Lines Matching refs:x86
1 ; RUN: llc < %s -mtriple=x86_64-apple-darwin -march=x86 -mattr=avx2 | FileCheck %s
5 …%res = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a0, <8 x i32> %a1) ; <<16 x i16>> [#uses…
8 declare <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32>, <8 x i32>) nounwind readnone
13 …%res = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a0, <16 x i16> %a1) ; <<32 x i8>> [#uses…
16 declare <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16>, <16 x i16>) nounwind readnone
21 …%res = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a0, <16 x i16> %a1) ; <<32 x i8>> [#uses…
24 declare <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16>, <16 x i16>) nounwind readnone
29 %res = call <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
32 declare <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8>, <32 x i8>) nounwind readnone
37 …%res = call <16 x i16> @llvm.x86.avx2.padds.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#use…
40 declare <16 x i16> @llvm.x86.avx2.padds.w(<16 x i16>, <16 x i16>) nounwind readnone
45 …%res = call <32 x i8> @llvm.x86.avx2.paddus.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
48 declare <32 x i8> @llvm.x86.avx2.paddus.b(<32 x i8>, <32 x i8>) nounwind readnone
53 …%res = call <16 x i16> @llvm.x86.avx2.paddus.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#us…
56 declare <16 x i16> @llvm.x86.avx2.paddus.w(<16 x i16>, <16 x i16>) nounwind readnone
61 %res = call <32 x i8> @llvm.x86.avx2.pavg.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
64 declare <32 x i8> @llvm.x86.avx2.pavg.b(<32 x i8>, <32 x i8>) nounwind readnone
69 …%res = call <16 x i16> @llvm.x86.avx2.pavg.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses…
72 declare <16 x i16> @llvm.x86.avx2.pavg.w(<16 x i16>, <16 x i16>) nounwind readnone
77 …%res = call <8 x i32> @llvm.x86.avx2.pmadd.wd(<16 x i16> %a0, <16 x i16> %a1) ; <<8 x i32>> [#uses…
80 declare <8 x i32> @llvm.x86.avx2.pmadd.wd(<16 x i16>, <16 x i16>) nounwind readnone
85 …%res = call <16 x i16> @llvm.x86.avx2.pmaxs.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#use…
88 declare <16 x i16> @llvm.x86.avx2.pmaxs.w(<16 x i16>, <16 x i16>) nounwind readnone
93 %res = call <32 x i8> @llvm.x86.avx2.pmaxu.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
96 declare <32 x i8> @llvm.x86.avx2.pmaxu.b(<32 x i8>, <32 x i8>) nounwind readnone
101 …%res = call <16 x i16> @llvm.x86.avx2.pmins.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#use…
104 declare <16 x i16> @llvm.x86.avx2.pmins.w(<16 x i16>, <16 x i16>) nounwind readnone
109 %res = call <32 x i8> @llvm.x86.avx2.pminu.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
112 declare <32 x i8> @llvm.x86.avx2.pminu.b(<32 x i8>, <32 x i8>) nounwind readnone
117 %res = call i32 @llvm.x86.avx2.pmovmskb(<32 x i8> %a0) ; <i32> [#uses=1]
120 declare i32 @llvm.x86.avx2.pmovmskb(<32 x i8>) nounwind readnone
125 …%res = call <16 x i16> @llvm.x86.avx2.pmulh.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#use…
128 declare <16 x i16> @llvm.x86.avx2.pmulh.w(<16 x i16>, <16 x i16>) nounwind readnone
133 …%res = call <16 x i16> @llvm.x86.avx2.pmulhu.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#us…
136 declare <16 x i16> @llvm.x86.avx2.pmulhu.w(<16 x i16>, <16 x i16>) nounwind readnone
141 …%res = call <4 x i64> @llvm.x86.avx2.pmulu.dq(<8 x i32> %a0, <8 x i32> %a1) ; <<4 x i64>> [#uses=1]
144 declare <4 x i64> @llvm.x86.avx2.pmulu.dq(<8 x i32>, <8 x i32>) nounwind readnone
149 %res = call <4 x i64> @llvm.x86.avx2.psad.bw(<32 x i8> %a0, <32 x i8> %a1) ; <<4 x i64>> [#uses=1]
152 declare <4 x i64> @llvm.x86.avx2.psad.bw(<32 x i8>, <32 x i8>) nounwind readnone
157 %res = call <8 x i32> @llvm.x86.avx2.psll.d(<8 x i32> %a0, <4 x i32> %a1) ; <<8 x i32>> [#uses=1]
160 declare <8 x i32> @llvm.x86.avx2.psll.d(<8 x i32>, <4 x i32>) nounwind readnone
165 %res = call <4 x i64> @llvm.x86.avx2.psll.q(<4 x i64> %a0, <2 x i64> %a1) ; <<4 x i64>> [#uses=1]
168 declare <4 x i64> @llvm.x86.avx2.psll.q(<4 x i64>, <2 x i64>) nounwind readnone
173 …%res = call <16 x i16> @llvm.x86.avx2.psll.w(<16 x i16> %a0, <8 x i16> %a1) ; <<16 x i16>> [#uses=…
176 declare <16 x i16> @llvm.x86.avx2.psll.w(<16 x i16>, <8 x i16>) nounwind readnone
181 %res = call <8 x i32> @llvm.x86.avx2.pslli.d(<8 x i32> %a0, i32 7) ; <<8 x i32>> [#uses=1]
184 declare <8 x i32> @llvm.x86.avx2.pslli.d(<8 x i32>, i32) nounwind readnone
189 %res = call <4 x i64> @llvm.x86.avx2.pslli.q(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
192 declare <4 x i64> @llvm.x86.avx2.pslli.q(<4 x i64>, i32) nounwind readnone
197 %res = call <16 x i16> @llvm.x86.avx2.pslli.w(<16 x i16> %a0, i32 7) ; <<16 x i16>> [#uses=1]
200 declare <16 x i16> @llvm.x86.avx2.pslli.w(<16 x i16>, i32) nounwind readnone
205 %res = call <8 x i32> @llvm.x86.avx2.psra.d(<8 x i32> %a0, <4 x i32> %a1) ; <<8 x i32>> [#uses=1]
208 declare <8 x i32> @llvm.x86.avx2.psra.d(<8 x i32>, <4 x i32>) nounwind readnone
213 …%res = call <16 x i16> @llvm.x86.avx2.psra.w(<16 x i16> %a0, <8 x i16> %a1) ; <<16 x i16>> [#uses=…
216 declare <16 x i16> @llvm.x86.avx2.psra.w(<16 x i16>, <8 x i16>) nounwind readnone
221 %res = call <8 x i32> @llvm.x86.avx2.psrai.d(<8 x i32> %a0, i32 7) ; <<8 x i32>> [#uses=1]
224 declare <8 x i32> @llvm.x86.avx2.psrai.d(<8 x i32>, i32) nounwind readnone
229 %res = call <16 x i16> @llvm.x86.avx2.psrai.w(<16 x i16> %a0, i32 7) ; <<16 x i16>> [#uses=1]
232 declare <16 x i16> @llvm.x86.avx2.psrai.w(<16 x i16>, i32) nounwind readnone
237 %res = call <8 x i32> @llvm.x86.avx2.psrl.d(<8 x i32> %a0, <4 x i32> %a1) ; <<8 x i32>> [#uses=1]
240 declare <8 x i32> @llvm.x86.avx2.psrl.d(<8 x i32>, <4 x i32>) nounwind readnone
245 %res = call <4 x i64> @llvm.x86.avx2.psrl.q(<4 x i64> %a0, <2 x i64> %a1) ; <<4 x i64>> [#uses=1]
248 declare <4 x i64> @llvm.x86.avx2.psrl.q(<4 x i64>, <2 x i64>) nounwind readnone
253 …%res = call <16 x i16> @llvm.x86.avx2.psrl.w(<16 x i16> %a0, <8 x i16> %a1) ; <<16 x i16>> [#uses=…
256 declare <16 x i16> @llvm.x86.avx2.psrl.w(<16 x i16>, <8 x i16>) nounwind readnone
261 %res = call <8 x i32> @llvm.x86.avx2.psrli.d(<8 x i32> %a0, i32 7) ; <<8 x i32>> [#uses=1]
264 declare <8 x i32> @llvm.x86.avx2.psrli.d(<8 x i32>, i32) nounwind readnone
269 %res = call <4 x i64> @llvm.x86.avx2.psrli.q(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
272 declare <4 x i64> @llvm.x86.avx2.psrli.q(<4 x i64>, i32) nounwind readnone
277 %res = call <16 x i16> @llvm.x86.avx2.psrli.w(<16 x i16> %a0, i32 7) ; <<16 x i16>> [#uses=1]
280 declare <16 x i16> @llvm.x86.avx2.psrli.w(<16 x i16>, i32) nounwind readnone
285 %res = call <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
288 declare <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8>, <32 x i8>) nounwind readnone
293 …%res = call <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#use…
296 declare <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16>, <16 x i16>) nounwind readnone
301 …%res = call <32 x i8> @llvm.x86.avx2.psubus.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
304 declare <32 x i8> @llvm.x86.avx2.psubus.b(<32 x i8>, <32 x i8>) nounwind readnone
309 …%res = call <16 x i16> @llvm.x86.avx2.psubus.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#us…
312 declare <16 x i16> @llvm.x86.avx2.psubus.w(<16 x i16>, <16 x i16>) nounwind readnone
317 %res = call <32 x i8> @llvm.x86.avx2.pabs.b(<32 x i8> %a0) ; <<32 x i8>> [#uses=1]
320 declare <32 x i8> @llvm.x86.avx2.pabs.b(<32 x i8>) nounwind readnone
325 %res = call <8 x i32> @llvm.x86.avx2.pabs.d(<8 x i32> %a0) ; <<8 x i32>> [#uses=1]
328 declare <8 x i32> @llvm.x86.avx2.pabs.d(<8 x i32>) nounwind readnone
333 %res = call <16 x i16> @llvm.x86.avx2.pabs.w(<16 x i16> %a0) ; <<16 x i16>> [#uses=1]
336 declare <16 x i16> @llvm.x86.avx2.pabs.w(<16 x i16>) nounwind readnone
341 %res = call <8 x i32> @llvm.x86.avx2.phadd.d(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
344 declare <8 x i32> @llvm.x86.avx2.phadd.d(<8 x i32>, <8 x i32>) nounwind readnone
349 …%res = call <16 x i16> @llvm.x86.avx2.phadd.sw(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#us…
352 declare <16 x i16> @llvm.x86.avx2.phadd.sw(<16 x i16>, <16 x i16>) nounwind readnone
357 …%res = call <16 x i16> @llvm.x86.avx2.phadd.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#use…
360 declare <16 x i16> @llvm.x86.avx2.phadd.w(<16 x i16>, <16 x i16>) nounwind readnone
365 %res = call <8 x i32> @llvm.x86.avx2.phsub.d(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
368 declare <8 x i32> @llvm.x86.avx2.phsub.d(<8 x i32>, <8 x i32>) nounwind readnone
373 …%res = call <16 x i16> @llvm.x86.avx2.phsub.sw(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#us…
376 declare <16 x i16> @llvm.x86.avx2.phsub.sw(<16 x i16>, <16 x i16>) nounwind readnone
381 …%res = call <16 x i16> @llvm.x86.avx2.phsub.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#use…
384 declare <16 x i16> @llvm.x86.avx2.phsub.w(<16 x i16>, <16 x i16>) nounwind readnone
389 …%res = call <16 x i16> @llvm.x86.avx2.pmadd.ub.sw(<32 x i8> %a0, <32 x i8> %a1) ; <<16 x i16>> [#u…
392 declare <16 x i16> @llvm.x86.avx2.pmadd.ub.sw(<32 x i8>, <32 x i8>) nounwind readnone
397 …%res = call <16 x i16> @llvm.x86.avx2.pmul.hr.sw(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#…
400 declare <16 x i16> @llvm.x86.avx2.pmul.hr.sw(<16 x i16>, <16 x i16>) nounwind readnone
405 %res = call <32 x i8> @llvm.x86.avx2.pshuf.b(<32 x i8> %a0, <32 x i8> %a1) ; <<16 x i8>> [#uses=1]
408 declare <32 x i8> @llvm.x86.avx2.pshuf.b(<32 x i8>, <32 x i8>) nounwind readnone
413 %res = call <32 x i8> @llvm.x86.avx2.psign.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
416 declare <32 x i8> @llvm.x86.avx2.psign.b(<32 x i8>, <32 x i8>) nounwind readnone
421 %res = call <8 x i32> @llvm.x86.avx2.psign.d(<8 x i32> %a0, <8 x i32> %a1) ; <<4 x i32>> [#uses=1]
424 declare <8 x i32> @llvm.x86.avx2.psign.d(<8 x i32>, <8 x i32>) nounwind readnone
429 …%res = call <16 x i16> @llvm.x86.avx2.psign.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#use…
432 declare <16 x i16> @llvm.x86.avx2.psign.w(<16 x i16>, <16 x i16>) nounwind readnone
438 %res = call <4 x i64> @llvm.x86.avx2.movntdqa(i8* %a0) ; <<4 x i64>> [#uses=1]
441 declare <4 x i64> @llvm.x86.avx2.movntdqa(i8*) nounwind readonly
446 …%res = call <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8> %a0, <32 x i8> %a1, i8 7) ; <<16 x i16>> […
449 declare <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8>, <32 x i8>, i8) nounwind readnone
454 …%res = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a0, <8 x i32> %a1) ; <<16 x i16>> [#uses…
457 declare <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32>, <8 x i32>) nounwind readnone
462 …%res = call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> %a0, <32 x i8> %a1, <32 x i8> %a2) ; <<32 …
465 declare <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8>, <32 x i8>, <32 x i8>) nounwind readnone
470 …%res = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a1, i8 7) ; <<16 x i16>>…
473 declare <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16>, <16 x i16>, i8) nounwind readnone
478 %res = call <32 x i8> @llvm.x86.avx2.pmaxs.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
481 declare <32 x i8> @llvm.x86.avx2.pmaxs.b(<32 x i8>, <32 x i8>) nounwind readnone
486 %res = call <8 x i32> @llvm.x86.avx2.pmaxs.d(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
489 declare <8 x i32> @llvm.x86.avx2.pmaxs.d(<8 x i32>, <8 x i32>) nounwind readnone
494 %res = call <8 x i32> @llvm.x86.avx2.pmaxu.d(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
497 declare <8 x i32> @llvm.x86.avx2.pmaxu.d(<8 x i32>, <8 x i32>) nounwind readnone
502 …%res = call <16 x i16> @llvm.x86.avx2.pmaxu.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#use…
505 declare <16 x i16> @llvm.x86.avx2.pmaxu.w(<16 x i16>, <16 x i16>) nounwind readnone
510 %res = call <32 x i8> @llvm.x86.avx2.pmins.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
513 declare <32 x i8> @llvm.x86.avx2.pmins.b(<32 x i8>, <32 x i8>) nounwind readnone
518 %res = call <8 x i32> @llvm.x86.avx2.pmins.d(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
521 declare <8 x i32> @llvm.x86.avx2.pmins.d(<8 x i32>, <8 x i32>) nounwind readnone
526 %res = call <8 x i32> @llvm.x86.avx2.pminu.d(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
529 declare <8 x i32> @llvm.x86.avx2.pminu.d(<8 x i32>, <8 x i32>) nounwind readnone
534 …%res = call <16 x i16> @llvm.x86.avx2.pminu.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#use…
537 declare <16 x i16> @llvm.x86.avx2.pminu.w(<16 x i16>, <16 x i16>) nounwind readnone
542 %res = call <8 x i32> @llvm.x86.avx2.pmovsxbd(<16 x i8> %a0) ; <<8 x i32>> [#uses=1]
545 declare <8 x i32> @llvm.x86.avx2.pmovsxbd(<16 x i8>) nounwind readnone
550 %res = call <4 x i64> @llvm.x86.avx2.pmovsxbq(<16 x i8> %a0) ; <<4 x i64>> [#uses=1]
553 declare <4 x i64> @llvm.x86.avx2.pmovsxbq(<16 x i8>) nounwind readnone
558 %res = call <16 x i16> @llvm.x86.avx2.pmovsxbw(<16 x i8> %a0) ; <<8 x i16>> [#uses=1]
561 declare <16 x i16> @llvm.x86.avx2.pmovsxbw(<16 x i8>) nounwind readnone
566 %res = call <4 x i64> @llvm.x86.avx2.pmovsxdq(<4 x i32> %a0) ; <<4 x i64>> [#uses=1]
569 declare <4 x i64> @llvm.x86.avx2.pmovsxdq(<4 x i32>) nounwind readnone
574 %res = call <8 x i32> @llvm.x86.avx2.pmovsxwd(<8 x i16> %a0) ; <<8 x i32>> [#uses=1]
577 declare <8 x i32> @llvm.x86.avx2.pmovsxwd(<8 x i16>) nounwind readnone
582 %res = call <4 x i64> @llvm.x86.avx2.pmovsxwq(<8 x i16> %a0) ; <<4 x i64>> [#uses=1]
585 declare <4 x i64> @llvm.x86.avx2.pmovsxwq(<8 x i16>) nounwind readnone
590 %res = call <8 x i32> @llvm.x86.avx2.pmovzxbd(<16 x i8> %a0) ; <<8 x i32>> [#uses=1]
593 declare <8 x i32> @llvm.x86.avx2.pmovzxbd(<16 x i8>) nounwind readnone
598 %res = call <4 x i64> @llvm.x86.avx2.pmovzxbq(<16 x i8> %a0) ; <<4 x i64>> [#uses=1]
601 declare <4 x i64> @llvm.x86.avx2.pmovzxbq(<16 x i8>) nounwind readnone
606 %res = call <16 x i16> @llvm.x86.avx2.pmovzxbw(<16 x i8> %a0) ; <<16 x i16>> [#uses=1]
609 declare <16 x i16> @llvm.x86.avx2.pmovzxbw(<16 x i8>) nounwind readnone
614 %res = call <4 x i64> @llvm.x86.avx2.pmovzxdq(<4 x i32> %a0) ; <<4 x i64>> [#uses=1]
617 declare <4 x i64> @llvm.x86.avx2.pmovzxdq(<4 x i32>) nounwind readnone
622 %res = call <8 x i32> @llvm.x86.avx2.pmovzxwd(<8 x i16> %a0) ; <<8 x i32>> [#uses=1]
625 declare <8 x i32> @llvm.x86.avx2.pmovzxwd(<8 x i16>) nounwind readnone
630 %res = call <4 x i64> @llvm.x86.avx2.pmovzxwq(<8 x i16> %a0) ; <<4 x i64>> [#uses=1]
633 declare <4 x i64> @llvm.x86.avx2.pmovzxwq(<8 x i16>) nounwind readnone
638 %res = call <4 x i64> @llvm.x86.avx2.pmul.dq(<8 x i32> %a0, <8 x i32> %a1) ; <<2 x i64>> [#uses=1]
641 declare <4 x i64> @llvm.x86.avx2.pmul.dq(<8 x i32>, <8 x i32>) nounwind readnone
646 …%res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a1, i8 7) ; <<4 x i32>>…
649 declare <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32>, <4 x i32>, i8) nounwind readnone
654 …%res = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %a0, <8 x i32> %a1, i8 7) ; <<8 x i32>>…
657 declare <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32>, <8 x i32>, i8) nounwind readnone
665 %res = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
668 declare <8 x i32> @llvm.x86.avx2.permd(<8 x i32>, <8 x i32>) nounwind readonly
676 …%res = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> %a1) ; <<8 x float>> [#us…
679 declare <8 x float> @llvm.x86.avx2.permps(<8 x float>, <8 x i32>) nounwind readonly
684 …%res = call <4 x i64> @llvm.x86.avx2.vperm2i128(<4 x i64> %a0, <4 x i64> %a1, i8 1) ; <<4 x i64>> …
687 declare <4 x i64> @llvm.x86.avx2.vperm2i128(<4 x i64>, <4 x i64>, i8) nounwind readonly
692 %res = call <2 x i64> @llvm.x86.avx2.maskload.q(i8* %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
695 declare <2 x i64> @llvm.x86.avx2.maskload.q(i8*, <2 x i64>) nounwind readonly
700 …%res = call <4 x i64> @llvm.x86.avx2.maskload.q.256(i8* %a0, <4 x i64> %a1) ; <<4 x i64>> [#uses=1]
703 declare <4 x i64> @llvm.x86.avx2.maskload.q.256(i8*, <4 x i64>) nounwind readonly
708 %res = call <4 x i32> @llvm.x86.avx2.maskload.d(i8* %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
711 declare <4 x i32> @llvm.x86.avx2.maskload.d(i8*, <4 x i32>) nounwind readonly
716 …%res = call <8 x i32> @llvm.x86.avx2.maskload.d.256(i8* %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
719 declare <8 x i32> @llvm.x86.avx2.maskload.d.256(i8*, <8 x i32>) nounwind readonly
724 call void @llvm.x86.avx2.maskstore.q(i8* %a0, <2 x i64> %a1, <2 x i64> %a2)
727 declare void @llvm.x86.avx2.maskstore.q(i8*, <2 x i64>, <2 x i64>) nounwind
732 call void @llvm.x86.avx2.maskstore.q.256(i8* %a0, <4 x i64> %a1, <4 x i64> %a2)
735 declare void @llvm.x86.avx2.maskstore.q.256(i8*, <4 x i64>, <4 x i64>) nounwind
740 call void @llvm.x86.avx2.maskstore.d(i8* %a0, <4 x i32> %a1, <4 x i32> %a2)
743 declare void @llvm.x86.avx2.maskstore.d(i8*, <4 x i32>, <4 x i32>) nounwind
748 call void @llvm.x86.avx2.maskstore.d.256(i8* %a0, <8 x i32> %a1, <8 x i32> %a2)
751 declare void @llvm.x86.avx2.maskstore.d.256(i8*, <8 x i32>, <8 x i32>) nounwind
756 %res = call <4 x i32> @llvm.x86.avx2.psllv.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
759 declare <4 x i32> @llvm.x86.avx2.psllv.d(<4 x i32>, <4 x i32>) nounwind readnone
764 …%res = call <8 x i32> @llvm.x86.avx2.psllv.d.256(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#use…
767 declare <8 x i32> @llvm.x86.avx2.psllv.d.256(<8 x i32>, <8 x i32>) nounwind readnone
772 %res = call <2 x i64> @llvm.x86.avx2.psllv.q(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
775 declare <2 x i64> @llvm.x86.avx2.psllv.q(<2 x i64>, <2 x i64>) nounwind readnone
780 …%res = call <4 x i64> @llvm.x86.avx2.psllv.q.256(<4 x i64> %a0, <4 x i64> %a1) ; <<4 x i64>> [#use…
783 declare <4 x i64> @llvm.x86.avx2.psllv.q.256(<4 x i64>, <4 x i64>) nounwind readnone
788 %res = call <4 x i32> @llvm.x86.avx2.psrlv.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
791 declare <4 x i32> @llvm.x86.avx2.psrlv.d(<4 x i32>, <4 x i32>) nounwind readnone
796 …%res = call <8 x i32> @llvm.x86.avx2.psrlv.d.256(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#use…
799 declare <8 x i32> @llvm.x86.avx2.psrlv.d.256(<8 x i32>, <8 x i32>) nounwind readnone
804 %res = call <2 x i64> @llvm.x86.avx2.psrlv.q(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
807 declare <2 x i64> @llvm.x86.avx2.psrlv.q(<2 x i64>, <2 x i64>) nounwind readnone
812 …%res = call <4 x i64> @llvm.x86.avx2.psrlv.q.256(<4 x i64> %a0, <4 x i64> %a1) ; <<4 x i64>> [#use…
815 declare <4 x i64> @llvm.x86.avx2.psrlv.q.256(<4 x i64>, <4 x i64>) nounwind readnone
820 %res = call <4 x i32> @llvm.x86.avx2.psrav.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
823 declare <4 x i32> @llvm.x86.avx2.psrav.d(<4 x i32>, <4 x i32>) nounwind readnone
828 …%res = call <8 x i32> @llvm.x86.avx2.psrav.d.256(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#use…
831 declare <8 x i32> @llvm.x86.avx2.psrav.d.256(<8 x i32>, <8 x i32>) nounwind readnone
838 call void @llvm.x86.avx.storeu.dq.256(i8* %a0, <32 x i8> %a2)
841 declare void @llvm.x86.avx.storeu.dq.256(i8*, <32 x i8>) nounwind
846 %res = call <2 x double> @llvm.x86.avx2.gather.d.pd(<2 x double> %a0,
850 declare <2 x double> @llvm.x86.avx2.gather.d.pd(<2 x double>, i8*,
856 %res = call <4 x double> @llvm.x86.avx2.gather.d.pd.256(<4 x double> %a0,
860 declare <4 x double> @llvm.x86.avx2.gather.d.pd.256(<4 x double>, i8*,
866 %res = call <2 x double> @llvm.x86.avx2.gather.q.pd(<2 x double> %a0,
870 declare <2 x double> @llvm.x86.avx2.gather.q.pd(<2 x double>, i8*,
876 %res = call <4 x double> @llvm.x86.avx2.gather.q.pd.256(<4 x double> %a0,
880 declare <4 x double> @llvm.x86.avx2.gather.q.pd.256(<4 x double>, i8*,
886 %res = call <4 x float> @llvm.x86.avx2.gather.d.ps(<4 x float> %a0,
890 declare <4 x float> @llvm.x86.avx2.gather.d.ps(<4 x float>, i8*,
896 %res = call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> %a0,
900 declare <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float>, i8*,
906 %res = call <4 x float> @llvm.x86.avx2.gather.q.ps(<4 x float> %a0,
910 declare <4 x float> @llvm.x86.avx2.gather.q.ps(<4 x float>, i8*,
916 %res = call <4 x float> @llvm.x86.avx2.gather.q.ps.256(<4 x float> %a0,
920 declare <4 x float> @llvm.x86.avx2.gather.q.ps.256(<4 x float>, i8*,
926 %res = call <2 x i64> @llvm.x86.avx2.gather.d.q(<2 x i64> %a0,
930 declare <2 x i64> @llvm.x86.avx2.gather.d.q(<2 x i64>, i8*,
936 %res = call <4 x i64> @llvm.x86.avx2.gather.d.q.256(<4 x i64> %a0,
940 declare <4 x i64> @llvm.x86.avx2.gather.d.q.256(<4 x i64>, i8*,
946 %res = call <2 x i64> @llvm.x86.avx2.gather.q.q(<2 x i64> %a0,
950 declare <2 x i64> @llvm.x86.avx2.gather.q.q(<2 x i64>, i8*,
956 %res = call <4 x i64> @llvm.x86.avx2.gather.q.q.256(<4 x i64> %a0,
960 declare <4 x i64> @llvm.x86.avx2.gather.q.q.256(<4 x i64>, i8*,
966 %res = call <4 x i32> @llvm.x86.avx2.gather.d.d(<4 x i32> %a0,
970 declare <4 x i32> @llvm.x86.avx2.gather.d.d(<4 x i32>, i8*,
976 %res = call <8 x i32> @llvm.x86.avx2.gather.d.d.256(<8 x i32> %a0,
980 declare <8 x i32> @llvm.x86.avx2.gather.d.d.256(<8 x i32>, i8*,
986 %res = call <4 x i32> @llvm.x86.avx2.gather.q.d(<4 x i32> %a0,
990 declare <4 x i32> @llvm.x86.avx2.gather.q.d(<4 x i32>, i8*,
996 %res = call <4 x i32> @llvm.x86.avx2.gather.q.d.256(<4 x i32> %a0,
1000 declare <4 x i32> @llvm.x86.avx2.gather.q.d.256(<4 x i32>, i8*,
1012 %res = call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> %a0,