Lines Matching full:x86
1 ; RUN: llc < %s -mtriple=x86_64-apple-darwin -march=x86 -mcpu=corei7 -mattr=avx | FileCheck %s
5 %res = call <2 x i64> @llvm.x86.aesni.aesdec(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
8 declare <2 x i64> @llvm.x86.aesni.aesdec(<2 x i64>, <2 x i64>) nounwind readnone
13 %res = call <2 x i64> @llvm.x86.aesni.aesdeclast(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
16 declare <2 x i64> @llvm.x86.aesni.aesdeclast(<2 x i64>, <2 x i64>) nounwind readnone
21 %res = call <2 x i64> @llvm.x86.aesni.aesenc(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
24 declare <2 x i64> @llvm.x86.aesni.aesenc(<2 x i64>, <2 x i64>) nounwind readnone
29 %res = call <2 x i64> @llvm.x86.aesni.aesenclast(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
32 declare <2 x i64> @llvm.x86.aesni.aesenclast(<2 x i64>, <2 x i64>) nounwind readnone
37 %res = call <2 x i64> @llvm.x86.aesni.aesimc(<2 x i64> %a0) ; <<2 x i64>> [#uses=1]
40 declare <2 x i64> @llvm.x86.aesni.aesimc(<2 x i64>) nounwind readnone
45 %res = call <2 x i64> @llvm.x86.aesni.aeskeygenassist(<2 x i64> %a0, i8 7) ; <<2 x i64>> [#uses=1]
48 declare <2 x i64> @llvm.x86.aesni.aeskeygenassist(<2 x i64>, i8) nounwind readnone
53 %res = call <2 x double> @llvm.x86.sse2.add.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
56 declare <2 x double> @llvm.x86.sse2.add.sd(<2 x double>, <2 x double>) nounwind readnone
61 %res = call <2 x double> @llvm.x86.sse2.cmp.pd(<2 x double> %a0, <2 x double> %a1, i8 7) ; <<2 x double>> [#uses=1]
64 declare <2 x double> @llvm.x86.sse2.cmp.pd(<2 x double>, <2 x double>, i8) nounwind readnone
69 %res = call <2 x double> @llvm.x86.sse2.cmp.sd(<2 x double> %a0, <2 x double> %a1, i8 7) ; <<2 x double>> [#uses=1]
72 declare <2 x double> @llvm.x86.sse2.cmp.sd(<2 x double>, <2 x double>, i8) nounwind readnone
79 %res = call i32 @llvm.x86.sse2.comieq.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
82 declare i32 @llvm.x86.sse2.comieq.sd(<2 x double>, <2 x double>) nounwind readnone
89 %res = call i32 @llvm.x86.sse2.comige.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
92 declare i32 @llvm.x86.sse2.comige.sd(<2 x double>, <2 x double>) nounwind readnone
99 %res = call i32 @llvm.x86.sse2.comigt.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
102 declare i32 @llvm.x86.sse2.comigt.sd(<2 x double>, <2 x double>) nounwind readnone
109 %res = call i32 @llvm.x86.sse2.comile.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
112 declare i32 @llvm.x86.sse2.comile.sd(<2 x double>, <2 x double>) nounwind readnone
119 %res = call i32 @llvm.x86.sse2.comilt.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
122 declare i32 @llvm.x86.sse2.comilt.sd(<2 x double>, <2 x double>) nounwind readnone
129 %res = call i32 @llvm.x86.sse2.comineq.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
132 declare i32 @llvm.x86.sse2.comineq.sd(<2 x double>, <2 x double>) nounwind readnone
137 %res = call <2 x double> @llvm.x86.sse2.cvtdq2pd(<4 x i32> %a0) ; <<2 x double>> [#uses=1]
140 declare <2 x double> @llvm.x86.sse2.cvtdq2pd(<4 x i32>) nounwind readnone
145 %res = call <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32> %a0) ; <<4 x float>> [#uses=1]
148 declare <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32>) nounwind readnone
153 %res = call <4 x i32> @llvm.x86.sse2.cvtpd2dq(<2 x double> %a0) ; <<4 x i32>> [#uses=1]
156 declare <4 x i32> @llvm.x86.sse2.cvtpd2dq(<2 x double>) nounwind readnone
161 %res = call <4 x float> @llvm.x86.sse2.cvtpd2ps(<2 x double> %a0) ; <<4 x float>> [#uses=1]
164 declare <4 x float> @llvm.x86.sse2.cvtpd2ps(<2 x double>) nounwind readnone
169 %res = call <4 x i32> @llvm.x86.sse2.cvtps2dq(<4 x float> %a0) ; <<4 x i32>> [#uses=1]
172 declare <4 x i32> @llvm.x86.sse2.cvtps2dq(<4 x float>) nounwind readnone
177 %res = call <2 x double> @llvm.x86.sse2.cvtps2pd(<4 x float> %a0) ; <<2 x double>> [#uses=1]
180 declare <2 x double> @llvm.x86.sse2.cvtps2pd(<4 x float>) nounwind readnone
185 %res = call i32 @llvm.x86.sse2.cvtsd2si(<2 x double> %a0) ; <i32> [#uses=1]
188 declare i32 @llvm.x86.sse2.cvtsd2si(<2 x double>) nounwind readnone
193 %res = call <4 x float> @llvm.x86.sse2.cvtsd2ss(<4 x float> %a0, <2 x double> %a1) ; <<4 x float>> [#uses=1]
196 declare <4 x float> @llvm.x86.sse2.cvtsd2ss(<4 x float>, <2 x double>) nounwind readnone
202 %res = call <2 x double> @llvm.x86.sse2.cvtsi2sd(<2 x double> %a0, i32 7) ; <<2 x double>> [#uses=1]
205 declare <2 x double> @llvm.x86.sse2.cvtsi2sd(<2 x double>, i32) nounwind readnone
210 %res = call <2 x double> @llvm.x86.sse2.cvtss2sd(<2 x double> %a0, <4 x float> %a1) ; <<2 x double>> [#uses=1]
213 declare <2 x double> @llvm.x86.sse2.cvtss2sd(<2 x double>, <4 x float>) nounwind readnone
218 %res = call <4 x i32> @llvm.x86.sse2.cvttpd2dq(<2 x double> %a0) ; <<4 x i32>> [#uses=1]
221 declare <4 x i32> @llvm.x86.sse2.cvttpd2dq(<2 x double>) nounwind readnone
226 %res = call <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float> %a0) ; <<4 x i32>> [#uses=1]
229 declare <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float>) nounwind readnone
234 %res = call i32 @llvm.x86.sse2.cvttsd2si(<2 x double> %a0) ; <i32> [#uses=1]
237 declare i32 @llvm.x86.sse2.cvttsd2si(<2 x double>) nounwind readnone
242 %res = call <2 x double> @llvm.x86.sse2.div.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
245 declare <2 x double> @llvm.x86.sse2.div.sd(<2 x double>, <2 x double>) nounwind readnone
251 %res = call <16 x i8> @llvm.x86.sse2.loadu.dq(i8* %a0) ; <<16 x i8>> [#uses=1]
254 declare <16 x i8> @llvm.x86.sse2.loadu.dq(i8*) nounwind readonly
260 %res = call <2 x double> @llvm.x86.sse2.loadu.pd(i8* %a0) ; <<2 x double>> [#uses=1]
263 declare <2 x double> @llvm.x86.sse2.loadu.pd(i8*) nounwind readonly
271 call void @llvm.x86.sse2.maskmov.dqu(<16 x i8> %a0, <16 x i8> %a1, i8* %a2)
274 declare void @llvm.x86.sse2.maskmov.dqu(<16 x i8>, <16 x i8>, i8*) nounwind
279 %res = call <2 x double> @llvm.x86.sse2.max.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
282 declare <2 x double> @llvm.x86.sse2.max.pd(<2 x double>, <2 x double>) nounwind readnone
287 %res = call <2 x double> @llvm.x86.sse2.max.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
290 declare <2 x double> @llvm.x86.sse2.max.sd(<2 x double>, <2 x double>) nounwind readnone
295 %res = call <2 x double> @llvm.x86.sse2.min.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
298 declare <2 x double> @llvm.x86.sse2.min.pd(<2 x double>, <2 x double>) nounwind readnone
303 %res = call <2 x double> @llvm.x86.sse2.min.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
306 declare <2 x double> @llvm.x86.sse2.min.sd(<2 x double>, <2 x double>) nounwind readnone
311 %res = call i32 @llvm.x86.sse2.movmsk.pd(<2 x double> %a0) ; <i32> [#uses=1]
314 declare i32 @llvm.x86.sse2.movmsk.pd(<2 x double>) nounwind readnone
320 call void @llvm.x86.sse2.movnt.dq(i8* %a0, <2 x i64> %a1)
323 declare void @llvm.x86.sse2.movnt.dq(i8*, <2 x i64>) nounwind
329 call void @llvm.x86.sse2.movnt.pd(i8* %a0, <2 x double> %a1)
332 declare void @llvm.x86.sse2.movnt.pd(i8*, <2 x double>) nounwind
337 %res = call <2 x double> @llvm.x86.sse2.mul.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
340 declare <2 x double> @llvm.x86.sse2.mul.sd(<2 x double>, <2 x double>) nounwind readnone
345 %res = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a0, <4 x i32> %a1) ; <<8 x i16>> [#uses=1]
348 declare <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32>, <4 x i32>) nounwind readnone
353 %res = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a0, <8 x i16> %a1) ; <<16 x i8>> [#uses=1]
356 declare <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16>, <8 x i16>) nounwind readnone
361 %res = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a0, <8 x i16> %a1) ; <<16 x i8>> [#uses=1]
364 declare <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16>, <8 x i16>) nounwind readnone
369 %res = call <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
372 declare <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8>, <16 x i8>) nounwind readnone
377 %res = call <8 x i16> @llvm.x86.sse2.padds.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
380 declare <8 x i16> @llvm.x86.sse2.padds.w(<8 x i16>, <8 x i16>) nounwind readnone
385 %res = call <16 x i8> @llvm.x86.sse2.paddus.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
388 declare <16 x i8> @llvm.x86.sse2.paddus.b(<16 x i8>, <16 x i8>) nounwind readnone
393 %res = call <8 x i16> @llvm.x86.sse2.paddus.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
396 declare <8 x i16> @llvm.x86.sse2.paddus.w(<8 x i16>, <8 x i16>) nounwind readnone
401 %res = call <16 x i8> @llvm.x86.sse2.pavg.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
404 declare <16 x i8> @llvm.x86.sse2.pavg.b(<16 x i8>, <16 x i8>) nounwind readnone
409 %res = call <8 x i16> @llvm.x86.sse2.pavg.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
412 declare <8 x i16> @llvm.x86.sse2.pavg.w(<8 x i16>, <8 x i16>) nounwind readnone
417 %res = call <16 x i8> @llvm.x86.sse2.pcmpeq.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
420 declare <16 x i8> @llvm.x86.sse2.pcmpeq.b(<16 x i8>, <16 x i8>) nounwind readnone
425 %res = call <4 x i32> @llvm.x86.sse2.pcmpeq.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
428 declare <4 x i32> @llvm.x86.sse2.pcmpeq.d(<4 x i32>, <4 x i32>) nounwind readnone
433 %res = call <8 x i16> @llvm.x86.sse2.pcmpeq.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
436 declare <8 x i16> @llvm.x86.sse2.pcmpeq.w(<8 x i16>, <8 x i16>) nounwind readnone
441 %res = call <16 x i8> @llvm.x86.sse2.pcmpgt.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
444 declare <16 x i8> @llvm.x86.sse2.pcmpgt.b(<16 x i8>, <16 x i8>) nounwind readnone
449 %res = call <4 x i32> @llvm.x86.sse2.pcmpgt.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
452 declare <4 x i32> @llvm.x86.sse2.pcmpgt.d(<4 x i32>, <4 x i32>) nounwind readnone
457 %res = call <8 x i16> @llvm.x86.sse2.pcmpgt.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
460 declare <8 x i16> @llvm.x86.sse2.pcmpgt.w(<8 x i16>, <8 x i16>) nounwind readnone
465 %res = call <4 x i32> @llvm.x86.sse2.pmadd.wd(<8 x i16> %a0, <8 x i16> %a1) ; <<4 x i32>> [#uses=1]
468 declare <4 x i32> @llvm.x86.sse2.pmadd.wd(<8 x i16>, <8 x i16>) nounwind readnone
473 %res = call <8 x i16> @llvm.x86.sse2.pmaxs.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
476 declare <8 x i16> @llvm.x86.sse2.pmaxs.w(<8 x i16>, <8 x i16>) nounwind readnone
481 %res = call <16 x i8> @llvm.x86.sse2.pmaxu.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
484 declare <16 x i8> @llvm.x86.sse2.pmaxu.b(<16 x i8>, <16 x i8>) nounwind readnone
489 %res = call <8 x i16> @llvm.x86.sse2.pmins.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
492 declare <8 x i16> @llvm.x86.sse2.pmins.w(<8 x i16>, <8 x i16>) nounwind readnone
497 %res = call <16 x i8> @llvm.x86.sse2.pminu.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
500 declare <16 x i8> @llvm.x86.sse2.pminu.b(<16 x i8>, <16 x i8>) nounwind readnone
505 %res = call i32 @llvm.x86.sse2.pmovmskb.128(<16 x i8> %a0) ; <i32> [#uses=1]
508 declare i32 @llvm.x86.sse2.pmovmskb.128(<16 x i8>) nounwind readnone
513 %res = call <8 x i16> @llvm.x86.sse2.pmulh.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
516 declare <8 x i16> @llvm.x86.sse2.pmulh.w(<8 x i16>, <8 x i16>) nounwind readnone
521 %res = call <8 x i16> @llvm.x86.sse2.pmulhu.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
524 declare <8 x i16> @llvm.x86.sse2.pmulhu.w(<8 x i16>, <8 x i16>) nounwind readnone
529 %res = call <2 x i64> @llvm.x86.sse2.pmulu.dq(<4 x i32> %a0, <4 x i32> %a1) ; <<2 x i64>> [#uses=1]
532 declare <2 x i64> @llvm.x86.sse2.pmulu.dq(<4 x i32>, <4 x i32>) nounwind readnone
537 %res = call <2 x i64> @llvm.x86.sse2.psad.bw(<16 x i8> %a0, <16 x i8> %a1) ; <<2 x i64>> [#uses=1]
540 declare <2 x i64> @llvm.x86.sse2.psad.bw(<16 x i8>, <16 x i8>) nounwind readnone
545 %res = call <4 x i32> @llvm.x86.sse2.psll.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
548 declare <4 x i32> @llvm.x86.sse2.psll.d(<4 x i32>, <4 x i32>) nounwind readnone
553 %res = call <2 x i64> @llvm.x86.sse2.psll.dq(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
556 declare <2 x i64> @llvm.x86.sse2.psll.dq(<2 x i64>, i32) nounwind readnone
561 %res = call <2 x i64> @llvm.x86.sse2.psll.dq.bs(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
564 declare <2 x i64> @llvm.x86.sse2.psll.dq.bs(<2 x i64>, i32) nounwind readnone
569 %res = call <2 x i64> @llvm.x86.sse2.psll.q(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
572 declare <2 x i64> @llvm.x86.sse2.psll.q(<2 x i64>, <2 x i64>) nounwind readnone
577 %res = call <8 x i16> @llvm.x86.sse2.psll.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
580 declare <8 x i16> @llvm.x86.sse2.psll.w(<8 x i16>, <8 x i16>) nounwind readnone
585 %res = call <4 x i32> @llvm.x86.sse2.pslli.d(<4 x i32> %a0, i32 7) ; <<4 x i32>> [#uses=1]
588 declare <4 x i32> @llvm.x86.sse2.pslli.d(<4 x i32>, i32) nounwind readnone
593 %res = call <2 x i64> @llvm.x86.sse2.pslli.q(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
596 declare <2 x i64> @llvm.x86.sse2.pslli.q(<2 x i64>, i32) nounwind readnone
601 %res = call <8 x i16> @llvm.x86.sse2.pslli.w(<8 x i16> %a0, i32 7) ; <<8 x i16>> [#uses=1]
604 declare <8 x i16> @llvm.x86.sse2.pslli.w(<8 x i16>, i32) nounwind readnone
609 %res = call <4 x i32> @llvm.x86.sse2.psra.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
612 declare <4 x i32> @llvm.x86.sse2.psra.d(<4 x i32>, <4 x i32>) nounwind readnone
617 %res = call <8 x i16> @llvm.x86.sse2.psra.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
620 declare <8 x i16> @llvm.x86.sse2.psra.w(<8 x i16>, <8 x i16>) nounwind readnone
625 %res = call <4 x i32> @llvm.x86.sse2.psrai.d(<4 x i32> %a0, i32 7) ; <<4 x i32>> [#uses=1]
628 declare <4 x i32> @llvm.x86.sse2.psrai.d(<4 x i32>, i32) nounwind readnone
633 %res = call <8 x i16> @llvm.x86.sse2.psrai.w(<8 x i16> %a0, i32 7) ; <<8 x i16>> [#uses=1]
636 declare <8 x i16> @llvm.x86.sse2.psrai.w(<8 x i16>, i32) nounwind readnone
641 %res = call <4 x i32> @llvm.x86.sse2.psrl.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
644 declare <4 x i32> @llvm.x86.sse2.psrl.d(<4 x i32>, <4 x i32>) nounwind readnone
649 %res = call <2 x i64> @llvm.x86.sse2.psrl.dq(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
652 declare <2 x i64> @llvm.x86.sse2.psrl.dq(<2 x i64>, i32) nounwind readnone
657 %res = call <2 x i64> @llvm.x86.sse2.psrl.dq.bs(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
660 declare <2 x i64> @llvm.x86.sse2.psrl.dq.bs(<2 x i64>, i32) nounwind readnone
665 %res = call <2 x i64> @llvm.x86.sse2.psrl.q(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
668 declare <2 x i64> @llvm.x86.sse2.psrl.q(<2 x i64>, <2 x i64>) nounwind readnone
673 %res = call <8 x i16> @llvm.x86.sse2.psrl.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
676 declare <8 x i16> @llvm.x86.sse2.psrl.w(<8 x i16>, <8 x i16>) nounwind readnone
681 %res = call <4 x i32> @llvm.x86.sse2.psrli.d(<4 x i32> %a0, i32 7) ; <<4 x i32>> [#uses=1]
684 declare <4 x i32> @llvm.x86.sse2.psrli.d(<4 x i32>, i32) nounwind readnone
689 %res = call <2 x i64> @llvm.x86.sse2.psrli.q(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
692 declare <2 x i64> @llvm.x86.sse2.psrli.q(<2 x i64>, i32) nounwind readnone
697 %res = call <8 x i16> @llvm.x86.sse2.psrli.w(<8 x i16> %a0, i32 7) ; <<8 x i16>> [#uses=1]
700 declare <8 x i16> @llvm.x86.sse2.psrli.w(<8 x i16>, i32) nounwind readnone
705 %res = call <16 x i8> @llvm.x86.sse2.psubs.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
708 declare <16 x i8> @llvm.x86.sse2.psubs.b(<16 x i8>, <16 x i8>) nounwind readnone
713 %res = call <8 x i16> @llvm.x86.sse2.psubs.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
716 declare <8 x i16> @llvm.x86.sse2.psubs.w(<8 x i16>, <8 x i16>) nounwind readnone
721 %res = call <16 x i8> @llvm.x86.sse2.psubus.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
724 declare <16 x i8> @llvm.x86.sse2.psubus.b(<16 x i8>, <16 x i8>) nounwind readnone
729 %res = call <8 x i16> @llvm.x86.sse2.psubus.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
732 declare <8 x i16> @llvm.x86.sse2.psubus.w(<8 x i16>, <8 x i16>) nounwind readnone
737 %res = call <2 x double> @llvm.x86.sse2.sqrt.pd(<2 x double> %a0) ; <<2 x double>> [#uses=1]
740 declare <2 x double> @llvm.x86.sse2.sqrt.pd(<2 x double>) nounwind readnone
745 %res = call <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double> %a0) ; <<2 x double>> [#uses=1]
748 declare <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double>) nounwind readnone
754 call void @llvm.x86.sse2.storel.dq(i8* %a0, <4 x i32> %a1)
757 declare void @llvm.x86.sse2.storel.dq(i8*, <4 x i32>) nounwind
763 call void @llvm.x86.sse2.storeu.dq(i8* %a0, <16 x i8> %a1)
766 declare void @llvm.x86.sse2.storeu.dq(i8*, <16 x i8>) nounwind
772 call void @llvm.x86.sse2.storeu.pd(i8* %a0, <2 x double> %a1)
775 declare void @llvm.x86.sse2.storeu.pd(i8*, <2 x double>) nounwind
780 %res = call <2 x double> @llvm.x86.sse2.sub.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
783 declare <2 x double> @llvm.x86.sse2.sub.sd(<2 x double>, <2 x double>) nounwind readnone
790 %res = call i32 @llvm.x86.sse2.ucomieq.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
793 declare i32 @llvm.x86.sse2.ucomieq.sd(<2 x double>, <2 x double>) nounwind readnone
800 %res = call i32 @llvm.x86.sse2.ucomige.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
803 declare i32 @llvm.x86.sse2.ucomige.sd(<2 x double>, <2 x double>) nounwind readnone
810 %res = call i32 @llvm.x86.sse2.ucomigt.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
813 declare i32 @llvm.x86.sse2.ucomigt.sd(<2 x double>, <2 x double>) nounwind readnone
820 %res = call i32 @llvm.x86.sse2.ucomile.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
823 declare i32 @llvm.x86.sse2.ucomile.sd(<2 x double>, <2 x double>) nounwind readnone
829 %res = call i32 @llvm.x86.sse2.ucomilt.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
832 declare i32 @llvm.x86.sse2.ucomilt.sd(<2 x double>, <2 x double>) nounwind readnone
839 %res = call i32 @llvm.x86.sse2.ucomineq.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
842 declare i32 @llvm.x86.sse2.ucomineq.sd(<2 x double>, <2 x double>) nounwind readnone
847 %res = call <2 x double> @llvm.x86.sse3.addsub.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
850 declare <2 x double> @llvm.x86.sse3.addsub.pd(<2 x double>, <2 x double>) nounwind readnone
855 %res = call <4 x float> @llvm.x86.sse3.addsub.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
858 declare <4 x float> @llvm.x86.sse3.addsub.ps(<4 x float>, <4 x float>) nounwind readnone
863 %res = call <2 x double> @llvm.x86.sse3.hadd.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
866 declare <2 x double> @llvm.x86.sse3.hadd.pd(<2 x double>, <2 x double>) nounwind readnone
871 %res = call <4 x float> @llvm.x86.sse3.hadd.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
874 declare <4 x float> @llvm.x86.sse3.hadd.ps(<4 x float>, <4 x float>) nounwind readnone
879 %res = call <2 x double> @llvm.x86.sse3.hsub.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
882 declare <2 x double> @llvm.x86.sse3.hsub.pd(<2 x double>, <2 x double>) nounwind readnone
887 %res = call <4 x float> @llvm.x86.sse3.hsub.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
890 declare <4 x float> @llvm.x86.sse3.hsub.ps(<4 x float>, <4 x float>) nounwind readnone
896 %res = call <16 x i8> @llvm.x86.sse3.ldu.dq(i8* %a0) ; <<16 x i8>> [#uses=1]
899 declare <16 x i8> @llvm.x86.sse3.ldu.dq(i8*) nounwind readonly
904 %res = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
907 declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i32) nounwind readnone
912 %res = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
915 declare <4 x float> @llvm.x86
920 %res = call <2 x double> @llvm.x86.sse41.blendvpd(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2) ; <<2 x double>> [#uses=1]
923 declare <2 x double> @llvm.x86.sse41.blendvpd(<2 x double>, <2 x double>, <2 x double>) nounwind readnone
928 %res = call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2) ; <<4 x float>> [#uses=1]
931 declare <4 x float> @llvm.x86.sse41.blendvps(<4 x float>, <4 x float>, <4 x float>) nounwind readnone
936 %res = call <2 x double> @llvm.x86.sse41.dppd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
939 declare <2 x double> @llvm.x86.sse41.dppd(<2 x double>, <2 x double>, i32) nounwind readnone
944 %res = call <4 x float> @llvm.x86.sse41.dpps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
947 declare <4 x float> @llvm.x86.sse41.dpps(<4 x float>, <4 x float>, i32) nounwind readnone
952 %res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
955 declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i32) nounwind readnone
961 %res = call <2 x i64> @llvm.x86.sse41.movntdqa(i8* %a0) ; <<2 x i64>> [#uses=1]
964 declare <2 x i64> @llvm.x86.sse41.movntdqa(i8*) nounwind readonly
969 %res = call <16 x i8> @llvm.x86.sse41.mpsadbw(<16 x i8> %a0, <16 x i8> %a1, i32 7) ; <<16 x i8>> [#uses=1]
972 declare <16 x i8> @llvm.x86.sse41.mpsadbw(<16 x i8>, <16 x i8>, i32) nounwind readnone
977 %res = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a0, <4 x i32> %a1) ; <<8 x i16>> [#uses=1]
980 declare <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32>, <4 x i32>) nounwind readnone
985 %res = call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> %a2) ; <<16 x i8>> [#uses=1]
988 declare <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8>, <16 x i8>, <16 x i8>) nounwind readnone
993 %res = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %a0, <8 x i16> %a1, i32 7) ; <<8 x i16>> [#uses=1]
996 declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i32) nounwind readnone
1001 %res = call <2 x i64> @llvm.x86.sse41.pcmpeqq(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
1004 declare <2 x i64> @llvm.x86.sse41.pcmpeqq(<2 x i64>, <2 x i64>) nounwind readnone
1009 %res = call <8 x i16> @llvm.x86.sse41.phminposuw(<8 x i16> %a0) ; <<8 x i16>> [#uses=1]
1012 declare <8 x i16> @llvm.x86.sse41.phminposuw(<8 x i16>) nounwind readnone
1017 %res = call <16 x i8> @llvm.x86.sse41.pmaxsb(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
1020 declare <16 x i8> @llvm.x86.sse41.pmaxsb(<16 x i8>, <16 x i8>) nounwind readnone
1025 %res = call <4 x i32> @llvm.x86.sse41.pmaxsd(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1028 declare <4 x i32> @llvm.x86.sse41.pmaxsd(<4 x i32>, <4 x i32>) nounwind readnone
1033 %res = call <4 x i32> @llvm.x86.sse41.pmaxud(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1036 declare <4 x i32> @llvm.x86.sse41.pmaxud(<4 x i32>, <4 x i32>) nounwind readnone
1041 %res = call <8 x i16> @llvm.x86.sse41.pmaxuw(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1044 declare <8 x i16> @llvm.x86.sse41.pmaxuw(<8 x i16>, <8 x i16>) nounwind readnone
1049 %res = call <16 x i8> @llvm.x86.sse41.pminsb(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
1052 declare <16 x i8> @llvm.x86.sse41.pminsb(<16 x i8>, <16 x i8>) nounwind readnone
1057 %res = call <4 x i32> @llvm.x86.sse41.pminsd(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1060 declare <4 x i32> @llvm.x86.sse41.pminsd(<4 x i32>, <4 x i32>) nounwind readnone
1065 %res = call <4 x i32> @llvm.x86.sse41.pminud(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1068 declare <4 x i32> @llvm.x86.sse41.pminud(<4 x i32>, <4 x i32>) nounwind readnone
1073 %res = call <8 x i16> @llvm.x86.sse41.pminuw(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1076 declare <8 x i16> @llvm.x86.sse41.pminuw(<8 x i16>, <8 x i16>) nounwind readnone
1081 %res = call <4 x i32> @llvm.x86.sse41.pmovsxbd(<16 x i8> %a0) ; <<4 x i32>> [#uses=1]
1084 declare <4 x i32> @llvm.x86.sse41.pmovsxbd(<16 x i8>) nounwind readnone
1089 %res = call <2 x i64> @llvm.x86.sse41.pmovsxbq(<16 x i8> %a0) ; <<2 x i64>> [#uses=1]
1092 declare <2 x i64> @llvm.x86.sse41.pmovsxbq(<16 x i8>) nounwind readnone
1097 %res = call <8 x i16> @llvm.x86.sse41.pmovsxbw(<16 x i8> %a0) ; <<8 x i16>> [#uses=1]
1100 declare <8 x i16> @llvm.x86.sse41.pmovsxbw(<16 x i8>) nounwind readnone
1105 %res = call <2 x i64> @llvm.x86.sse41.pmovsxdq(<4 x i32> %a0) ; <<2 x i64>> [#uses=1]
1108 declare <2 x i64> @llvm.x86.sse41.pmovsxdq(<4 x i32>) nounwind readnone
1113 %res = call <4 x i32> @llvm.x86.sse41.pmovsxwd(<8 x i16> %a0) ; <<4 x i32>> [#uses=1]
1116 declare <4 x i32> @llvm.x86.sse41.pmovsxwd(<8 x i16>) nounwind readnone
1121 %res = call <2 x i64> @llvm.x86.sse41.pmovsxwq(<8 x i16> %a0) ; <<2 x i64>> [#uses=1]
1124 declare <2 x i64> @llvm.x86.sse41.pmovsxwq(<8 x i16>) nounwind readnone
1129 %res = call <4 x i32> @llvm.x86.sse41.pmovzxbd(<16 x i8> %a0) ; <<4 x i32>> [#uses=1]
1132 declare <4 x i32> @llvm.x86.sse41.pmovzxbd(<16 x i8>) nounwind readnone
1137 %res = call <2 x i64> @llvm.x86.sse41.pmovzxbq(<16 x i8> %a0) ; <<2 x i64>> [#uses=1]
1140 declare <2 x i64> @llvm.x86.sse41.pmovzxbq(<16 x i8>) nounwind readnone
1145 %res = call <8 x i16> @llvm.x86.sse41.pmovzxbw(<16 x i8> %a0) ; <<8 x i16>> [#uses=1]
1148 declare <8 x i16> @llvm.x86.sse41.pmovzxbw(<16 x i8>) nounwind readnone
1153 %res = call <2 x i64> @llvm.x86.sse41.pmovzxdq(<4 x i32> %a0) ; <<2 x i64>> [#uses=1]
1156 declare <2 x i64> @llvm.x86.sse41.pmovzxdq(<4 x i32>) nounwind readnone
1161 %res = call <4 x i32> @llvm.x86.sse41.pmovzxwd(<8 x i16> %a0) ; <<4 x i32>> [#uses=1]
1164 declare <4 x i32> @llvm.x86.sse41.pmovzxwd(<8 x i16>) nounwind readnone
1169 %res = call <2 x i64> @llvm.x86.sse41.pmovzxwq(<8 x i16> %a0) ; <<2 x i64>> [#uses=1]
1172 declare <2 x i64> @llvm.x86.sse41.pmovzxwq(<8 x i16>) nounwind readnone
1177 %res = call <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32> %a0, <4 x i32> %a1) ; <<2 x i64>> [#uses=1]
1180 declare <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32>, <4 x i32>) nounwind readnone
1186 %res = call i32 @llvm.x86.sse41.ptestc(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1189 declare i32 @llvm.x86.sse41.ptestc(<4 x float>, <4 x float>) nounwind readnone
1196 %res = call i32 @llvm.x86.sse41.ptestnzc(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1199 declare i32 @llvm.x86.sse41.ptestnzc(<4 x float>, <4 x float>) nounwind readnone
1206 %res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1209 declare i32 @llvm.x86.sse41.ptestz(<4 x float>, <4 x float>) nounwind readnone
1214 %res = call <2 x double> @llvm.x86.sse41.round.pd(<2 x double> %a0, i32 7) ; <<2 x double>> [#uses=1]
1217 declare <2 x double> @llvm.x86.sse41.round.pd(<2 x double>, i32) nounwind readnone
1222 %res = call <4 x float> @llvm.x86.sse41.round.ps(<4 x float> %a0, i32 7) ; <<4 x float>> [#uses=1]
1225 declare <4 x float> @llvm.x86.sse41.round.ps(<4 x float>, i32) nounwind readnone
1230 %res = call <2 x double> @llvm.x86.sse41.round.sd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
1233 declare <2 x double> @llvm.x86.sse41.round.sd(<2 x double>, <2 x double>, i32) nounwind readnone
1238 %res = call <4 x float> @llvm.x86.sse41.round.ss(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
1241 declare <4 x float> @llvm.x86.sse41.round.ss(<4 x float>, <4 x float>, i32) nounwind readnone
1249 %res = call i32 @llvm.x86.sse42.pcmpestri128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1252 declare i32 @llvm.x86.sse42.pcmpestri128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1260 %res = call i32 @llvm.x86.sse42.pcmpestria128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1263 declare i32 @llvm.x86.sse42.pcmpestria128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1271 %res = call i32 @llvm.x86.sse42.pcmpestric128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1274 declare i32 @llvm.x86.sse42.pcmpestric128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1282 %res = call i32 @llvm.x86.sse42.pcmpestrio128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1285 declare i32 @llvm.x86.sse42.pcmpestrio128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1293 %res = call i32 @llvm.x86.sse42.pcmpestris128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1296 declare i32 @llvm.x86.sse42.pcmpestris128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1304 %res = call i32 @llvm.x86.sse42.pcmpestriz128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1307 declare i32 @llvm.x86.sse42.pcmpestriz128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1314 %res = call <16 x i8> @llvm.x86.sse42.pcmpestrm128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <<16 x i8>> [#uses=1]
1317 declare <16 x i8> @llvm.x86.sse42.pcmpestrm128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1322 %res = call <2 x i64> @llvm.x86.sse42.pcmpgtq(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
1325 declare <2 x i64> @llvm.x86.sse42.pcmpgtq(<2 x i64>, <2 x i64>) nounwind readnone
1331 %res = call i32 @llvm.x86.sse42.pcmpistri128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1334 declare i32 @llvm.x86.sse42.pcmpistri128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1340 %res = call i32 @llvm.x86.sse42.pcmpistria128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1343 declare i32 @llvm.x86.sse42.pcmpistria128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1349 %res = call i32 @llvm.x86.sse42.pcmpistric128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1352 declare i32 @llvm.x86.sse42.pcmpistric128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1358 %res = call i32 @llvm.x86.sse42.pcmpistrio128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1361 declare i32 @llvm.x86.sse42.pcmpistrio128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1367 %res = call i32 @llvm.x86
1370 declare i32 @llvm.x86.sse42.pcmpistris128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1376 %res = call i32 @llvm.x86.sse42.pcmpistriz128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1379 declare i32 @llvm.x86.sse42.pcmpistriz128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1384 %res = call <16 x i8> @llvm.x86.sse42.pcmpistrm128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <<16 x i8>> [#uses=1]
1387 declare <16 x i8> @llvm.x86.sse42.pcmpistrm128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1392 %res = call <4 x float> @llvm.x86.sse.add.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1395 declare <4 x float> @llvm.x86.sse.add.ss(<4 x float>, <4 x float>) nounwind readnone
1400 %res = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
1403 declare <4 x float> @llvm.x86.sse.cmp.ps(<4 x float>, <4 x float>, i8) nounwind readnone
1408 %res = call <4 x float> @llvm.x86.sse.cmp.ss(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
1411 declare <4 x float> @llvm.x86.sse.cmp.ss(<4 x float>, <4 x float>, i8) nounwind readnone
1418 %res = call i32 @llvm.x86.sse.comieq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1421 declare i32 @llvm.x86.sse.comieq.ss(<4 x float>, <4 x float>) nounwind readnone
1428 %res = call i32 @llvm.x86.sse.comige.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1431 declare i32 @llvm.x86.sse.comige.ss(<4 x float>, <4 x float>) nounwind readnone
1438 %res = call i32 @llvm.x86.sse.comigt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1441 declare i32 @llvm.x86.sse.comigt.ss(<4 x float>, <4 x float>) nounwind readnone
1448 %res = call i32 @llvm.x86.sse.comile.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1451 declare i32 @llvm.x86.sse.comile.ss(<4 x float>, <4 x float>) nounwind readnone
1457 %res = call i32 @llvm.x86.sse.comilt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1460 declare i32 @llvm.x86.sse.comilt.ss(<4 x float>, <4 x float>) nounwind readnone
1467 %res = call i32 @llvm.x86.sse.comineq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1470 declare i32 @llvm.x86.sse.comineq.ss(<4 x float>, <4 x float>) nounwind readnone
1476 %res = call <4 x float> @llvm.x86.sse.cvtsi2ss(<4 x float> %a0, i32 7) ; <<4 x float>> [#uses=1]
1479 declare <4 x float> @llvm.x86.sse.cvtsi2ss(<4 x float>, i32) nounwind readnone
1484 %res = call i32 @llvm.x86.sse.cvtss2si(<4 x float> %a0) ; <i32> [#uses=1]
1487 declare i32 @llvm.x86.sse.cvtss2si(<4 x float>) nounwind readnone
1492 %res = call i32 @llvm.x86.sse.cvttss2si(<4 x float> %a0) ; <i32> [#uses=1]
1495 declare i32 @llvm.x86.sse.cvttss2si(<4 x float>) nounwind readnone
1500 %res = call <4 x float> @llvm.x86.sse.div.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1503 declare <4 x float> @llvm.x86.sse.div.ss(<4 x float>, <4 x float>) nounwind readnone
1509 call void @llvm.x86.sse.ldmxcsr(i8* %a0)
1512 declare void @llvm.x86.sse.ldmxcsr(i8*) nounwind
1518 %res = call <4 x float> @llvm.x86.sse.loadu.ps(i8* %a0) ; <<4 x float>> [#uses=1]
1521 declare <4 x float> @llvm.x86.sse.loadu.ps(i8*) nounwind readonly
1526 %res = call <4 x float> @llvm.x86.sse.max.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1529 declare <4 x float> @llvm.x86.sse.max.ps(<4 x float>, <4 x float>) nounwind readnone
1534 %res = call <4 x float> @llvm.x86.sse.max.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1537 declare <4 x float> @llvm.x86.sse.max.ss(<4 x float>, <4 x float>) nounwind readnone
1542 %res = call <4 x float> @llvm.x86.sse.min.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1545 declare <4 x float> @llvm.x86.sse.min.ps(<4 x float>, <4 x float>) nounwind readnone
1550 %res = call <4 x float> @llvm.x86.sse.min.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1553 declare <4 x float> @llvm.x86.sse.min.ss(<4 x float>, <4 x float>) nounwind readnone
1558 %res = call i32 @llvm.x86.sse.movmsk.ps(<4 x float> %a0) ; <i32> [#uses=1]
1561 declare i32 @llvm.x86.sse.movmsk.ps(<4 x float>) nounwind readnone
1567 call void @llvm.x86.sse.movnt.ps(i8* %a0, <4 x float> %a1)
1570 declare void @llvm.x86.sse.movnt.ps(i8*, <4 x float>) nounwind
1575 %res = call <4 x float> @llvm.x86.sse.mul.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1578 declare <4 x float> @llvm.x86.sse.mul.ss(<4 x float>, <4 x float>) nounwind readnone
1583 %res = call <4 x float> @llvm.x86.sse.rcp.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1586 declare <4 x float> @llvm.x86.sse.rcp.ps(<4 x float>) nounwind readnone
1591 %res = call <4 x float> @llvm.x86.sse.rcp.ss(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1594 declare <4 x float> @llvm.x86.sse.rcp.ss(<4 x float>) nounwind readnone
1599 %res = call <4 x float> @llvm.x86.sse.rsqrt.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1602 declare <4 x float> @llvm.x86.sse.rsqrt.ps(<4 x float>) nounwind readnone
1607 %res = call <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1610 declare <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float>) nounwind readnone
1615 %res = call <4 x float> @llvm.x86.sse.sqrt.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1618 declare <4 x float> @llvm.x86.sse.sqrt.ps(<4 x float>) nounwind readnone
1623 %res = call <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1626 declare <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float>) nounwind readnone
1632 call void @llvm.x86.sse.stmxcsr(i8* %a0)
1635 declare void @llvm.x86.sse.stmxcsr(i8*) nounwind
1641 call void @llvm.x86.sse.storeu.ps(i8* %a0, <4 x float> %a1)
1644 declare void @llvm.x86.sse.storeu.ps(i8*, <4 x float>) nounwind
1649 %res = call <4 x float> @llvm.x86.sse.sub.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1652 declare <4 x float> @llvm.x86.sse.sub.ss(<4 x float>, <4 x float>) nounwind readnone
1659 %res = call i32 @llvm.x86.sse.ucomieq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1662 declare i32 @llvm.x86.sse.ucomieq.ss(<4 x float>, <4 x float>) nounwind readnone
1669 %res = call i32 @llvm.x86.sse.ucomige.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1672 declare i32 @llvm.x86.sse.ucomige.ss(<4 x float>, <4 x float>) nounwind readnone
1679 %res = call i32 @llvm.x86.sse.ucomigt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1682 declare i32 @llvm.x86.sse.ucomigt.ss(<4 x float>, <4 x float>) nounwind readnone
1689 %res = call i32 @llvm.x86.sse.ucomile.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1692 declare i32 @llvm.x86.sse.ucomile.ss(<4 x float>, <4 x float>) nounwind readnone
1698 %res = call i32 @llvm.x86.sse.ucomilt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1701 declare i32 @llvm.x86.sse.ucomilt.ss(<4 x float>, <4 x float>) nounwind readnone
1708 %res = call i32 @llvm.x86.sse.ucomineq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1711 declare i32 @llvm.x86.sse.ucomineq.ss(<4 x float>, <4 x float>) nounwind readnone
1716 %res = call <16 x i8> @llvm.x86.ssse3.pabs.b.128(<16 x i8> %a0) ; <<16 x i8>> [#uses=1]
1719 declare <16 x i8> @llvm.x86.ssse3.pabs.b.128(<16 x i8>) nounwind readnone
1724 %res = call <4 x i32> @llvm.x86.ssse3.pabs.d.128(<4 x i32> %a0) ; <<4 x i32>> [#uses=1]
1727 declare <4 x i32> @llvm.x86.ssse3.pabs.d.128(<4 x i32>) nounwind readnone
1732 %res = call <8 x i16> @llvm.x86.ssse3.pabs.w.128(<8 x i16> %a0) ; <<8 x i16>> [#uses=1]
1735 declare <8 x i16> @llvm.x86.ssse3.pabs.w.128(<8 x i16>) nounwind readnone
1740 %res = call <4 x i32> @llvm.x86.ssse3.phadd.d.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1743 declare <4 x i32> @llvm.x86.ssse3.phadd.d.128(<4 x i32>, <4 x i32>) nounwind readnone
1748 %res = call <4 x i32> @llvm.x86.ssse3.phadd.sw.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1751 declare <4 x i32> @llvm.x86.ssse3.phadd.sw.128(<4 x i32>, <4 x i32>) nounwind readnone
1756 %res = call <8 x i16> @llvm.x86.ssse3.phadd.w.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1759 declare <8 x i16> @llvm.x86.ssse3.phadd.w.128(<8 x i16>, <8 x i16>) nounwind readnone
1764 %res = call <4 x i32> @llvm.x86.ssse3.phsub.d.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1767 declare <4 x i32> @llvm.x86.ssse3.phsub.d.128(<4 x i32>, <4 x i32>) nounwind readnone
1772 %res = call <8 x i16> @llvm.x86.ssse3.phsub.sw.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1775 declare <8 x i16> @llvm.x86.ssse3.phsub.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
1780 %res = call <8 x i16> @llvm.x86.ssse3.phsub.w.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1783 declare <8 x i16> @llvm.x86.ssse3.phsub.w.128(<8 x i16>, <8 x i16>) nounwind readnone
1788 %res = call <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1791 declare <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
1796 %res = call <8 x i16> @llvm.x86.ssse3.pmul.hr.sw.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1799 declare <8 x i16> @llvm.x86.ssse3.pmul.hr.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
1804 %res = call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
1807 declare <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8>, <16 x i8>) nounwind readnone
1812 %res = call <16 x i8> @llvm.x86.ssse3.psign.b.128(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
1815 declare <16 x i8> @llvm.x86.ssse3.psign.b.128(<16 x i8>, <16 x i8>) nounwind readnone
1820 %res = call <4 x i32> @llvm.x86.ssse3.psign.d.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1823 declare <4 x i32> @llvm.x86.ssse3.psign.d.128(<4 x i32>, <4 x i32>) nounwind readnone
1828 %res = call <8 x i16> @llvm.x86.ssse3.psign.w.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1831 declare <8 x i16> @llvm.x86.ssse3.psign.w.128(<8 x i16>, <8 x i16>) nounwind readnone
1836 %res = call <4 x double> @llvm.x86.avx.addsub.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
1839 declare <4 x double> @llvm.x86
1844 %res = call <8 x float> @llvm.x86.avx.addsub.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
1847 declare <8 x float> @llvm.x86.avx.addsub.ps.256(<8 x float>, <8 x float>) nounwind readnone
1852 %res = call <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double> %a0, <4 x double> %a1, i32 7) ; <<4 x double>> [#uses=1]
1855 declare <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double>, <4 x double>, i32) nounwind readnone
1860 %res = call <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float> %a0, <8 x float> %a1, i32 7) ; <<8 x float>> [#uses=1]
1863 declare <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
1868 %res = call <4 x double> @llvm.x86.avx.blendv.pd.256(<4 x double> %a0, <4 x double> %a1, <4 x double> %a2) ; <<4 x double>> [#uses=1]
1871 declare <4 x double> @llvm.x86.avx.blendv.pd.256(<4 x double>, <4 x double>, <4 x double>) nounwind readnone
1876 %res = call <8 x float> @llvm.x86.avx.blendv.ps.256(<8 x float> %a0, <8 x float> %a1, <8 x float> %a2) ; <<8 x float>> [#uses=1]
1879 declare <8 x float> @llvm.x86.avx.blendv.ps.256(<8 x float>, <8 x float>, <8 x float>) nounwind readnone
1884 %res = call <4 x double> @llvm.x86.avx.cmp.pd.256(<4 x double> %a0, <4 x double> %a1, i8 7) ; <<4 x double>> [#uses=1]
1887 declare <4 x double> @llvm.x86.avx.cmp.pd.256(<4 x double>, <4 x double>, i8) nounwind readnone
1892 %res = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a1, i8 7) ; <<8 x float>> [#uses=1]
1895 declare <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float>, <8 x float>, i8) nounwind readnone
1900 %res = call <4 x float> @llvm.x86.avx.cvt.pd2.ps.256(<4 x double> %a0) ; <<4 x float>> [#uses=1]
1903 declare <4 x float> @llvm.x86.avx.cvt.pd2.ps.256(<4 x double>) nounwind readnone
1908 %res = call <4 x i32> @llvm.x86.avx.cvt.pd2dq.256(<4 x double> %a0) ; <<4 x i32>> [#uses=1]
1911 declare <4 x i32> @llvm.x86.avx.cvt.pd2dq.256(<4 x double>) nounwind readnone
1916 %res = call <4 x double> @llvm.x86.avx.cvt.ps2.pd.256(<4 x float> %a0) ; <<4 x double>> [#uses=1]
1919 declare <4 x double> @llvm.x86.avx.cvt.ps2.pd.256(<4 x float>) nounwind readnone
1924 %res = call <8 x i32> @llvm.x86.avx.cvt.ps2dq.256(<8 x float> %a0) ; <<8 x i32>> [#uses=1]
1927 declare <8 x i32> @llvm.x86.avx.cvt.ps2dq.256(<8 x float>) nounwind readnone
1932 %res = call <4 x double> @llvm.x86.avx.cvtdq2.pd.256(<4 x i32> %a0) ; <<4 x double>> [#uses=1]
1935 declare <4 x double> @llvm.x86.avx.cvtdq2.pd.256(<4 x i32>) nounwind readnone
1940 %res = call <8 x float> @llvm.x86.avx.cvtdq2.ps.256(<8 x i32> %a0) ; <<8 x float>> [#uses=1]
1943 declare <8 x float> @llvm.x86.avx.cvtdq2.ps.256(<8 x i32>) nounwind readnone
1948 %res = call <4 x i32> @llvm.x86.avx.cvtt.pd2dq.256(<4 x double> %a0) ; <<4 x i32>> [#uses=1]
1951 declare <4 x i32> @llvm.x86.avx.cvtt.pd2dq.256(<4 x double>) nounwind readnone
1956 %res = call <8 x i32> @llvm.x86.avx.cvtt.ps2dq.256(<8 x float> %a0) ; <<8 x i32>> [#uses=1]
1959 declare <8 x i32> @llvm.x86.avx.cvtt.ps2dq.256(<8 x float>) nounwind readnone
1964 %res = call <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float> %a0, <8 x float> %a1, i32 7) ; <<8 x float>> [#uses=1]
1967 declare <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
1972 %res = call <4 x double> @llvm.x86.avx.hadd.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
1975 declare <4 x double> @llvm.x86.avx.hadd.pd.256(<4 x double>, <4 x double>) nounwind readnone
1980 %res = call <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
1983 declare <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float>, <8 x float>) nounwind readnone
1988 %res = call <4 x double> @llvm.x86.avx.hsub.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
1991 declare <4 x double> @llvm.x86.avx.hsub.pd.256(<4 x double>, <4 x double>) nounwind readnone
1996 %res = call <8 x float> @llvm.x86.avx.hsub.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
1999 declare <8 x float> @llvm.x86.avx.hsub.ps.256(<8 x float>, <8 x float>) nounwind readnone
2004 %res = call <32 x i8> @llvm.x86.avx.ldu.dq.256(i8* %a0) ; <<32 x i8>> [#uses=1]
2007 declare <32 x i8> @llvm.x86.avx.ldu.dq.256(i8*) nounwind readonly
2012 %res = call <32 x i8> @llvm.x86.avx.loadu.dq.256(i8* %a0) ; <<32 x i8>> [#uses=1]
2015 declare <32 x i8> @llvm.x86.avx.loadu.dq.256(i8*) nounwind readonly
2020 %res = call <4 x double> @llvm.x86.avx.loadu.pd.256(i8* %a0) ; <<4 x double>> [#uses=1]
2023 declare <4 x double> @llvm.x86.avx.loadu.pd.256(i8*) nounwind readonly
2028 %res = call <8 x float> @llvm.x86.avx.loadu.ps.256(i8* %a0) ; <<8 x float>> [#uses=1]
2031 declare <8 x float> @llvm.x86.avx.loadu.ps.256(i8*) nounwind readonly
2036 %res = call <2 x double> @llvm.x86.avx.maskload.pd(i8* %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
2039 declare <2 x double> @llvm.x86.avx.maskload.pd(i8*, <2 x double>) nounwind readonly
2044 %res = call <4 x double> @llvm.x86.avx.maskload.pd.256(i8* %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
2047 declare <4 x double> @llvm.x86.avx.maskload.pd.256(i8*, <4 x double>) nounwind readonly
2052 %res = call <4 x float> @llvm.x86.avx.maskload.ps(i8* %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
2055 declare <4 x float> @llvm.x86.avx.maskload.ps(i8*, <4 x float>) nounwind readonly
2060 %res = call <8 x float> @llvm.x86.avx.maskload.ps.256(i8* %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
2063 declare <8 x float> @llvm.x86.avx.maskload.ps.256(i8*, <8 x float>) nounwind readonly
2068 call void @llvm.x86.avx.maskstore.pd(i8* %a0, <2 x double> %a1, <2 x double> %a2)
2071 declare void @llvm.x86.avx.maskstore.pd(i8*, <2 x double>, <2 x double>) nounwind
2076 call void @llvm.x86.avx.maskstore.pd.256(i8* %a0, <4 x double> %a1, <4 x double> %a2)
2079 declare void @llvm.x86.avx.maskstore.pd.256(i8*, <4 x double>, <4 x double>) nounwind
2084 call void @llvm.x86.avx.maskstore.ps(i8* %a0, <4 x float> %a1, <4 x float> %a2)
2087 declare void @llvm.x86.avx.maskstore.ps(i8*, <4 x float>, <4 x float>) nounwind
2092 call void @llvm.x86.avx.maskstore.ps.256(i8* %a0, <8 x float> %a1, <8 x float> %a2)
2095 declare void @llvm.x86.avx.maskstore.ps.256(i8*, <8 x float>, <8 x float>) nounwind
2100 %res = call <4 x double> @llvm.x86.avx.max.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
2103 declare <4 x double> @llvm.x86.avx.max.pd.256(<4 x double>, <4 x double>) nounwind readnone
2108 %res = call <8 x float> @llvm.x86.avx.max.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
2111 declare <8 x float> @llvm.x86.avx.max.ps.256(<8 x float>, <8 x float>) nounwind readnone
2116 %res = call <4 x double> @llvm.x86.avx.min.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
2119 declare <4 x double> @llvm.x86.avx.min.pd.256(<4 x double>, <4 x double>) nounwind readnone
2124 %res = call <8 x float> @llvm.x86.avx.min.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
2127 declare <8 x float> @llvm.x86.avx.min.ps.256(<8 x float>, <8 x float>) nounwind readnone
2132 %res = call i32 @llvm.x86.avx.movmsk.pd.256(<4 x double> %a0) ; <i32> [#uses=1]
2135 declare i32 @llvm.x86.avx.movmsk.pd.256(<4 x double>) nounwind readnone
2140 %res = call i32 @llvm.x86.avx.movmsk.ps.256(<8 x float> %a0) ; <i32> [#uses=1]
2143 declare i32 @llvm.x86.avx.movmsk.ps.256(<8 x float>) nounwind readnone
2148 call void @llvm.x86.avx.movnt.dq.256(i8* %a0, <4 x i64> %a1)
2151 declare void @llvm.x86.avx.movnt.dq.256(i8*, <4 x i64>) nounwind
2156 call void @llvm.x86.avx.movnt.pd.256(i8* %a0, <4 x double> %a1)
2159 declare void @llvm.x86.avx.movnt.pd.256(i8*, <4 x double>) nounwind
2164 call void @llvm.x86.avx.movnt.ps.256(i8* %a0, <8 x float> %a1)
2167 declare void @llvm.x86.avx.movnt.ps.256(i8*, <8 x float>) nounwind
2173 %res = call i32 @llvm.x86.avx.ptestc.256(<4 x i64> %a0, <4 x i64> %a1) ; <i32> [#uses=1]
2176 declare i32 @llvm.x86.avx.ptestc.256(<4 x i64>, <4 x i64>) nounwind readnone
2183 %res = call i32 @llvm.x86.avx.ptestnzc.256(<4 x i64> %a0, <4 x i64> %a1) ; <i32> [#uses=1]
2186 declare i32 @llvm.x86.avx.ptestnzc.256(<4 x i64>, <4 x i64>) nounwind readnone
2193 %res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a0, <4 x i64> %a1) ; <i32> [#uses=1]
2196 declare i32 @llvm.x86.avx.ptestz.256(<4 x i64>, <4 x i64>) nounwind readnone
2201 %res = call <8 x float> @llvm.x86.avx.rcp.ps.256(<8 x float> %a0) ; <<8 x float>> [#uses=1]
2204 declare <8 x float> @llvm.x86.avx.rcp.ps.256(<8 x float>) nounwind readnone
2209 %res = call <4 x double> @llvm.x86.avx.round.pd.256(<4 x double> %a0, i32 7) ; <<4 x double>> [#uses=1]
2212 declare <4 x double> @llvm.x86.avx.round.pd.256(<4 x double>, i32) nounwind readnone
2217 %res = call <8 x float> @llvm.x86.avx.round.ps.256(<8 x float> %a0, i32 7) ; <<8 x float>> [#uses=1]
2220 declare <8 x float> @llvm.x86.avx.round.ps.256(<8 x float>, i32) nounwind readnone
2225 %res = call <8 x float> @llvm.x86.avx.rsqrt.ps.256(<8 x float> %a0) ; <<8 x float>> [#uses=1]
2228 declare <8 x float> @llvm.x86.avx.rsqrt.ps.256(<8 x float>) nounwind readnone
2233 %res = call <4 x double> @llvm.x86.avx.sqrt.pd.256(<4 x double> %a0) ; <<4 x double>> [#uses=1]
2236 declare <4 x double> @llvm.x86.avx.sqrt.pd.256(<4 x double>) nounwind readnone
2241 %res = call <8 x float> @llvm.x86.avx.sqrt.ps.256(<8 x float> %a0) ; <<8 x float>> [#uses=1]
2244 declare <8 x float> @llvm.x86.avx.sqrt.ps.256(<8 x float>) nounwind readnone
2249 call void @llvm.x86.avx.storeu.dq.256(i8* %a0, <32 x i8> %a1)
2252 declare void @llvm.x86.avx.storeu.dq.256(i8*, <32 x i8>) nounwind
2257 call void @llvm.x86.avx.storeu.pd.256(i8* %a0, <4 x double> %a1)
2260 declare void @llvm.x86.avx.storeu.pd.256(i8*, <4 x double>) nounwind
2265 call void @llvm.x86.avx.storeu.ps.256(i8* %a0, <8 x float> %a1)
2268 declare void @llvm.x86.avx.storeu.ps.256(i8*, <8 x float>) nounwind
2273 %res = call <4 x double> @llvm.x86.avx.vbroadcast.sd.256(i8* %a0) ; <<4 x double>> [#uses=1]
2276 declare <4 x double> @llvm.x86.avx.vbroadcast.sd.256(i8*) nounwind readonly
2281 %res = call <4 x double> @llvm.x86.avx.vbroadcastf128.pd.256(i8* %a0) ; <<4 x double>> [#uses=1]
2284 declare <4 x double> @llvm.x86.avx.vbroadcastf128.pd.256(i8*) nounwind readonly
2289 %res = call <8 x float> @llvm.x86.avx.vbroadcastf128.ps.256(i8* %a0) ; <<8 x float>> [#uses=1]
2292 declare <8 x float> @llvm.x86.avx.vbroadcastf128.ps.256(i8*) nounwind readonly
2297 %res = call <4 x float> @llvm.x86.avx.vbroadcastss(i8* %a0) ; <<4 x float>> [#uses=1]
2300 declare <4 x float> @llvm.x86.avx.vbroadcastss(i8*) nounwind readonly
2305 %res = call <8 x float> @llvm.x86.avx.vbroadcastss.256(i8* %a0) ; <<8 x float>> [#uses=1]
2308 declare <8 x float> @llvm.x86.avx.vbroadcastss.256(i8*) nounwind readonly
2313 %res = call <2 x double> @llvm.x86.avx.vextractf128.pd.256(<4 x double> %a0, i8 7) ; <<2 x double>> [#uses=1]
2316 declare <2 x double> @llvm.x86.avx.vextractf128.pd.256(<4 x double>, i8) nounwind readnone
2321 %res = call <4 x float> @llvm.x86.avx.vextractf128.ps.256(<8 x float> %a0, i8 7) ; <<4 x float>> [#uses=1]
2324 declare <4 x float> @llvm.x86.avx.vextractf128.ps.256(<8 x float>, i8) nounwind readnone
2329 %res = call <4 x i32> @llvm.x86.avx.vextractf128.si.256(<8 x i32> %a0, i8 7) ; <<4 x i32>> [#uses=1]
2332 declare <4 x i32> @llvm.x86.avx.vextractf128.si.256(<8 x i32>, i8) nounwind readnone
2337 %res = call <4 x double> @llvm.x86.avx.vinsertf128.pd.256(<4 x double> %a0, <2 x double> %a1, i8 7) ; <<4 x double>> [#uses=1]
2340 declare <4 x double> @llvm.x86.avx.vinsertf128.pd.256(<4 x double>, <2 x double>, i8) nounwind readnone
2345 %res = call <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float> %a0, <4 x float> %a1, i8 7) ; <<8 x float>> [#uses=1]
2348 declare <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float>, <4 x float>, i8) nounwind readnone
2353 %res = call <8 x i32> @llvm.x86.avx.vinsertf128.si.256(<8 x i32> %a0, <4 x i32> %a1, i8 7) ; <<8 x i32>> [#uses=1]
2356 declare <8 x i32> @llvm.x86.avx.vinsertf128.si.256(<8 x i32>, <4 x i32>, i8) nounwind readnone
2361 %res = call <4 x double> @llvm.x86.avx.vperm2f128.pd.256(<4 x double> %a0, <4 x double> %a1, i8 7) ; <<4 x double>> [#uses=1]
2364 declare <4 x double> @llvm.x86.avx.vperm2f128.pd.256(<4 x double>, <4 x double>, i8) nounwind readnone
2369 %res = call <8 x float> @llvm.x86.avx.vperm2f128.ps.256(<8 x float> %a0, <8 x float> %a1, i8 7) ; <<8 x float>> [#uses=1]
2372 declare <8 x float> @llvm.x86.avx.vperm2f128.ps.256(<8 x float>, <8 x float>, i8) nounwind readnone
2377 %res = call <8 x i32> @llvm.x86.avx.vperm2f128.si.256(<8 x i32> %a0, <8 x i32> %a1, i8 7) ; <<8 x i32>> [#uses=1]
2380 declare <8 x i32> @llvm.x86.avx.vperm2f128.si.256(<8 x i32>, <8 x i32>, i8) nounwind readnone
2385 %res = call <2 x double> @llvm.x86.avx.vpermil.pd(<2 x double> %a0, i8 7) ; <<2 x double>> [#uses=1]
2388 declare <2 x double> @llvm.x86.avx.vpermil.pd(<2 x double>, i8) nounwind readnone
2393 %res = call <4 x double> @llvm.x86.avx.vpermil.pd.256(<4 x double> %a0, i8 7) ; <<4 x double>> [#uses=1]
2396 declare <4 x double> @llvm.x86.avx.vpermil.pd.256(<4 x double>, i8) nounwind readnone
2401 %res = call <4 x float> @llvm.x86.avx.vpermil.ps(<4 x float> %a0, i8 7) ; <<4 x float>> [#uses=1]
2404 declare <4 x float> @llvm.x86.avx.vpermil.ps(<4 x float>, i8) nounwind readnone
2409 %res = call <8 x float> @llvm.x86.avx.vpermil.ps.256(<8 x float> %a0, i8 7) ; <<8 x float>> [#uses=1]
2412 declare <8 x float> @llvm.x86.avx.vpermil.ps.256(<8 x float>, i8) nounwind readnone
2417 %res = call <2 x double> @llvm.x86.avx.vpermilvar.pd(<2 x double> %a0, <2 x i64> %a1) ; <<2 x double>> [#uses=1]
2420 declare <2 x double> @llvm.x86.avx.vpermilvar.pd(<2 x double>, <2 x i64>) nounwind readnone
2425 %res = call <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double> %a0, <4 x i64> %a1) ; <<4 x double>> [#uses=1]
2428 declare <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double>, <4 x i64>) nounwind readnone
2433 %res = call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float> %a0, <4 x i32> %a1) ; <<4 x float>> [#uses=1]
2436 declare <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float>, <4 x i32>) nounwind readnone
2441 %res = call <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float> %a0, <8 x i32> %a1) ; <<8 x float>> [#uses=1]
2444 declare <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float>, <8 x i32>) nounwind readnone
2450 %res = call i32 @llvm.x86.avx.vtestc.pd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
2453 declare i32 @llvm.x86.avx.vtestc.pd(<2 x double>, <2 x double>) nounwind readnone
2459 %res = call i32 @llvm.x86.avx.vtestc.pd.256(<4 x double> %a0, <4 x double> %a1) ; <i32> [#uses=1]
2462 declare i32 @llvm.x86.avx.vtestc.pd.256(<4 x double>, <4 x double>) nounwind readnone
2468 %res = call i32 @llvm.x86.avx.vtestc.ps(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
2471 declare i32 @llvm.x86.avx.vtestc.ps(<4 x float>, <4 x float>) nounwind readnone
2477 %res = call i32 @llvm.x86.avx.vtestc.ps.256(<8 x float> %a0, <8 x float> %a1) ; <i32> [#uses=1]
2480 declare i32 @llvm.x86.avx.vtestc.ps.256(<8 x float>, <8 x float>) nounwind readnone
2487 %res = call i32 @llvm.x86.avx.vtestnzc.pd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
2490 declare i32 @llvm.x86.avx.vtestnzc.pd(<2 x double>, <2 x double>) nounwind readnone
2497 %res = call i32 @llvm.x86.avx.vtestnzc.pd.256(<4 x double> %a0, <4 x double> %a1) ; <i32> [#uses=1]
2500 declare i32 @llvm.x86.avx.vtestnzc.pd.256(<4 x double>, <4 x double>) nounwind readnone
2507 %res = call i32 @llvm.x86.avx.vtestnzc.ps(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
2510 declare i32 @llvm.x86.avx.vtestnzc.ps(<4 x float>, <4 x float>) nounwind readnone
2517 %res = call i32 @llvm.x86.avx.vtestnzc.ps.256(<8 x float> %a0, <8 x float> %a1) ; <i32> [#uses=1]
2520 declare i32 @llvm.x86.avx.vtestnzc.ps.256(<8 x float>, <8 x float>) nounwind readnone
2527 %res = call i32 @llvm.x86.avx.vtestz.pd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
2530 declare i32 @llvm.x86.avx.vtestz.pd(<2 x double>, <2 x double>) nounwind readnone
2537 %res = call i32 @llvm.x86.avx.vtestz.pd.256(<4 x double> %a0, <4 x double> %a1) ; <i32> [#uses=1]
2540 declare i32 @llvm.x86.avx.vtestz.pd.256(<4 x double>, <4 x double>) nounwind readnone
2547 %res = call i32 @llvm.x86.avx.vtestz.ps(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
2550 declare i32 @llvm.x86.avx.vtestz.ps(<4 x float>, <4 x float>) nounwind readnone
2557 %res = call i32 @llvm.x86.avx.vtestz.ps.256(<8 x float> %a0, <8 x float> %a1) ; <i32> [#uses=1]
2560 declare i32 @llvm.x86.avx.vtestz.ps.256(<8 x float>, <8 x float>) nounwind readnone
2565 call void @llvm.x86.avx.vzeroall()
2568 declare void @llvm.x86.avx.vzeroall() nounwind
2573 call void @llvm.x86.avx.vzeroupper()
2576 declare void @llvm.x86.avx.vzeroupper() nounwind
