)
964 vmovupd %ymm3,160(%rcx)
965
966 # qhasm: r = b0 & a4
967 # asm 1: vpand <b0=reg256#12,<a4=reg256#3,>r=reg256#2
968 # asm 2: vpand <b0=%ymm11,<a4=%ymm2,>r=%ymm1
969 vpand %ymm11,%ymm2,%ymm1
970
971 # qhasm: r4 ^= r
972 # asm 1: vpxor <r=reg256#2,<r4=reg256#6,<r4=reg256#6
973 # asm 2: vpxor <r=%ymm1,<r4=%ymm5,<r4=%ymm5
974 vpxor %ymm1,%ymm5,%ymm5
975
976 # qhasm: r = b0 & a3
977 # asm 1: vpand <b0=reg256#12,<a3=reg256#5,>r=reg256#2
978 # asm 2: vpand <b0=%ymm11,<a3=%ymm4,>r=%ymm1
979 vpand %ymm11,%ymm4,%ymm1
980
981 # qhasm: r3 ^= r
982 # asm 1: vpxor <r=reg256#2,<r3=reg256#8,<r3=reg256#8
983 # asm 2: vpxor <r=%ymm1,<r3=%ymm7,<r3=%ymm7
984 vpxor %ymm1,%ymm7,%ymm7
985
986 # qhasm: r = b0 & a2
987 # asm 1: vpand <b0=reg256#12,<a2=reg256#7,>r=reg256#2
988 # asm 2: vpand <b0=%ymm11,<a2=%ymm6,>r=%ymm1
989 vpand %ymm11,%ymm6,%ymm1
990
991 # qhasm: r2 ^= r
992 # asm 1: vpxor <r=reg256#2,<r2=reg256#10,<r2=reg256#10
993 # asm 2: vpxor <r=%ymm1,<r2=%ymm9,<r2=%ymm9
994 vpxor %ymm1,%ymm9,%ymm9
995
996 # qhasm: r = b0 & a1
997 # asm 1: vpand <b0=reg256#12,<a1=reg256#9,>r=reg256#2
998 # asm 2: vpand <b0=%ymm11,<a1=%ymm8,>r=%ymm1
999 vpand %ymm11,%ymm8,%ymm1
1000
1001 # qhasm: r1 ^= r
1002 # asm 1: vpxor <r=reg256#2,<r1=reg256#1,<r1=reg256#1
1003 # asm 2: vpxor <r=%ymm1,<r1=%ymm0,<r1=%ymm0
1004 vpxor %ymm1,%ymm0,%ymm0
1005
1006 # qhasm: r0 = b0 & a0
1007 # asm 1: vpand <b0=reg256#12,<a0=reg256#11,>r0=reg256#2
1008 # asm 2: vpand <b0=%ymm11,<a0=%ymm10,>r0=%ymm1
1009 vpand %ymm11,%ymm10,%ymm1
1010
1011 # qhasm: mem256[ ptr + 128 ] = r4
1012 # asm 1: vmovupd <r4=reg256#6,128(<ptr=int64#4)
1013 # asm 2: vmovupd <r4=%ymm5,128(<ptr=%rcx)
1014 vmovupd %ymm5,128(%rcx)
1015
1016 # qhasm: mem256[ ptr + 96 ] = r3
1017 # asm 1: vmovupd <r3=reg256#8,96(<ptr=int64#4)
1018 # asm 2: vmovupd <r3=%ymm7,96(<ptr=%rcx)
1019 vmovupd %ymm7,96(%rcx)
1020
1021 # qhasm: mem256[ ptr + 64 ] = r2
1022 # asm 1: vmovupd <r2=reg256#10,64(<ptr=int64#4)
1023 # asm 2: vmovupd <r2=%ymm9,64(<ptr=%rcx)
1024 vmovupd %ymm9,64(%rcx)
1025
1026 # qhasm: mem256[ ptr + 32 ] = r1
1027 # asm 1: vmovupd <r1=reg256#1,32(<ptr=int64#4)
1028 # asm 2: vmovupd <r1=%ymm0,32(<ptr=%rcx)
1029 vmovupd %ymm0,32(%rcx)
1030
1031 # qhasm: mem256[ ptr + 0 ] = r0
1032 # asm 1: vmovupd <r0=reg256#2,0(<ptr=int64#4)
1033 # asm 2: vmovupd <r0=%ymm1,0(<ptr=%rcx)
1034 vmovupd %ymm1,0(%rcx)
1035
1036 # qhasm: vzeroupper
1037 vzeroupper
1038
1039 # qhasm: h22 = mem128[ ptr + 528 ]
1040 # asm 1: movdqu 528(<ptr=int64#4),>h22=reg128#1
1041 # asm 2: movdqu 528(<ptr=%rcx),>h22=%xmm0
1042 movdqu 528(%rcx),%xmm0
1043
1044 # qhasm: h13 = h22
1045 # asm 1: movdqa <h22=reg128#1,>h13=reg128#2
1046 # asm 2: movdqa <h22=%xmm0,>h13=%xmm1
1047 movdqa %xmm0,%xmm1
1048
1049 # qhasm: h10 = h22
1050 # asm 1: movdqa <h22=reg128#1,>h10=reg128#1
1051 # asm 2: movdqa <h22=%xmm0,>h10=%xmm0
1052 movdqa %xmm0,%xmm0
1053
1054 # qhasm: h21 = mem128[ ptr + 496 ]
1055 # asm 1: movdqu 496(<ptr=int64#4),>h21=reg128#3
1056 # asm 2: movdqu 496(<ptr=%rcx),>h21=%xmm2
1057 movdqu 496(%rcx),%xmm2
1058
1059 # qhasm: h12 = h21
1060 # asm 1: movdqa <h21=reg128#3,>h12=reg128#4
1061 # asm 2: movdqa <h21=%xmm2,>h12=%xmm3
1062 movdqa %xmm2,%xmm3
1063
1064 # qhasm: h9 = h21
1065 # asm 1: movdqa <h21=reg128#3,>h9=reg128#3
1066 # asm 2: movdqa <h21=%xmm2,>h9=%xmm2
1067 movdqa %xmm2,%xmm2
1068
1069 # qhasm: h20 = mem128[ ptr + 464 ]
1070 # asm 1: movdqu 464(<ptr=int64#4),>h20=reg128#5
1071 # asm 2: movdqu 464(<ptr=%rcx),>h20=%xmm4
1072 movdqu 464(%rcx),%xmm4
1073
1074 # qhasm: h11 = h20
1075 # asm 1: movdqa <h20=reg128#5,>h11=reg128#6
1076 # asm 2: movdqa <h20=%xmm4,>h11=%xmm5
1077 movdqa %xmm4,%xmm5
1078
1079 # qhasm: h8 = h20
1080 # asm 1: movdqa <h20=reg128#5,>h8=reg128#5
1081 # asm 2: movdqa <h20=%xmm4,>h8=%xmm4
1082 movdqa %xmm4,%xmm4
1083
1084 # qhasm: h19 = mem128[ ptr + 432 ]
1085 # asm 1: movdqu 432(<ptr=int64#4),>h19=reg128#7
1086 # asm 2: movdqu 432(<ptr=%rcx),>h19=%xmm6
1087 movdqu 432(%rcx),%xmm6
1088
1089 # qhasm: h10 = h10 ^ h19
1090 # asm 1: vpxor <h19=reg128#7,<h10=reg128#1,>h10=reg128#1
1091 # asm 2: vpxor <h19=%xmm6,<h10=%xmm0,>h10=%xmm0
1092 vpxor %xmm6,%xmm0,%xmm0
1093
1094 # qhasm: h7 = h19
1095 # asm 1: movdqa <h19=reg128#7,>h7=reg128#7
1096 # asm 2: movdqa <h19=%xmm6,>h7=%xmm6
1097 movdqa %xmm6,%xmm6
1098
1099 # qhasm: h18 = mem128[ ptr + 400 ]
1100 # asm 1: movdqu 400(<ptr=int64#4),>h18=reg128#8
1101 # asm 2: movdqu 400(<ptr=%rcx),>h18=%xmm7
1102 movdqu 400(%rcx),%xmm7
1103
1104 # qhasm: h9 = h9 ^ h18
1105 # asm 1: vpxor <h18=reg128#8,<h9=reg128#3,>h9=reg128#3
1106 # asm 2: vpxor <h18=%xmm7,<h9=%xmm2,>h9=%xmm2
1107 vpxor %xmm7,%xmm2,%xmm2
1108
1109 # qhasm: h6 = h18
1110 # asm 1: movdqa <h18=reg128#8,>h6=reg128#8
1111 # asm 2: movdqa <h18=%xmm7,>h6=%xmm7
1112 movdqa %xmm7,%xmm7
1113
1114 # qhasm: h17 = mem128[ ptr + 368 ]
1115 # asm 1: movdqu 368(<ptr=int64#4),>h17=reg128#9
1116 # asm 2: movdqu 368(<ptr=%rcx),>h17=%xmm8
1117 movdqu 368(%rcx),%xmm8
1118
1119 # qhasm: h8 = h8 ^ h17
1120 # asm 1: vpxor <h17=reg128#9,<h8=reg128#5,>h8=reg128#5
1121 # asm 2: vpxor <h17=%xmm8,<h8=%xmm4,>h8=%xmm4
1122 vpxor %xmm8,%xmm4,%xmm4
1123
1124 # qhasm: h5 = h17
1125 # asm 1: movdqa <h17=reg128#9,>h5=reg128#9
1126 # asm 2: movdqa <h17=%xmm8,>h5=%xmm8
1127 movdqa %xmm8,%xmm8
1128
1129 # qhasm: h16 = mem128[ ptr + 336 ]
1130 # asm 1: movdqu 336(<ptr=int64#4),>h16=reg128#10
1131 # asm 2: movdqu 336(<ptr=%rcx),>h16=%xmm9
1132 movdqu 336(%rcx),%xmm9
1133
1134 # qhasm: h16 = h16 ^ mem128[ ptr + 512 ]
1135 # asm 1: vpxor 512(<ptr=int64#4),<h16=reg128#10,>h16=reg128#10
1136 # asm 2: vpxor 512(<ptr=%rcx),<h16=%xmm9,>h16=%xmm9
1137 vpxor 512(%rcx),%xmm9,%xmm9
1138
1139 # qhasm: h7 = h7 ^ h16
1140 # asm 1: vpxor <h16=reg128#10,<h7=reg128#7,>h7=reg128#7
1141 # asm 2: vpxor <h16=%xmm9,<h7=%xmm6,>h7=%xmm6
1142 vpxor %xmm9,%xmm6,%xmm6
1143
1144 # qhasm: h4 = h16
1145 # asm 1: movdqa <h16=reg128#10,>h4=reg128#10
1146 # asm 2: movdqa <h16=%xmm9,>h4=%xmm9
1147 movdqa %xmm9,%xmm9
1148
1149 # qhasm: h15 = mem128[ ptr + 304 ]
1150 # asm 1: movdqu 304(<ptr=int64#4),>h15=reg128#11
1151 # asm 2: movdqu 304(<ptr=%rcx),>h15=%xmm10
1152 movdqu 304(%rcx),%xmm10
1153
1154 # qhasm: h15 = h15 ^ mem128[ ptr + 480 ]
1155 # asm 1: vpxor 480(<ptr=int64#4),<h15=reg128#11,>h15=reg128#11
1156 # asm 2: vpxor 480(<ptr=%rcx),<h15=%xmm10,>h15=%xmm10
1157 vpxor 480(%rcx),%xmm10,%xmm10
1158
1159 # qhasm: h6 = h6 ^ h15
1160 # asm 1: vpxor <h15=reg128#11,<h6=reg128#8,>h6=reg128#8
1161 # asm 2: vpxor <h15=%xmm10,<h6=%xmm7,>h6=%xmm7
1162 vpxor %xmm10,%xmm7,%xmm7
1163
1164 # qhasm: h3 = h15
1165 # asm 1: movdqa <h15=reg128#11,>h3=reg128#11
1166 # asm 2: movdqa <h15=%xmm10,>h3=%xmm10
1167 movdqa %xmm10,%xmm10
1168
1169 # qhasm: h14 = mem128[ ptr + 272 ]
1170 # asm 1: movdqu 272(<ptr=int64#4),>h14=reg128#12
1171 # asm 2: movdqu 272(<ptr=%rcx),>h14=%xmm11
1172 movdqu 272(%rcx),%xmm11
1173
1174 # qhasm: h14 = h14 ^ mem128[ ptr + 448 ]
1175 # asm 1: vpxor 448(<ptr=int64#4),<h14=reg128#12,>h14=reg128#12
1176 # asm 2: vpxor 448(<ptr=%rcx),<h14=%xmm11,>h14=%xmm11
1177 vpxor 448(%rcx),%xmm11,%xmm11
1178
1179 # qhasm: h5 = h5 ^ h14
1180 # asm 1: vpxor <h14=reg128#12,<h5=reg128#9,>h5=reg128#9
1181 # asm 2: vpxor <h14=%xmm11,<h5=%xmm8,>h5=%xmm8
1182 vpxor %xmm11,%xmm8,%xmm8
1183
1184 # qhasm: h2 = h14
1185 # asm 1: movdqa <h14=reg128#12,>h2=reg128#12
1186 # asm 2: movdqa <h14=%xmm11,>h2=%xmm11
1187 movdqa %xmm11,%xmm11
1188
1189 # qhasm: h13 = h13 ^ mem128[ ptr + 240 ]
1190 # asm 1: vpxor 240(<ptr=int64#4),<h13=reg128#2,>h13=reg128#2
1191 # asm 2: vpxor 240(<ptr=%rcx),<h13=%xmm1,>h13=%xmm1
1192 vpxor 240(%rcx),%xmm1,%xmm1
1193
1194 # qhasm: h13 = h13 ^ mem128[ ptr + 416 ]
1195 # asm 1: vpxor 416(<ptr=int64#4),<h13=reg128#2,>h13=reg128#2
1196 # asm 2: vpxor 416(<ptr=%rcx),<h13=%xmm1,>h13=%xmm1
1197 vpxor 416(%rcx),%xmm1,%xmm1
1198
1199 # qhasm: h4 = h4 ^ h13
1200 # asm 1: vpxor <h13=reg128#2,<h4=reg128#10,>h4=reg128#10
1201 # asm 2: vpxor <h13=%xmm1,<h4=%xmm9,>h4=%xmm9
1202 vpxor %xmm1,%xmm9,%xmm9
1203
1204 # qhasm: h1 = h13
1205 # asm 1: movdqa <h13=reg128#2,>h1=reg128#2
1206 # asm 2: movdqa <h13=%xmm1,>h1=%xmm1
1207 movdqa %xmm1,%xmm1
1208
1209 # qhasm: h12 = h12 ^ mem128[ ptr + 208 ]
1210 # asm 1: vpxor 208(<ptr=int64#4),<h12=reg128#4,>h12=reg128#4
1211 # asm 2: vpxor 208(<ptr=%rcx),<h12=%xmm3,>h12=%xmm3
1212 vpxor 208(%rcx),%xmm3,%xmm3
1213
1214 # qhasm: h12 = h12 ^ mem128[ ptr + 384 ]
1215 # asm 1: vpxor 384(<ptr=int64#4),<h12=reg128#4,>h12=reg128#4
1216 # asm 2: vpxor 384(<ptr=%rcx),<h12=%xmm3,>h12=%xmm3
1217 vpxor 384(%rcx),%xmm3,%xmm3
1218
1219 # qhasm: h3 = h3 ^ h12
1220 # asm 1: vpxor <h12=reg128#4,<h3=reg128#11,>h3=reg128#11
1221 # asm 2: vpxor <h12=%xmm3,<h3=%xmm10,>h3=%xmm10
1222 vpxor %xmm3,%xmm10,%xmm10
1223
1224 # qhasm: h0 = h12
1225 # asm 1: movdqa <h12=reg128#4,>h0=reg128#4
1226 # asm 2: movdqa <h12=%xmm3,>h0=%xmm3
1227 movdqa %xmm3,%xmm3
1228
1229 # qhasm: h11 = h11 ^ mem128[ ptr + 352 ]
1230 # asm 1: vpxor 352(<ptr=int64#4),<h11=reg128#6,>h11=reg128#6
1231 # asm 2: vpxor 352(<ptr=%rcx),<h11=%xmm5,>h11=%xmm5
1232 vpxor 352(%rcx),%xmm5,%xmm5
1233
1234 # qhasm: h11 = h11 ^ mem128[ ptr + 176 ]
1235 # asm 1: vpxor 176(<ptr=int64#4),<h11=reg128#6,>h11=reg128#6
1236 # asm 2: vpxor 176(<ptr=%rcx),<h11=%xmm5,>h11=%xmm5
1237 vpxor 176(%rcx),%xmm5,%xmm5
1238
1239 # qhasm: mem128[ input_0 + 176 ] = h11
1240 # asm 1: movdqu <h11=reg128#6,176(<input_0=int64#1)
1241 # asm 2: movdqu <h11=%xmm5,176(<input_0=%rdi)
1242 movdqu %xmm5,176(%rdi)
1243
1244 # qhasm: h10 = h10 ^ mem128[ ptr + 320 ]
1245 # asm 1: vpxor 320(<ptr=int64#4),<h10=reg128#1,>h10=reg128#1
1246 # asm 2: vpxor 320(<ptr=%rcx),<h10=%xmm0,>h10=%xmm0
1247 vpxor 320(%rcx),%xmm0,%xmm0
1248
1249 # qhasm: h10 = h10 ^ mem128[ ptr + 144 ]
1250 # asm 1: vpxor 144(<ptr=int64#4),<h10=reg128#1,>h10=reg128#1
1251 # asm 2: vpxor 144(<ptr=%rcx),<h10=%xmm0,>h10=%xmm0
1252 vpxor 144(%rcx),%xmm0,%xmm0
1253
1254 # qhasm: mem128[ input_0 + 160 ] = h10
1255 # asm 1: movdqu <h10=reg128#1,160(<input_0=int64#1)
1256 # asm 2: movdqu <h10=%xmm0,160(<input_0=%rdi)
1257 movdqu %xmm0,160(%rdi)
1258
1259 # qhasm: h9 = h9 ^ mem128[ ptr + 288 ]
1260 # asm 1: vpxor 288(<ptr=int64#4),<h9=reg128#3,>h9=reg128#1
1261 # asm 2: vpxor 288(<ptr=%rcx),<h9=%xmm2,>h9=%xmm0
1262 vpxor 288(%rcx),%xmm2,%xmm0
1263
1264 # qhasm: h9 = h9 ^ mem128[ ptr + 112 ]
1265 # asm 1: vpxor 112(<ptr=int64#4),<h9=reg128#1,>h9=reg128#1
1266 # asm 2: vpxor 112(<ptr=%rcx),<h9=%xmm0,>h9=%xmm0
1267 vpxor 112(%rcx),%xmm0,%xmm0
1268
1269 # qhasm: mem128[ input_0 + 144 ] = h9
1270 # asm 1: movdqu <h9=reg128#1,144(<input_0=int64#1)
1271 # asm 2: movdqu <h9=%xmm0,144(<input_0=%rdi)
1272 movdqu %xmm0,144(%rdi)
1273
1274 # qhasm: h8 = h8 ^ mem128[ ptr + 256 ]
1275 # asm 1: vpxor 256(<ptr=int64#4),<h8=reg128#5,>h8=reg128#1
1276 # asm 2: vpxor 256(<ptr=%rcx),<h8=%xmm4,>h8=%xmm0
1277 vpxor 256(%rcx),%xmm4,%xmm0
1278
1279 # qhasm: h8 = h8 ^ mem128[ ptr + 80 ]
1280 # asm 1: vpxor 80(<ptr=int64#4),<h8=reg128#1,>h8=reg128#1
1281 # asm 2: vpxor 80(<ptr=%rcx),<h8=%xmm0,>h8=%xmm0
1282 vpxor 80(%rcx),%xmm0,%xmm0
1283
1284 # qhasm: mem128[ input_0 + 128 ] = h8
1285 # asm 1: movdqu <h8=reg128#1,128(<input_0=int64#1)
1286 # asm 2: movdqu <h8=%xmm0,128(<input_0=%rdi)
1287 movdqu %xmm0,128(%rdi)
1288
1289 # qhasm: h7 = h7 ^ mem128[ ptr + 224 ]
1290 # asm 1: vpxor 224(<ptr=int64#4),<h7=reg128#7,>h7=reg128#1
1291 # asm 2: vpxor 224(<ptr=%rcx),<h7=%xmm6,>h7=%xmm0
1292 vpxor 224(%rcx),%xmm6,%xmm0
1293
1294 # qhasm: h7 = h7 ^ mem128[ ptr + 48 ]
1295 # asm 1: vpxor 48(<ptr=int64#4),<h7=reg128#1,>h7=reg128#1
1296 # asm 2: vpxor 48(<ptr=%rcx),<h7=%xmm0,>h7=%xmm0
1297 vpxor 48(%rcx),%xmm0,%xmm0
1298
1299 # qhasm: mem128[ input_0 + 112 ] = h7
1300 # asm 1: movdqu <h7=reg128#1,112(<input_0=int64#1)
1301 # asm 2: movdqu <h7=%xmm0,112(<input_0=%rdi)
1302 movdqu %xmm0,112(%rdi)
1303
1304 # qhasm: h6 = h6 ^ mem128[ ptr + 192 ]
1305 # asm 1: vpxor 192(<ptr=int64#4),<h6=reg128#8,>h6=reg128#1
1306 # asm 2: vpxor 192(<ptr=%rcx),<h6=%xmm7,>h6=%xmm0
1307 vpxor 192(%rcx),%xmm7,%xmm0
1308
1309 # qhasm: h6 = h6 ^ mem128[ ptr + 16 ]
1310 # asm 1: vpxor 16(<ptr=int64#4),<h6=reg128#1,>h6=reg128#1
1311 # asm 2: vpxor 16(<ptr=%rcx),<h6=%xmm0,>h6=%xmm0
1312 vpxor 16(%rcx),%xmm0,%xmm0
1313
1314 # qhasm: mem128[ input_0 + 96 ] = h6
1315 # asm 1: movdqu <h6=reg128#1,96(<input_0=int64#1)
1316 # asm 2: movdqu <h6=%xmm0,96(<input_0=%rdi)
1317 movdqu %xmm0,96(%rdi)
1318
1319 # qhasm: h5 = h5 ^ mem128[ ptr + 160 ]
1320 # asm 1: vpxor 160(<ptr=int64#4),<h5=reg128#9,>h5=reg128#1
1321 # asm 2: vpxor 160(<ptr=%rcx),<h5=%xmm8,>h5=%xmm0
1322 vpxor 160(%rcx),%xmm8,%xmm0
1323
1324 # qhasm: mem128[ input_0 + 80 ] = h5
1325 # asm 1: movdqu <h5=reg128#1,80(<input_0=int64#1)
1326 # asm 2: movdqu <h5=%xmm0,80(<input_0=%rdi)
1327 movdqu %xmm0,80(%rdi)
1328
1329 # qhasm: h4 = h4 ^ mem128[ ptr + 128 ]
1330 # asm 1: vpxor 128(<ptr=int64#4),<h4=reg128#10,>h4=reg128#1
1331 # asm 2: vpxor 128(<ptr=%rcx),<h4=%xmm9,>h4=%xmm0
1332 vpxor 128(%rcx),%xmm9,%xmm0
1333
1334 # qhasm: mem128[ input_0 + 64 ] = h4
1335 # asm 1: movdqu <h4=reg128#1,64(<input_0=int64#1)
1336 # asm 2: movdqu <h4=%xmm0,64(<input_0=%rdi)
1337 movdqu %xmm0,64(%rdi)
1338
1339 # qhasm: h3 = h3 ^ mem128[ ptr + 96 ]
1340 # asm 1: vpxor 96(<ptr=int64#4),<h3=reg128#11,>h3=reg128#1
1341 # asm 2: vpxor 96(<ptr=%rcx),<h3=%xmm10,>h3=%xmm0
1342 vpxor 96(%rcx),%xmm10,%xmm0
1343
1344 # qhasm: mem128[ input_0 + 48 ] = h3
1345 # asm 1: movdqu <h3=reg128#1,48(<input_0=int64#1)
1346 # asm 2: movdqu <h3=%xmm0,48(<input_0=%rdi)
1347 movdqu %xmm0,48(%rdi)
1348
1349 # qhasm: h2 = h2 ^ mem128[ ptr + 64 ]
1350 # asm 1: vpxor 64(<ptr=int64#4),<h2=reg128#12,>h2=reg128#1
1351 # asm 2: vpxor 64(<ptr=%rcx),<h2=%xmm11,>h2=%xmm0
1352 vpxor 64(%rcx),%xmm11,%xmm0
1353
1354 # qhasm: mem128[ input_0 + 32 ] = h2
1355 # asm 1: movdqu <h2=reg128#1,32(<input_0=int64#1)
1356 # asm 2: movdqu <h2=%xmm0,32(<input_0=%rdi)
1357 movdqu %xmm0,32(%rdi)
1358
1359 # qhasm: h1 = h1 ^ mem128[ ptr + 32 ]
1360 # asm 1: vpxor 32(<ptr=int64#4),<h1=reg128#2,>h1=reg128#1
1361 # asm 2: vpxor 32(<ptr=%rcx),<h1=%xmm1,>h1=%xmm0
1362 vpxor 32(%rcx),%xmm1,%xmm0
1363
1364 # qhasm: mem128[ input_0 + 16 ] = h1
1365 # asm 1: movdqu <h1=reg128#1,16(<input_0=int64#1)
1366 # asm 2: movdqu <h1=%xmm0,16(<input_0=%rdi)
1367 movdqu %xmm0,16(%rdi)
1368
1369 # qhasm: h0 = h0 ^ mem128[ ptr + 0 ]
1370 # asm 1: vpxor 0(<ptr=int64#4),<h0=reg128#4,>h0=reg128#1
1371 # asm 2: vpxor 0(<ptr=%rcx),<h0=%xmm3,>h0=%xmm0
1372 vpxor 0(%rcx),%xmm3,%xmm0
1373
1374 # qhasm: mem128[ input_0 + 0 ] = h0
1375 # asm 1: movdqu <h0=reg128#1,0(<input_0=int64#1)
1376 # asm 2: movdqu <h0=%xmm0,0(<input_0=%rdi)
1377 movdqu %xmm0,0(%rdi)
1378
1379 # qhasm: return
1380 add %r11,%rsp
1381 ret
1382 .section .note.GNU-stack,"",@progbits