Lines Matching full:x86
1 ; RUN: llc < %s -mtriple=x86_64-apple-darwin -march=x86 -mcpu=core-avx2 -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=1]
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=1]
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=1]
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>> [#uses=1]
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>> [#uses=1]
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=1]
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=1]
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>> [#uses=1]
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>> [#uses=1]
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>> [#uses=1]
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>> [#uses=1]
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.dq(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
168 declare <4 x i64> @llvm.x86.avx2.psll.dq(<4 x i64>, i32) nounwind readnone
173 %res = call <4 x i64> @llvm.x86.avx2.psll.dq.bs(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
176 declare <4 x i64> @llvm.x86.avx2.psll.dq.bs(<4 x i64>, i32) nounwind readnone
181 %res = call <4 x i64> @llvm.x86.avx2.psll.q(<4 x i64> %a0, <2 x i64> %a1) ; <<4 x i64>> [#uses=1]
184 declare <4 x i64> @llvm.x86.avx2.psll.q(<4 x i64>, <2 x i64>) nounwind readnone
189 %res = call <16 x i16> @llvm.x86.avx2.psll.w(<16 x i16> %a0, <8 x i16> %a1) ; <<16 x i16>> [#uses=1]
192 declare <16 x i16> @llvm.x86.avx2.psll.w(<16 x i16>, <8 x i16>) nounwind readnone
197 %res = call <8 x i32> @llvm.x86.avx2.pslli.d(<8 x i32> %a0, i32 7) ; <<8 x i32>> [#uses=1]
200 declare <8 x i32> @llvm.x86.avx2.pslli.d(<8 x i32>, i32) nounwind readnone
205 %res = call <4 x i64> @llvm.x86.avx2.pslli.q(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
208 declare <4 x i64> @llvm.x86.avx2.pslli.q(<4 x i64>, i32) nounwind readnone
213 %res = call <16 x i16> @llvm.x86.avx2.pslli.w(<16 x i16> %a0, i32 7) ; <<16 x i16>> [#uses=1]
216 declare <16 x i16> @llvm.x86.avx2.pslli.w(<16 x i16>, i32) nounwind readnone
221 %res = call <8 x i32> @llvm.x86.avx2.psra.d(<8 x i32> %a0, <4 x i32> %a1) ; <<8 x i32>> [#uses=1]
224 declare <8 x i32> @llvm.x86.avx2.psra.d(<8 x i32>, <4 x i32>) nounwind readnone
229 %res = call <16 x i16> @llvm.x86.avx2.psra.w(<16 x i16> %a0, <8 x i16> %a1) ; <<16 x i16>> [#uses=1]
232 declare <16 x i16> @llvm.x86.avx2.psra.w(<16 x i16>, <8 x i16>) nounwind readnone
237 %res = call <8 x i32> @llvm.x86.avx2.psrai.d(<8 x i32> %a0, i32 7) ; <<8 x i32>> [#uses=1]
240 declare <8 x i32> @llvm.x86.avx2.psrai.d(<8 x i32>, i32) nounwind readnone
245 %res = call <16 x i16> @llvm.x86.avx2.psrai.w(<16 x i16> %a0, i32 7) ; <<16 x i16>> [#uses=1]
248 declare <16 x i16> @llvm.x86.avx2.psrai.w(<16 x i16>, i32) nounwind readnone
253 %res = call <8 x i32> @llvm.x86.avx2.psrl.d(<8 x i32> %a0, <4 x i32> %a1) ; <<8 x i32>> [#uses=1]
256 declare <8 x i32> @llvm.x86.avx2.psrl.d(<8 x i32>, <4 x i32>) nounwind readnone
261 %res = call <4 x i64> @llvm.x86.avx2.psrl.dq(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
264 declare <4 x i64> @llvm.x86.avx2.psrl.dq(<4 x i64>, i32) nounwind readnone
269 %res = call <4 x i64> @llvm.x86.avx2.psrl.dq.bs(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
272 declare <4 x i64> @llvm.x86.avx2.psrl.dq.bs(<4 x i64>, i32) nounwind readnone
277 %res = call <4 x i64> @llvm.x86.avx2.psrl.q(<4 x i64> %a0, <2 x i64> %a1) ; <<4 x i64>> [#uses=1]
280 declare <4 x i64> @llvm.x86.avx2.psrl.q(<4 x i64>, <2 x i64>) nounwind readnone
285 %res = call <16 x i16> @llvm.x86.avx2.psrl.w(<16 x i16> %a0, <8 x i16> %a1) ; <<16 x i16>> [#uses=1]
288 declare <16 x i16> @llvm.x86.avx2.psrl.w(<16 x i16>, <8 x i16>) nounwind readnone
293 %res = call <8 x i32> @llvm.x86.avx2.psrli.d(<8 x i32> %a0, i32 7) ; <<8 x i32>> [#uses=1]
296 declare <8 x i32> @llvm.x86.avx2.psrli.d(<8 x i32>, i32) nounwind readnone
301 %res = call <4 x i64> @llvm.x86.avx2.psrli.q(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
304 declare <4 x i64> @llvm.x86.avx2.psrli.q(<4 x i64>, i32) nounwind readnone
309 %res = call <16 x i16> @llvm.x86.avx2.psrli.w(<16 x i16> %a0, i32 7) ; <<16 x i16>> [#uses=1]
312 declare <16 x i16> @llvm.x86.avx2.psrli.w(<16 x i16>, i32) nounwind readnone
317 %res = call <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
320 declare <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8>, <32 x i8>) nounwind readnone
325 %res = call <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
328 declare <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16>, <16 x i16>) nounwind readnone
333 %res = call <32 x i8> @llvm.x86.avx2.psubus.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
336 declare <32 x i8> @llvm.x86.avx2.psubus.b(<32 x i8>, <32 x i8>) nounwind readnone
341 %res = call <16 x i16> @llvm.x86.avx2.psubus.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
344 declare <16 x i16> @llvm.x86.avx2.psubus.w(<16 x i16>, <16 x i16>) nounwind readnone
349 %res = call <32 x i8> @llvm.x86.avx2.pabs.b(<32 x i8> %a0) ; <<32 x i8>> [#uses=1]
352 declare <32 x i8> @llvm.x86.avx2.pabs.b(<32 x i8>) nounwind readnone
357 %res = call <8 x i32> @llvm.x86.avx2.pabs.d(<8 x i32> %a0) ; <<8 x i32>> [#uses=1]
360 declare <8 x i32> @llvm.x86.avx2.pabs.d(<8 x i32>) nounwind readnone
365 %res = call <16 x i16> @llvm.x86.avx2.pabs.w(<16 x i16> %a0) ; <<16 x i16>> [#uses=1]
368 declare <16 x i16> @llvm.x86.avx2.pabs.w(<16 x i16>) nounwind readnone
373 %res = call <8 x i32> @llvm.x86.avx2.phadd.d(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
376 declare <8 x i32> @llvm.x86.avx2.phadd.d(<8 x i32>, <8 x i32>) nounwind readnone
381 %res = call <16 x i16> @llvm.x86.avx2.phadd.sw(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
384 declare <16 x i16> @llvm.x86.avx2.phadd.sw(<16 x i16>, <16 x i16>) nounwind readnone
389 %res = call <16 x i16> @llvm.x86.avx2.phadd.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
392 declare <16 x i16> @llvm.x86.avx2.phadd.w(<16 x i16>, <16 x i16>) nounwind readnone
397 %res = call <8 x i32> @llvm.x86.avx2.phsub.d(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
400 declare <8 x i32> @llvm.x86.avx2.phsub.d(<8 x i32>, <8 x i32>) nounwind readnone
405 %res = call <16 x i16> @llvm.x86.avx2.phsub.sw(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
408 declare <16 x i16> @llvm.x86.avx2.phsub.sw(<16 x i16>, <16 x i16>) nounwind readnone
413 %res = call <16 x i16> @llvm.x86.avx2.phsub.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
416 declare <16 x i16> @llvm.x86.avx2.phsub.w(<16 x i16>, <16 x i16>) nounwind readnone
421 %res = call <16 x i16> @llvm.x86.avx2.pmadd.ub.sw(<32 x i8> %a0, <32 x i8> %a1) ; <<16 x i16>> [#uses=1]
424 declare <16 x i16> @llvm.x86.avx2.pmadd.ub.sw(<32 x i8>, <32 x i8>) nounwind readnone
429 %res = call <16 x i16> @llvm.x86.avx2.pmul.hr.sw(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
432 declare <16 x i16> @llvm.x86.avx2.pmul.hr.sw(<16 x i16>, <16 x i16>) nounwind readnone
437 %res = call <32 x i8> @llvm.x86.avx2.pshuf.b(<32 x i8> %a0, <32 x i8> %a1) ; <<16 x i8>> [#uses=1]
440 declare <32 x i8> @llvm.x86.avx2.pshuf.b(<32 x i8>, <32 x i8>) nounwind readnone
445 %res = call <32 x i8> @llvm.x86
448 declare <32 x i8> @llvm.x86.avx2.psign.b(<32 x i8>, <32 x i8>) nounwind readnone
453 %res = call <8 x i32> @llvm.x86.avx2.psign.d(<8 x i32> %a0, <8 x i32> %a1) ; <<4 x i32>> [#uses=1]
456 declare <8 x i32> @llvm.x86.avx2.psign.d(<8 x i32>, <8 x i32>) nounwind readnone
461 %res = call <16 x i16> @llvm.x86.avx2.psign.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
464 declare <16 x i16> @llvm.x86.avx2.psign.w(<16 x i16>, <16 x i16>) nounwind readnone
470 %res = call <4 x i64> @llvm.x86.avx2.movntdqa(i8* %a0) ; <<4 x i64>> [#uses=1]
473 declare <4 x i64> @llvm.x86.avx2.movntdqa(i8*) nounwind readonly
478 %res = call <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8> %a0, <32 x i8> %a1, i32 7) ; <<16 x i16>> [#uses=1]
481 declare <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8>, <32 x i8>, i32) nounwind readnone
486 %res = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a0, <8 x i32> %a1) ; <<16 x i16>> [#uses=1]
489 declare <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32>, <8 x i32>) nounwind readnone
494 %res = call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> %a0, <32 x i8> %a1, <32 x i8> %a2) ; <<32 x i8>> [#uses=1]
497 declare <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8>, <32 x i8>, <32 x i8>) nounwind readnone
502 %res = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a1, i32 7) ; <<16 x i16>> [#uses=1]
505 declare <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16>, <16 x i16>, i32) nounwind readnone
510 %res = call <32 x i8> @llvm.x86.avx2.pmaxs.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
513 declare <32 x i8> @llvm.x86.avx2.pmaxs.b(<32 x i8>, <32 x i8>) nounwind readnone
518 %res = call <8 x i32> @llvm.x86.avx2.pmaxs.d(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
521 declare <8 x i32> @llvm.x86.avx2.pmaxs.d(<8 x i32>, <8 x i32>) nounwind readnone
526 %res = call <8 x i32> @llvm.x86.avx2.pmaxu.d(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
529 declare <8 x i32> @llvm.x86.avx2.pmaxu.d(<8 x i32>, <8 x i32>) nounwind readnone
534 %res = call <16 x i16> @llvm.x86.avx2.pmaxu.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
537 declare <16 x i16> @llvm.x86.avx2.pmaxu.w(<16 x i16>, <16 x i16>) nounwind readnone
542 %res = call <32 x i8> @llvm.x86.avx2.pmins.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
545 declare <32 x i8> @llvm.x86.avx2.pmins.b(<32 x i8>, <32 x i8>) nounwind readnone
550 %res = call <8 x i32> @llvm.x86.avx2.pmins.d(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
553 declare <8 x i32> @llvm.x86.avx2.pmins.d(<8 x i32>, <8 x i32>) nounwind readnone
558 %res = call <8 x i32> @llvm.x86.avx2.pminu.d(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
561 declare <8 x i32> @llvm.x86.avx2.pminu.d(<8 x i32>, <8 x i32>) nounwind readnone
566 %res = call <16 x i16> @llvm.x86.avx2.pminu.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
569 declare <16 x i16> @llvm.x86.avx2.pminu.w(<16 x i16>, <16 x i16>) nounwind readnone
574 %res = call <8 x i32> @llvm.x86.avx2.pmovsxbd(<16 x i8> %a0) ; <<8 x i32>> [#uses=1]
577 declare <8 x i32> @llvm.x86.avx2.pmovsxbd(<16 x i8>) nounwind readnone
582 %res = call <4 x i64> @llvm.x86.avx2.pmovsxbq(<16 x i8> %a0) ; <<4 x i64>> [#uses=1]
585 declare <4 x i64> @llvm.x86.avx2.pmovsxbq(<16 x i8>) nounwind readnone
590 %res = call <16 x i16> @llvm.x86.avx2.pmovsxbw(<16 x i8> %a0) ; <<8 x i16>> [#uses=1]
593 declare <16 x i16> @llvm.x86.avx2.pmovsxbw(<16 x i8>) nounwind readnone
598 %res = call <4 x i64> @llvm.x86.avx2.pmovsxdq(<4 x i32> %a0) ; <<4 x i64>> [#uses=1]
601 declare <4 x i64> @llvm.x86.avx2.pmovsxdq(<4 x i32>) nounwind readnone
606 %res = call <8 x i32> @llvm.x86.avx2.pmovsxwd(<8 x i16> %a0) ; <<8 x i32>> [#uses=1]
609 declare <8 x i32> @llvm.x86.avx2.pmovsxwd(<8 x i16>) nounwind readnone
614 %res = call <4 x i64> @llvm.x86.avx2.pmovsxwq(<8 x i16> %a0) ; <<4 x i64>> [#uses=1]
617 declare <4 x i64> @llvm.x86.avx2.pmovsxwq(<8 x i16>) nounwind readnone
622 %res = call <8 x i32> @llvm.x86.avx2.pmovzxbd(<16 x i8> %a0) ; <<8 x i32>> [#uses=1]
625 declare <8 x i32> @llvm.x86.avx2.pmovzxbd(<16 x i8>) nounwind readnone
630 %res = call <4 x i64> @llvm.x86.avx2.pmovzxbq(<16 x i8> %a0) ; <<4 x i64>> [#uses=1]
633 declare <4 x i64> @llvm.x86.avx2.pmovzxbq(<16 x i8>) nounwind readnone
638 %res = call <16 x i16> @llvm.x86.avx2.pmovzxbw(<16 x i8> %a0) ; <<16 x i16>> [#uses=1]
641 declare <16 x i16> @llvm.x86.avx2.pmovzxbw(<16 x i8>) nounwind readnone
646 %res = call <4 x i64> @llvm.x86.avx2.pmovzxdq(<4 x i32> %a0) ; <<4 x i64>> [#uses=1]
649 declare <4 x i64> @llvm.x86.avx2.pmovzxdq(<4 x i32>) nounwind readnone
654 %res = call <8 x i32> @llvm.x86.avx2.pmovzxwd(<8 x i16> %a0) ; <<8 x i32>> [#uses=1]
657 declare <8 x i32> @llvm.x86.avx2.pmovzxwd(<8 x i16>) nounwind readnone
662 %res = call <4 x i64> @llvm.x86.avx2.pmovzxwq(<8 x i16> %a0) ; <<4 x i64>> [#uses=1]
665 declare <4 x i64> @llvm.x86.avx2.pmovzxwq(<8 x i16>) nounwind readnone
670 %res = call <4 x i64> @llvm.x86.avx2.pmul.dq(<8 x i32> %a0, <8 x i32> %a1) ; <<2 x i64>> [#uses=1]
673 declare <4 x i64> @llvm.x86.avx2.pmul.dq(<8 x i32>, <8 x i32>) nounwind readnone
678 %res = call <4 x i64> @llvm.x86.avx2.vbroadcasti128(i8* %a0) ; <<4 x i64>> [#uses=1]
681 declare <4 x i64> @llvm.x86.avx2.vbroadcasti128(i8*) nounwind readonly
685 %res = call <4 x double> @llvm.x86.avx2.vbroadcast.sd.pd.256(<2 x double> %a0) ; <<4 x double>> [#uses=1]
688 declare <4 x double> @llvm.x86.avx2.vbroadcast.sd.pd.256(<2 x double>) nounwind readonly
693 %res = call <4 x float> @llvm.x86.avx2.vbroadcast.ss.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
696 declare <4 x float> @llvm.x86.avx2.vbroadcast.ss.ps(<4 x float>) nounwind readonly
701 %res = call <8 x float> @llvm.x86.avx2.vbroadcast.ss.ps.256(<4 x float> %a0) ; <<8 x float>> [#uses=1]
704 declare <8 x float> @llvm.x86.avx2.vbroadcast.ss.ps.256(<4 x float>) nounwind readonly
709 %res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a1, i32 7) ; <<4 x i32>> [#uses=1]
712 declare <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32>, <4 x i32>, i32) nounwind readnone
717 %res = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %a0, <8 x i32> %a1, i32 7) ; <<8 x i32>> [#uses=1]
720 declare <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32>, <8 x i32>, i32) nounwind readnone
725 %res = call <16 x i8> @llvm.x86.avx2.pbroadcastb.128(<16 x i8> %a0) ; <<16 x i8>> [#uses=1]
728 declare <16 x i8> @llvm.x86.avx2.pbroadcastb.128(<16 x i8>) nounwind readonly
733 %res = call <32 x i8> @llvm.x86.avx2.pbroadcastb.256(<16 x i8> %a0) ; <<32 x i8>> [#uses=1]
736 declare <32 x i8> @llvm.x86.avx2.pbroadcastb.256(<16 x i8>) nounwind readonly
741 %res = call <8 x i16> @llvm.x86.avx2.pbroadcastw.128(<8 x i16> %a0) ; <<8 x i16>> [#uses=1]
744 declare <8 x i16> @llvm.x86.avx2.pbroadcastw.128(<8 x i16>) nounwind readonly
749 %res = call <16 x i16> @llvm.x86.avx2.pbroadcastw.256(<8 x i16> %a0) ; <<16 x i16>> [#uses=1]
752 declare <16 x i16> @llvm.x86.avx2.pbroadcastw.256(<8 x i16>) nounwind readonly
757 %res = call <4 x i32> @llvm.x86.avx2.pbroadcastd.128(<4 x i32> %a0) ; <<4 x i32>> [#uses=1]
760 declare <4 x i32> @llvm.x86.avx2.pbroadcastd.128(<4 x i32>) nounwind readonly
765 %res = call <8 x i32> @llvm.x86.avx2.pbroadcastd.256(<4 x i32> %a0) ; <<8 x i32>> [#uses=1]
768 declare <8 x i32> @llvm.x86.avx2.pbroadcastd.256(<4 x i32>) nounwind readonly
773 %res = call <2 x i64> @llvm.x86.avx2.pbroadcastq.128(<2 x i64> %a0) ; <<2 x i64>> [#uses=1]
776 declare <2 x i64> @llvm.x86.avx2.pbroadcastq.128(<2 x i64>) nounwind readonly
781 %res = call <4 x i64> @llvm.x86.avx2.pbroadcastq.256(<2 x i64> %a0) ; <<4 x i64>> [#uses=1]
784 declare <4 x i64> @llvm.x86.avx2.pbroadcastq.256(<2 x i64>) nounwind readonly
789 %res = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
792 declare <8 x i32> @llvm.x86.avx2.permd(<8 x i32>, <8 x i32>) nounwind readonly
797 %res = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
800 declare <8 x float> @llvm.x86.avx2.permps(<8 x float>, <8 x float>) nounwind readonly
805 %res = call <4 x i64> @llvm.x86.avx2.vperm2i128(<4 x i64> %a0, <4 x i64> %a1, i8 1) ; <<4 x i64>> [#uses=1]
808 declare <4 x i64> @llvm.x86.avx2.vperm2i128(<4 x i64>, <4 x i64>, i8) nounwind readonly
813 %res = call <2 x i64> @llvm.x86.avx2.vextracti128(<4 x i64> %a0, i8 7) ; <<2 x i64>> [#uses=1]
816 declare <2 x i64> @llvm.x86.avx2.vextracti128(<4 x i64>, i8) nounwind readnone
821 %res = call <4 x i64> @llvm.x86.avx2.vinserti128(<4 x i64> %a0, <2 x i64> %a1, i8 7) ; <<4 x i64>> [#uses=1]
824 declare <4 x i64> @llvm.x86.avx2.vinserti128(<4 x i64>, <2 x i64>, i8) nounwind readnone
829 %res = call <2 x i64> @llvm.x86.avx2.maskload.q(i8* %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
832 declare <2 x i64> @llvm.x86.avx2.maskload.q(i8*, <2 x i64>) nounwind readonly
837 %res = call <4 x i64> @llvm.x86.avx2.maskload.q.256(i8* %a0, <4 x i64> %a1) ; <<4 x i64>> [#uses=1]
840 declare <4 x i64> @llvm.x86.avx2.maskload.q.256(i8*, <4 x i64>) nounwind readonly
845 %res = call <4 x i32> @llvm.x86.avx2.maskload.d(i8* %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
848 declare <4 x i32> @llvm.x86.avx2.maskload.d(i8*, <4 x i32>) nounwind readonly
853 %res = call <8 x i32> @llvm.x86.avx2.maskload.d.256(i8* %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
856 declare <8 x i32> @llvm.x86.avx2.maskload.d.256(i8*, <8 x i32>) nounwind readonly
861 call void @llvm.x86.avx2.maskstore.q(i8* %a0, <2 x i64> %a1, <2 x i64> %a2)
864 declare void @llvm.x86.avx2.maskstore.q(i8*, <2 x i64>, <2 x i64>) nounwind
869 call void @llvm.x86.avx2.maskstore.q.256(i8* %a0, <4 x i64> %a1, <4 x i64> %a2)
872 declare void @llvm.x86.avx2.maskstore.q.256(i8*, <4 x i64>, <4 x i64>) nounwind
877 call void @llvm.x86.avx2.maskstore.d(i8* %a0, <4 x i32> %a1, <4 x i32> %a2)
880 declare void @llvm.x86.avx2.maskstore.d(i8*, <4 x i32>, <4 x i32>) nounwind
885 call void @llvm.x86.avx2.maskstore.d.256(i8* %a0, <8 x i32> %a1, <8 x i32> %a2)
888 declare void @llvm.x86.avx2.maskstore.d.256(i8*, <8 x i32>, <8 x i32>) nounwind
893 %res = call <4 x i32> @llvm.x86.avx2.psllv.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
896 declare <4 x i32> @llvm.x86
901 %res = call <8 x i32> @llvm.x86.avx2.psllv.d.256(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
904 declare <8 x i32> @llvm.x86.avx2.psllv.d.256(<8 x i32>, <8 x i32>) nounwind readnone
909 %res = call <2 x i64> @llvm.x86.avx2.psllv.q(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
912 declare <2 x i64> @llvm.x86.avx2.psllv.q(<2 x i64>, <2 x i64>) nounwind readnone
917 %res = call <4 x i64> @llvm.x86.avx2.psllv.q.256(<4 x i64> %a0, <4 x i64> %a1) ; <<4 x i64>> [#uses=1]
920 declare <4 x i64> @llvm.x86.avx2.psllv.q.256(<4 x i64>, <4 x i64>) nounwind readnone
925 %res = call <4 x i32> @llvm.x86.avx2.psrlv.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
928 declare <4 x i32> @llvm.x86.avx2.psrlv.d(<4 x i32>, <4 x i32>) nounwind readnone
933 %res = call <8 x i32> @llvm.x86.avx2.psrlv.d.256(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
936 declare <8 x i32> @llvm.x86.avx2.psrlv.d.256(<8 x i32>, <8 x i32>) nounwind readnone
941 %res = call <2 x i64> @llvm.x86.avx2.psrlv.q(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
944 declare <2 x i64> @llvm.x86.avx2.psrlv.q(<2 x i64>, <2 x i64>) nounwind readnone
949 %res = call <4 x i64> @llvm.x86.avx2.psrlv.q.256(<4 x i64> %a0, <4 x i64> %a1) ; <<4 x i64>> [#uses=1]
952 declare <4 x i64> @llvm.x86.avx2.psrlv.q.256(<4 x i64>, <4 x i64>) nounwind readnone
957 %res = call <4 x i32> @llvm.x86.avx2.psrav.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
960 declare <4 x i32> @llvm.x86.avx2.psrav.d(<4 x i32>, <4 x i32>) nounwind readnone
965 %res = call <8 x i32> @llvm.x86.avx2.psrav.d.256(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
968 declare <8 x i32> @llvm.x86.avx2.psrav.d.256(<8 x i32>, <8 x i32>) nounwind readnone
975 call void @llvm.x86.avx.storeu.dq.256(i8* %a0, <32 x i8> %a2)
978 declare void @llvm.x86.avx.storeu.dq.256(i8*, <32 x i8>) nounwind
983 %res = call <2 x double> @llvm.x86.avx2.gather.d.pd(<2 x double> %a0,
987 declare <2 x double> @llvm.x86.avx2.gather.d.pd(<2 x double>, i8*,
993 %res = call <4 x double> @llvm.x86.avx2.gather.d.pd.256(<4 x double> %a0,
997 declare <4 x double> @llvm.x86.avx2.gather.d.pd.256(<4 x double>, i8*,
1003 %res = call <2 x double> @llvm.x86.avx2.gather.q.pd(<2 x double> %a0,
1007 declare <2 x double> @llvm.x86.avx2.gather.q.pd(<2 x double>, i8*,
1013 %res = call <4 x double> @llvm.x86.avx2.gather.q.pd.256(<4 x double> %a0,
1017 declare <4 x double> @llvm.x86.avx2.gather.q.pd.256(<4 x double>, i8*,
1023 %res = call <4 x float> @llvm.x86.avx2.gather.d.ps(<4 x float> %a0,
1027 declare <4 x float> @llvm.x86.avx2.gather.d.ps(<4 x float>, i8*,
1033 %res = call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> %a0,
1037 declare <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float>, i8*,
1043 %res = call <4 x float> @llvm.x86.avx2.gather.q.ps(<4 x float> %a0,
1047 declare <4 x float> @llvm.x86.avx2.gather.q.ps(<4 x float>, i8*,
1053 %res = call <4 x float> @llvm.x86.avx2.gather.q.ps.256(<4 x float> %a0,
1057 declare <4 x float> @llvm.x86.avx2.gather.q.ps.256(<4 x float>, i8*,
1063 %res = call <2 x i64> @llvm.x86.avx2.gather.d.q(<2 x i64> %a0,
1067 declare <2 x i64> @llvm.x86.avx2.gather.d.q(<2 x i64>, i8*,
1073 %res = call <4 x i64> @llvm.x86.avx2.gather.d.q.256(<4 x i64> %a0,
1077 declare <4 x i64> @llvm.x86.avx2.gather.d.q.256(<4 x i64>, i8*,
1083 %res = call <2 x i64> @llvm.x86.avx2.gather.q.q(<2 x i64> %a0,
1087 declare <2 x i64> @llvm.x86.avx2.gather.q.q(<2 x i64>, i8*,
1093 %res = call <4 x i64> @llvm.x86.avx2.gather.q.q.256(<4 x i64> %a0,
1097 declare <4 x i64> @llvm.x86.avx2.gather.q.q.256(<4 x i64>, i8*,
1103 %res = call <4 x i32> @llvm.x86.avx2.gather.d.d(<4 x i32> %a0,
1107 declare <4 x i32> @llvm.x86.avx2.gather.d.d(<4 x i32>, i8*,
1113 %res = call <8 x i32> @llvm.x86.avx2.gather.d.d.256(<8 x i32> %a0,
1117 declare <8 x i32> @llvm.x86.avx2.gather.d.d.256(<8 x i32>, i8*,
1123 %res = call <4 x i32> @llvm.x86.avx2.gather.q.d(<4 x i32> %a0,
1127 declare <4 x i32> @llvm.x86.avx2.gather.q.d(<4 x i32>, i8*,
1133 %res = call <4 x i32> @llvm.x86.avx2.gather.q.d.256(<4 x i32> %a0,
1137 declare <4 x i32> @llvm.x86.avx2.gather.q.d.256(<4 x i32>, i8*,
1149 %res = call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> %a0,
