Lines Matching full:x86
1 ; RUN: llc < %s -mtriple=x86_64-apple-darwin -march=x86 -mcpu=corei7-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 <2 x double> @llvm.x86.sse2.max.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
254 declare <2 x double> @llvm.x86.sse2.max.pd(<2 x double>, <2 x double>) nounwind readnone
259 %res = call <2 x double> @llvm.x86.sse2.max.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
262 declare <2 x double> @llvm.x86.sse2.max.sd(<2 x double>, <2 x double>) nounwind readnone
267 %res = call <2 x double> @llvm.x86.sse2.min.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
270 declare <2 x double> @llvm.x86.sse2.min.pd(<2 x double>, <2 x double>) nounwind readnone
275 %res = call <2 x double> @llvm.x86.sse2.min.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
278 declare <2 x double> @llvm.x86.sse2.min.sd(<2 x double>, <2 x double>) nounwind readnone
283 %res = call i32 @llvm.x86.sse2.movmsk.pd(<2 x double> %a0) ; <i32> [#uses=1]
286 declare i32 @llvm.x86.sse2.movmsk.pd(<2 x double>) nounwind readnone
294 %res = call <2 x double> @llvm.x86.sse2.mul.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
297 declare <2 x double> @llvm.x86.sse2.mul.sd(<2 x double>, <2 x double>) nounwind readnone
302 %res = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a0, <4 x i32> %a1) ; <<8 x i16>> [#uses=1]
305 declare <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32>, <4 x i32>) nounwind readnone
310 %res = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a0, <8 x i16> %a1) ; <<16 x i8>> [#uses=1]
313 declare <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16>, <8 x i16>) nounwind readnone
318 %res = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a0, <8 x i16> %a1) ; <<16 x i8>> [#uses=1]
321 declare <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16>, <8 x i16>) nounwind readnone
326 %res = call <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
329 declare <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8>, <16 x i8>) nounwind readnone
334 %res = call <8 x i16> @llvm.x86.sse2.padds.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
337 declare <8 x i16> @llvm.x86.sse2.padds.w(<8 x i16>, <8 x i16>) nounwind readnone
342 %res = call <16 x i8> @llvm.x86.sse2.paddus.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
345 declare <16 x i8> @llvm.x86.sse2.paddus.b(<16 x i8>, <16 x i8>) nounwind readnone
350 %res = call <8 x i16> @llvm.x86.sse2.paddus.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
353 declare <8 x i16> @llvm.x86.sse2.paddus.w(<8 x i16>, <8 x i16>) nounwind readnone
358 %res = call <16 x i8> @llvm.x86.sse2.pavg.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
361 declare <16 x i8> @llvm.x86.sse2.pavg.b(<16 x i8>, <16 x i8>) nounwind readnone
366 %res = call <8 x i16> @llvm.x86.sse2.pavg.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
369 declare <8 x i16> @llvm.x86.sse2.pavg.w(<8 x i16>, <8 x i16>) nounwind readnone
374 %res = call <4 x i32> @llvm.x86.sse2.pmadd.wd(<8 x i16> %a0, <8 x i16> %a1) ; <<4 x i32>> [#uses=1]
377 declare <4 x i32> @llvm.x86.sse2.pmadd.wd(<8 x i16>, <8 x i16>) nounwind readnone
382 %res = call <8 x i16> @llvm.x86.sse2.pmaxs.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
385 declare <8 x i16> @llvm.x86.sse2.pmaxs.w(<8 x i16>, <8 x i16>) nounwind readnone
390 %res = call <16 x i8> @llvm.x86.sse2.pmaxu.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
393 declare <16 x i8> @llvm.x86.sse2.pmaxu.b(<16 x i8>, <16 x i8>) nounwind readnone
398 %res = call <8 x i16> @llvm.x86.sse2.pmins.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
401 declare <8 x i16> @llvm.x86.sse2.pmins.w(<8 x i16>, <8 x i16>) nounwind readnone
406 %res = call <16 x i8> @llvm.x86.sse2.pminu.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
409 declare <16 x i8> @llvm.x86.sse2.pminu.b(<16 x i8>, <16 x i8>) nounwind readnone
414 %res = call i32 @llvm.x86.sse2.pmovmskb.128(<16 x i8> %a0) ; <i32> [#uses=1]
417 declare i32 @llvm.x86.sse2.pmovmskb.128(<16 x i8>) nounwind readnone
422 %res = call <8 x i16> @llvm.x86.sse2.pmulh.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
425 declare <8 x i16> @llvm.x86.sse2.pmulh.w(<8 x i16>, <8 x i16>) nounwind readnone
430 %res = call <8 x i16> @llvm.x86.sse2.pmulhu.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
433 declare <8 x i16> @llvm.x86.sse2.pmulhu.w(<8 x i16>, <8 x i16>) nounwind readnone
438 %res = call <2 x i64> @llvm.x86.sse2.pmulu.dq(<4 x i32> %a0, <4 x i32> %a1) ; <<2 x i64>> [#uses=1]
441 declare <2 x i64> @llvm.x86.sse2.pmulu.dq(<4 x i32>, <4 x i32>) nounwind readnone
446 %res = call <2 x i64> @llvm.x86.sse2.psad.bw(<16 x i8> %a0, <16 x i8> %a1) ; <<2 x i64>> [#uses=1]
449 declare <2 x i64> @llvm.x86
454 %res = call <4 x i32> @llvm.x86.sse2.psll.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
457 declare <4 x i32> @llvm.x86.sse2.psll.d(<4 x i32>, <4 x i32>) nounwind readnone
462 %res = call <2 x i64> @llvm.x86.sse2.psll.dq(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
465 declare <2 x i64> @llvm.x86.sse2.psll.dq(<2 x i64>, i32) nounwind readnone
470 %res = call <2 x i64> @llvm.x86.sse2.psll.dq.bs(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
473 declare <2 x i64> @llvm.x86.sse2.psll.dq.bs(<2 x i64>, i32) nounwind readnone
478 %res = call <2 x i64> @llvm.x86.sse2.psll.q(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
481 declare <2 x i64> @llvm.x86.sse2.psll.q(<2 x i64>, <2 x i64>) nounwind readnone
486 %res = call <8 x i16> @llvm.x86.sse2.psll.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
489 declare <8 x i16> @llvm.x86.sse2.psll.w(<8 x i16>, <8 x i16>) nounwind readnone
494 %res = call <4 x i32> @llvm.x86.sse2.pslli.d(<4 x i32> %a0, i32 7) ; <<4 x i32>> [#uses=1]
497 declare <4 x i32> @llvm.x86.sse2.pslli.d(<4 x i32>, i32) nounwind readnone
502 %res = call <2 x i64> @llvm.x86.sse2.pslli.q(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
505 declare <2 x i64> @llvm.x86.sse2.pslli.q(<2 x i64>, i32) nounwind readnone
510 %res = call <8 x i16> @llvm.x86.sse2.pslli.w(<8 x i16> %a0, i32 7) ; <<8 x i16>> [#uses=1]
513 declare <8 x i16> @llvm.x86.sse2.pslli.w(<8 x i16>, i32) nounwind readnone
518 %res = call <4 x i32> @llvm.x86.sse2.psra.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
521 declare <4 x i32> @llvm.x86.sse2.psra.d(<4 x i32>, <4 x i32>) nounwind readnone
526 %res = call <8 x i16> @llvm.x86.sse2.psra.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
529 declare <8 x i16> @llvm.x86.sse2.psra.w(<8 x i16>, <8 x i16>) nounwind readnone
534 %res = call <4 x i32> @llvm.x86.sse2.psrai.d(<4 x i32> %a0, i32 7) ; <<4 x i32>> [#uses=1]
537 declare <4 x i32> @llvm.x86.sse2.psrai.d(<4 x i32>, i32) nounwind readnone
542 %res = call <8 x i16> @llvm.x86.sse2.psrai.w(<8 x i16> %a0, i32 7) ; <<8 x i16>> [#uses=1]
545 declare <8 x i16> @llvm.x86.sse2.psrai.w(<8 x i16>, i32) nounwind readnone
550 %res = call <4 x i32> @llvm.x86.sse2.psrl.d(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
553 declare <4 x i32> @llvm.x86.sse2.psrl.d(<4 x i32>, <4 x i32>) nounwind readnone
558 %res = call <2 x i64> @llvm.x86.sse2.psrl.dq(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
561 declare <2 x i64> @llvm.x86.sse2.psrl.dq(<2 x i64>, i32) nounwind readnone
566 %res = call <2 x i64> @llvm.x86.sse2.psrl.dq.bs(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
569 declare <2 x i64> @llvm.x86.sse2.psrl.dq.bs(<2 x i64>, i32) nounwind readnone
574 %res = call <2 x i64> @llvm.x86.sse2.psrl.q(<2 x i64> %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
577 declare <2 x i64> @llvm.x86.sse2.psrl.q(<2 x i64>, <2 x i64>) nounwind readnone
582 %res = call <8 x i16> @llvm.x86.sse2.psrl.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
585 declare <8 x i16> @llvm.x86.sse2.psrl.w(<8 x i16>, <8 x i16>) nounwind readnone
590 %res = call <4 x i32> @llvm.x86.sse2.psrli.d(<4 x i32> %a0, i32 7) ; <<4 x i32>> [#uses=1]
593 declare <4 x i32> @llvm.x86.sse2.psrli.d(<4 x i32>, i32) nounwind readnone
598 %res = call <2 x i64> @llvm.x86.sse2.psrli.q(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
601 declare <2 x i64> @llvm.x86.sse2.psrli.q(<2 x i64>, i32) nounwind readnone
606 %res = call <8 x i16> @llvm.x86.sse2.psrli.w(<8 x i16> %a0, i32 7) ; <<8 x i16>> [#uses=1]
609 declare <8 x i16> @llvm.x86.sse2.psrli.w(<8 x i16>, i32) nounwind readnone
614 %res = call <16 x i8> @llvm.x86.sse2.psubs.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
617 declare <16 x i8> @llvm.x86.sse2.psubs.b(<16 x i8>, <16 x i8>) nounwind readnone
622 %res = call <8 x i16> @llvm.x86.sse2.psubs.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
625 declare <8 x i16> @llvm.x86.sse2.psubs.w(<8 x i16>, <8 x i16>) nounwind readnone
630 %res = call <16 x i8> @llvm.x86.sse2.psubus.b(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
633 declare <16 x i8> @llvm.x86.sse2.psubus.b(<16 x i8>, <16 x i8>) nounwind readnone
638 %res = call <8 x i16> @llvm.x86.sse2.psubus.w(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
641 declare <8 x i16> @llvm.x86.sse2.psubus.w(<8 x i16>, <8 x i16>) nounwind readnone
646 %res = call <2 x double> @llvm.x86.sse2.sqrt.pd(<2 x double> %a0) ; <<2 x double>> [#uses=1]
649 declare <2 x double> @llvm.x86.sse2.sqrt.pd(<2 x double>) nounwind readnone
654 %res = call <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double> %a0) ; <<2 x double>> [#uses=1]
657 declare <2 x double> @llvm.x86.sse2.sqrt.sd(<2 x double>) nounwind readnone
664 call void @llvm.x86.sse2.storel.dq(i8* %a0, <4 x i32> %a1)
667 declare void @llvm.x86.sse2.storel.dq(i8*, <4 x i32>) nounwind
676 call void @llvm.x86.sse2.storeu.dq(i8* %a0, <16 x i8> %a2)
679 declare void @llvm.x86.sse2.storeu.dq(i8*, <16 x i8>) nounwind
688 call void @llvm.x86.sse2.storeu.pd(i8* %a0, <2 x double> %a2)
691 declare void @llvm.x86.sse2.storeu.pd(i8*, <2 x double>) nounwind
697 %res = call <2 x double> @llvm.x86.sse2.sub.sd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
700 declare <2 x double> @llvm.x86.sse2.sub.sd(<2 x double>, <2 x double>) nounwind readnone
707 %res = call i32 @llvm.x86.sse2.ucomieq.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
710 declare i32 @llvm.x86.sse2.ucomieq.sd(<2 x double>, <2 x double>) nounwind readnone
717 %res = call i32 @llvm.x86.sse2.ucomige.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
720 declare i32 @llvm.x86.sse2.ucomige.sd(<2 x double>, <2 x double>) nounwind readnone
727 %res = call i32 @llvm.x86.sse2.ucomigt.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
730 declare i32 @llvm.x86.sse2.ucomigt.sd(<2 x double>, <2 x double>) nounwind readnone
737 %res = call i32 @llvm.x86.sse2.ucomile.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
740 declare i32 @llvm.x86.sse2.ucomile.sd(<2 x double>, <2 x double>) nounwind readnone
746 %res = call i32 @llvm.x86.sse2.ucomilt.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
749 declare i32 @llvm.x86.sse2.ucomilt.sd(<2 x double>, <2 x double>) nounwind readnone
756 %res = call i32 @llvm.x86.sse2.ucomineq.sd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
759 declare i32 @llvm.x86.sse2.ucomineq.sd(<2 x double>, <2 x double>) nounwind readnone
764 %res = call <2 x double> @llvm.x86.sse3.addsub.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
767 declare <2 x double> @llvm.x86.sse3.addsub.pd(<2 x double>, <2 x double>) nounwind readnone
772 %res = call <4 x float> @llvm.x86.sse3.addsub.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
775 declare <4 x float> @llvm.x86.sse3.addsub.ps(<4 x float>, <4 x float>) nounwind readnone
780 %res = call <2 x double> @llvm.x86.sse3.hadd.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
783 declare <2 x double> @llvm.x86.sse3.hadd.pd(<2 x double>, <2 x double>) nounwind readnone
788 %res = call <4 x float> @llvm.x86.sse3.hadd.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
791 declare <4 x float> @llvm.x86.sse3.hadd.ps(<4 x float>, <4 x float>) nounwind readnone
796 %res = call <2 x double> @llvm.x86.sse3.hsub.pd(<2 x double> %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
799 declare <2 x double> @llvm.x86.sse3.hsub.pd(<2 x double>, <2 x double>) nounwind readnone
804 %res = call <4 x float> @llvm.x86.sse3.hsub.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
807 declare <4 x float> @llvm.x86.sse3.hsub.ps(<4 x float>, <4 x float>) nounwind readnone
813 %res = call <16 x i8> @llvm.x86.sse3.ldu.dq(i8* %a0) ; <<16 x i8>> [#uses=1]
816 declare <16 x i8> @llvm.x86.sse3.ldu.dq(i8*) nounwind readonly
821 %res = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
824 declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i32) nounwind readnone
829 %res = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
832 declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i32) nounwind readnone
837 %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]
840 declare <2 x double> @llvm.x86.sse41.blendvpd(<2 x double>, <2 x double>, <2 x double>) nounwind readnone
845 %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]
848 declare <4 x float> @llvm.x86.sse41.blendvps(<4 x float>, <4 x float>, <4 x float>) nounwind readnone
853 %res = call <2 x double> @llvm.x86.sse41.dppd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
856 declare <2 x double> @llvm.x86.sse41.dppd(<2 x double>, <2 x double>, i32) nounwind readnone
861 %res = call <4 x float> @llvm.x86.sse41.dpps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
864 declare <4 x float> @llvm.x86.sse41.dpps(<4 x float>, <4 x float>, i32) nounwind readnone
869 %res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
872 declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i32) nounwind readnone
878 %res = call <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8> %a0, <16 x i8> %a1, i32 7) ; <<8 x i16>> [#uses=1]
881 declare <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8>, <16 x i8>, i32) nounwind readnone
886 %res = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a0, <4 x i32> %a1) ; <<8 x i16>> [#uses=1]
889 declare <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32>, <4 x i32>) nounwind readnone
894 %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]
897 declare <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8>, <16 x i8>, <16 x i8>) nounwind readnone
902 %res = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %a0, <8 x i16> %a1, i32 7) ; <<8 x i16>> [#uses=1]
905 declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i32) nounwind readnone
910 %res = call <8 x i16> @llvm.x86.sse41.phminposuw(<8 x i16> %a0) ; <<8 x i16>> [#uses=1]
913 declare <8 x i16> @llvm.x86.sse41.phminposuw(<8 x i16>) nounwind readnone
918 %res = call <16 x i8> @llvm.x86.sse41.pmaxsb(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
921 declare <16 x i8> @llvm.x86.sse41.pmaxsb(<16 x i8>, <16 x i8>) nounwind readnone
926 %res = call <4 x i32> @llvm.x86.sse41.pmaxsd(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
929 declare <4 x i32> @llvm.x86.sse41.pmaxsd(<4 x i32>, <4 x i32>) nounwind readnone
934 %res = call <4 x i32> @llvm.x86.sse41.pmaxud(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
937 declare <4 x i32> @llvm.x86.sse41.pmaxud(<4 x i32>, <4 x i32>) nounwind readnone
942 %res = call <8 x i16> @llvm.x86.sse41.pmaxuw(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
945 declare <8 x i16> @llvm.x86.sse41.pmaxuw(<8 x i16>, <8 x i16>) nounwind readnone
950 %res = call <16 x i8> @llvm.x86.sse41.pminsb(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
953 declare <16 x i8> @llvm.x86.sse41.pminsb(<16 x i8>, <16 x i8>) nounwind readnone
958 %res = call <4 x i32> @llvm.x86.sse41.pminsd(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
961 declare <4 x i32> @llvm.x86.sse41.pminsd(<4 x i32>, <4 x i32>) nounwind readnone
966 %res = call <4 x i32> @llvm.x86.sse41.pminud(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
969 declare <4 x i32> @llvm.x86.sse41.pminud(<4 x i32>, <4 x i32>) nounwind readnone
974 %res = call <8 x i16> @llvm.x86.sse41.pminuw(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
977 declare <8 x i16> @llvm.x86.sse41.pminuw(<8 x i16>, <8 x i16>) nounwind readnone
982 %res = call <4 x i32> @llvm.x86.sse41.pmovsxbd(<16 x i8> %a0) ; <<4 x i32>> [#uses=1]
985 declare <4 x i32> @llvm.x86.sse41.pmovsxbd(<16 x i8>) nounwind readnone
990 %res = call <2 x i64> @llvm.x86.sse41.pmovsxbq(<16 x i8> %a0) ; <<2 x i64>> [#uses=1]
993 declare <2 x i64> @llvm.x86.sse41.pmovsxbq(<16 x i8>) nounwind readnone
998 %res = call <8 x i16> @llvm.x86.sse41.pmovsxbw(<16 x i8> %a0) ; <<8 x i16>> [#uses=1]
1001 declare <8 x i16> @llvm.x86.sse41.pmovsxbw(<16 x i8>) nounwind readnone
1006 %res = call <2 x i64> @llvm.x86.sse41.pmovsxdq(<4 x i32> %a0) ; <<2 x i64>> [#uses=1]
1009 declare <2 x i64> @llvm.x86.sse41.pmovsxdq(<4 x i32>) nounwind readnone
1014 %res = call <4 x i32> @llvm.x86.sse41.pmovsxwd(<8 x i16> %a0) ; <<4 x i32>> [#uses=1]
1017 declare <4 x i32> @llvm.x86.sse41.pmovsxwd(<8 x i16>) nounwind readnone
1022 %res = call <2 x i64> @llvm.x86.sse41.pmovsxwq(<8 x i16> %a0) ; <<2 x i64>> [#uses=1]
1025 declare <2 x i64> @llvm.x86.sse41.pmovsxwq(<8 x i16>) nounwind readnone
1030 %res = call <4 x i32> @llvm.x86.sse41.pmovzxbd(<16 x i8> %a0) ; <<4 x i32>> [#uses=1]
1033 declare <4 x i32> @llvm.x86.sse41.pmovzxbd(<16 x i8>) nounwind readnone
1038 %res = call <2 x i64> @llvm.x86.sse41.pmovzxbq(<16 x i8> %a0) ; <<2 x i64>> [#uses=1]
1041 declare <2 x i64> @llvm.x86.sse41.pmovzxbq(<16 x i8>) nounwind readnone
1046 %res = call <8 x i16> @llvm.x86.sse41.pmovzxbw(<16 x i8> %a0) ; <<8 x i16>> [#uses=1]
1049 declare <8 x i16> @llvm.x86.sse41.pmovzxbw(<16 x i8>) nounwind readnone
1054 %res = call <2 x i64> @llvm.x86.sse41.pmovzxdq(<4 x i32> %a0) ; <<2 x i64>> [#uses=1]
1057 declare <2 x i64> @llvm.x86.sse41.pmovzxdq(<4 x i32>) nounwind readnone
1062 %res = call <4 x i32> @llvm.x86.sse41.pmovzxwd(<8 x i16> %a0) ; <<4 x i32>> [#uses=1]
1065 declare <4 x i32> @llvm.x86.sse41.pmovzxwd(<8 x i16>) nounwind readnone
1070 %res = call <2 x i64> @llvm.x86.sse41.pmovzxwq(<8 x i16> %a0) ; <<2 x i64>> [#uses=1]
1073 declare <2 x i64> @llvm.x86.sse41.pmovzxwq(<8 x i16>) nounwind readnone
1078 %res = call <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32> %a0, <4 x i32> %a1) ; <<2 x i64>> [#uses=1]
1081 declare <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32>, <4 x i32>) nounwind readnone
1087 %res = call i32 @llvm.x86.sse41.ptestc(<2 x i64> %a0, <2 x i64> %a1) ; <i32> [#uses=1]
1090 declare i32 @llvm.x86.sse41.ptestc(<2 x i64>, <2 x i64>) nounwind readnone
1097 %res = call i32 @llvm.x86.sse41.ptestnzc(<2 x i64> %a0, <2 x i64> %a1) ; <i32> [#uses=1]
1100 declare i32 @llvm.x86.sse41.ptestnzc(<2 x i64>, <2 x i64>) nounwind readnone
1107 %res = call i32 @llvm.x86.sse41.ptestz(<2 x i64> %a0, <2 x i64> %a1) ; <i32> [#uses=1]
1110 declare i32 @llvm.x86.sse41.ptestz(<2 x i64>, <2 x i64>) nounwind readnone
1115 %res = call <2 x double> @llvm.x86.sse41.round.pd(<2 x double> %a0, i32 7) ; <<2 x double>> [#uses=1]
1118 declare <2 x double> @llvm.x86.sse41.round.pd(<2 x double>, i32) nounwind readnone
1123 %res = call <4 x float> @llvm.x86.sse41.round.ps(<4 x float> %a0, i32 7) ; <<4 x float>> [#uses=1]
1126 declare <4 x float> @llvm.x86.sse41.round.ps(<4 x float>, i32) nounwind readnone
1131 %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]
1134 declare <2 x double> @llvm.x86.sse41.round.sd(<2 x double>, <2 x double>, i32) nounwind readnone
1139 %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]
1142 declare <4 x float> @llvm.x86.sse41.round.ss(<4 x float>, <4 x float>, i32) nounwind readnone
1150 %res = call i32 @llvm.x86.sse42.pcmpestri128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1153 declare i32 @llvm.x86.sse42.pcmpestri128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1163 %res = call i32 @llvm.x86.sse42.pcmpestri128(<16 x i8> %1, i32 7, <16 x i8> %2, i32 7, i8 7) ; <i32> [#uses=1]
1173 %res = call i32 @llvm.x86.sse42.pcmpestria128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1176 declare i32 @llvm.x86.sse42.pcmpestria128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1184 %res = call i32 @llvm.x86.sse42.pcmpestric128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1187 declare i32 @llvm.x86.sse42.pcmpestric128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1195 %res = call i32 @llvm.x86.sse42.pcmpestrio128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1198 declare i32 @llvm.x86.sse42.pcmpestrio128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1206 %res = call i32 @llvm.x86.sse42.pcmpestris128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1209 declare i32 @llvm.x86.sse42.pcmpestris128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1217 %res = call i32 @llvm.x86.sse42.pcmpestriz128(<16 x i8> %a0, i32 7, <16 x i8> %a2, i32 7, i8 7) ; <i32> [#uses=1]
1220 declare i32 @llvm.x86.sse42.pcmpestriz128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1228 %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]
1231 declare <16 x i8> @llvm.x86.sse42.pcmpestrm128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
1240 %res = call <16 x i8> @llvm.x86.sse42.pcmpestrm128(<16 x i8> %a0, i32 7, <16 x i8> %1, i32 7, i8 7) ; <<16 x i8>> [#uses=1]
1248 %res = call i32 @llvm.x86.sse42.pcmpistri128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1251 declare i32 @llvm.x86.sse42.pcmpistri128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1259 %res = call i32 @llvm.x86.sse42.pcmpistri128(<16 x i8> %1, <16 x i8> %2, i8 7) ; <i32> [#uses=1]
1267 %res = call i32 @llvm.x86.sse42.pcmpistria128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1270 declare i32 @llvm.x86.sse42.pcmpistria128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1276 %res = call i32 @llvm.x86.sse42.pcmpistric128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1279 declare i32 @llvm.x86.sse42.pcmpistric128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1285 %res = call i32 @llvm.x86.sse42.pcmpistrio128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1288 declare i32 @llvm.x86.sse42.pcmpistrio128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1294 %res = call i32 @llvm.x86.sse42.pcmpistris128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1297 declare i32 @llvm.x86.sse42.pcmpistris128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1303 %res = call i32 @llvm.x86.sse42.pcmpistriz128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <i32> [#uses=1]
1306 declare i32 @llvm.x86.sse42.pcmpistriz128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1312 %res = call <16 x i8> @llvm.x86.sse42.pcmpistrm128(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <<16 x i8>> [#uses=1]
1315 declare <16 x i8> @llvm.x86.sse42.pcmpistrm128(<16 x i8>, <16 x i8>, i8) nounwind readnone
1322 %res = call <16 x i8> @llvm.x86.sse42.pcmpistrm128(<16 x i8> %a0, <16 x i8> %1, i8 7) ; <<16 x i8>> [#uses=1]
1329 %res = call <4 x float> @llvm.x86.sse.add.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1332 declare <4 x float> @llvm.x86.sse.add.ss(<4 x float>, <4 x float>) nounwind readnone
1337 %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]
1340 declare <4 x float> @llvm.x86.sse.cmp.ps(<4 x float>, <4 x float>, i8) nounwind readnone
1345 %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]
1348 declare <4 x float> @llvm.x86.sse.cmp.ss(<4 x float>, <4 x float>, i8) nounwind readnone
1355 %res = call i32 @llvm.x86.sse.comieq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1358 declare i32 @llvm.x86.sse.comieq.ss(<4 x float>, <4 x float>) nounwind readnone
1365 %res = call i32 @llvm.x86
1368 declare i32 @llvm.x86.sse.comige.ss(<4 x float>, <4 x float>) nounwind readnone
1375 %res = call i32 @llvm.x86.sse.comigt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1378 declare i32 @llvm.x86.sse.comigt.ss(<4 x float>, <4 x float>) nounwind readnone
1385 %res = call i32 @llvm.x86.sse.comile.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1388 declare i32 @llvm.x86.sse.comile.ss(<4 x float>, <4 x float>) nounwind readnone
1394 %res = call i32 @llvm.x86.sse.comilt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1397 declare i32 @llvm.x86.sse.comilt.ss(<4 x float>, <4 x float>) nounwind readnone
1404 %res = call i32 @llvm.x86.sse.comineq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1407 declare i32 @llvm.x86.sse.comineq.ss(<4 x float>, <4 x float>) nounwind readnone
1413 %res = call <4 x float> @llvm.x86.sse.cvtsi2ss(<4 x float> %a0, i32 7) ; <<4 x float>> [#uses=1]
1416 declare <4 x float> @llvm.x86.sse.cvtsi2ss(<4 x float>, i32) nounwind readnone
1421 %res = call i32 @llvm.x86.sse.cvtss2si(<4 x float> %a0) ; <i32> [#uses=1]
1424 declare i32 @llvm.x86.sse.cvtss2si(<4 x float>) nounwind readnone
1429 %res = call i32 @llvm.x86.sse.cvttss2si(<4 x float> %a0) ; <i32> [#uses=1]
1432 declare i32 @llvm.x86.sse.cvttss2si(<4 x float>) nounwind readnone
1437 %res = call <4 x float> @llvm.x86.sse.div.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1440 declare <4 x float> @llvm.x86.sse.div.ss(<4 x float>, <4 x float>) nounwind readnone
1446 call void @llvm.x86.sse.ldmxcsr(i8* %a0)
1449 declare void @llvm.x86.sse.ldmxcsr(i8*) nounwind
1455 %res = call <4 x float> @llvm.x86.sse.max.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1458 declare <4 x float> @llvm.x86.sse.max.ps(<4 x float>, <4 x float>) nounwind readnone
1463 %res = call <4 x float> @llvm.x86.sse.max.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1466 declare <4 x float> @llvm.x86.sse.max.ss(<4 x float>, <4 x float>) nounwind readnone
1471 %res = call <4 x float> @llvm.x86.sse.min.ps(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1474 declare <4 x float> @llvm.x86.sse.min.ps(<4 x float>, <4 x float>) nounwind readnone
1479 %res = call <4 x float> @llvm.x86.sse.min.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1482 declare <4 x float> @llvm.x86.sse.min.ss(<4 x float>, <4 x float>) nounwind readnone
1487 %res = call i32 @llvm.x86.sse.movmsk.ps(<4 x float> %a0) ; <i32> [#uses=1]
1490 declare i32 @llvm.x86.sse.movmsk.ps(<4 x float>) nounwind readnone
1496 %res = call <4 x float> @llvm.x86.sse.mul.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1499 declare <4 x float> @llvm.x86.sse.mul.ss(<4 x float>, <4 x float>) nounwind readnone
1504 %res = call <4 x float> @llvm.x86.sse.rcp.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1507 declare <4 x float> @llvm.x86.sse.rcp.ps(<4 x float>) nounwind readnone
1512 %res = call <4 x float> @llvm.x86.sse.rcp.ss(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1515 declare <4 x float> @llvm.x86.sse.rcp.ss(<4 x float>) nounwind readnone
1520 %res = call <4 x float> @llvm.x86.sse.rsqrt.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1523 declare <4 x float> @llvm.x86.sse.rsqrt.ps(<4 x float>) nounwind readnone
1528 %res = call <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1531 declare <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float>) nounwind readnone
1536 %res = call <4 x float> @llvm.x86.sse.sqrt.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1539 declare <4 x float> @llvm.x86.sse.sqrt.ps(<4 x float>) nounwind readnone
1544 %res = call <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float> %a0) ; <<4 x float>> [#uses=1]
1547 declare <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float>) nounwind readnone
1553 call void @llvm.x86.sse.stmxcsr(i8* %a0)
1556 declare void @llvm.x86.sse.stmxcsr(i8*) nounwind
1562 call void @llvm.x86.sse.storeu.ps(i8* %a0, <4 x float> %a1)
1565 declare void @llvm.x86.sse.storeu.ps(i8*, <4 x float>) nounwind
1570 %res = call <4 x float> @llvm.x86.sse.sub.ss(<4 x float> %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
1573 declare <4 x float> @llvm.x86.sse.sub.ss(<4 x float>, <4 x float>) nounwind readnone
1580 %res = call i32 @llvm.x86.sse.ucomieq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1583 declare i32 @llvm.x86.sse.ucomieq.ss(<4 x float>, <4 x float>) nounwind readnone
1590 %res = call i32 @llvm.x86.sse.ucomige.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1593 declare i32 @llvm.x86.sse.ucomige.ss(<4 x float>, <4 x float>) nounwind readnone
1600 %res = call i32 @llvm.x86.sse.ucomigt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1603 declare i32 @llvm.x86.sse.ucomigt.ss(<4 x float>, <4 x float>) nounwind readnone
1610 %res = call i32 @llvm.x86.sse.ucomile.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1613 declare i32 @llvm.x86.sse.ucomile.ss(<4 x float>, <4 x float>) nounwind readnone
1619 %res = call i32 @llvm.x86.sse.ucomilt.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1622 declare i32 @llvm.x86.sse.ucomilt.ss(<4 x float>, <4 x float>) nounwind readnone
1629 %res = call i32 @llvm.x86.sse.ucomineq.ss(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
1632 declare i32 @llvm.x86.sse.ucomineq.ss(<4 x float>, <4 x float>) nounwind readnone
1637 %res = call <16 x i8> @llvm.x86.ssse3.pabs.b.128(<16 x i8> %a0) ; <<16 x i8>> [#uses=1]
1640 declare <16 x i8> @llvm.x86.ssse3.pabs.b.128(<16 x i8>) nounwind readnone
1645 %res = call <4 x i32> @llvm.x86.ssse3.pabs.d.128(<4 x i32> %a0) ; <<4 x i32>> [#uses=1]
1648 declare <4 x i32> @llvm.x86.ssse3.pabs.d.128(<4 x i32>) nounwind readnone
1653 %res = call <8 x i16> @llvm.x86.ssse3.pabs.w.128(<8 x i16> %a0) ; <<8 x i16>> [#uses=1]
1656 declare <8 x i16> @llvm.x86.ssse3.pabs.w.128(<8 x i16>) nounwind readnone
1661 %res = call <4 x i32> @llvm.x86.ssse3.phadd.d.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1664 declare <4 x i32> @llvm.x86.ssse3.phadd.d.128(<4 x i32>, <4 x i32>) nounwind readnone
1669 %res = call <8 x i16> @llvm.x86.ssse3.phadd.sw.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1672 declare <8 x i16> @llvm.x86.ssse3.phadd.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
1677 %res = call <8 x i16> @llvm.x86.ssse3.phadd.w.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1680 declare <8 x i16> @llvm.x86.ssse3.phadd.w.128(<8 x i16>, <8 x i16>) nounwind readnone
1685 %res = call <4 x i32> @llvm.x86.ssse3.phsub.d.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1688 declare <4 x i32> @llvm.x86.ssse3.phsub.d.128(<4 x i32>, <4 x i32>) nounwind readnone
1693 %res = call <8 x i16> @llvm.x86.ssse3.phsub.sw.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1696 declare <8 x i16> @llvm.x86.ssse3.phsub.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
1701 %res = call <8 x i16> @llvm.x86.ssse3.phsub.w.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1704 declare <8 x i16> @llvm.x86.ssse3.phsub.w.128(<8 x i16>, <8 x i16>) nounwind readnone
1709 %res = call <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<16 x i8> %a0, <16 x i8> %a1) ; <<8 x i16>> [#uses=1]
1712 declare <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<16 x i8>, <16 x i8>) nounwind readnone
1717 %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]
1720 declare <8 x i16> @llvm.x86.ssse3.pmul.hr.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
1725 %res = call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
1728 declare <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8>, <16 x i8>) nounwind readnone
1733 %res = call <16 x i8> @llvm.x86.ssse3.psign.b.128(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
1736 declare <16 x i8> @llvm.x86.ssse3.psign.b.128(<16 x i8>, <16 x i8>) nounwind readnone
1741 %res = call <4 x i32> @llvm.x86.ssse3.psign.d.128(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
1744 declare <4 x i32> @llvm.x86.ssse3.psign.d.128(<4 x i32>, <4 x i32>) nounwind readnone
1749 %res = call <8 x i16> @llvm.x86.ssse3.psign.w.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
1752 declare <8 x i16> @llvm.x86.ssse3.psign.w.128(<8 x i16>, <8 x i16>) nounwind readnone
1757 %res = call <4 x double> @llvm.x86.avx.addsub.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
1760 declare <4 x double> @llvm.x86.avx.addsub.pd.256(<4 x double>, <4 x double>) nounwind readnone
1765 %res = call <8 x float> @llvm.x86.avx.addsub.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
1768 declare <8 x float> @llvm.x86.avx.addsub.ps.256(<8 x float>, <8 x float>) nounwind readnone
1773 %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]
1776 declare <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double>, <4 x double>, i32) nounwind readnone
1781 %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]
1784 declare <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
1789 %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]
1792 declare <4 x double> @llvm.x86.avx.blendv.pd.256(<4 x double>, <4 x double>, <4 x double>) nounwind readnone
1797 %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]
1800 declare <8 x float> @llvm.x86.avx.blendv.ps.256(<8 x float>, <8 x float>, <8 x float>) nounwind readnone
1805 %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]
1808 declare <4 x double> @llvm.x86.avx.cmp.pd.256(<4 x double>, <4 x double>, i8) nounwind readnone
1813 %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]
1819 %a2 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a1, i8 0) ; <<8 x float>> [#uses=1]
1821 x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a2, i8 1) ; <<8 x float>> [#uses=1]
1823 %a4 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a3, i8 2) ; <<8 x float>> [#uses=1]
1825 %a5 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a4, i8 3) ; <<8 x float>> [#uses=1]
1827 %a6 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a5, i8 4) ; <<8 x float>> [#uses=1]
1829 %a7 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a6, i8 5) ; <<8 x float>> [#uses=1]
1831 %a8 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a7, i8 6) ; <<8 x float>> [#uses=1]
1833 %a9 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a8, i8 7) ; <<8 x float>> [#uses=1]
1835 %a10 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a9, i8 8) ; <<8 x float>> [#uses=1]
1837 %a11 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a10, i8 9) ; <<8 x float>> [#uses=1]
1839 %a12 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a11, i8 10) ; <<8 x float>> [#uses=1]
1841 %a13 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a12, i8 11) ; <<8 x float>> [#uses=1]
1843 %a14 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a13, i8 12) ; <<8 x float>> [#uses=1]
1845 %a15 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a14, i8 13) ; <<8 x float>> [#uses=1]
1847 %a16 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a15, i8 14) ; <<8 x float>> [#uses=1]
1849 %a17 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a16, i8 15) ; <<8 x float>> [#uses=1]
1851 %a18 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a17, i8 16) ; <<8 x float>> [#uses=1]
1853 %a19 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a18, i8 17) ; <<8 x float>> [#uses=1]
1855 %a20 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a19, i8 18) ; <<8 x float>> [#uses=1]
1857 %a21 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a20, i8 19) ; <<8 x float>> [#uses=1]
1859 %a22 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a21, i8 20) ; <<8 x float>> [#uses=1]
1861 %a23 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a22, i8 21) ; <<8 x float>> [#uses=1]
1863 %a24 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a23, i8 22) ; <<8 x float>> [#uses=1]
1865 %a25 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a24, i8 23) ; <<8 x float>> [#uses=1]
1867 %a26 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a25, i8 24) ; <<8 x float>> [#uses=1]
1869 %a27 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a26, i8 25) ; <<8 x float>> [#uses=1]
1871 %a28 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a27, i8 26) ; <<8 x float>> [#uses=1]
1873 %a29 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a28, i8 27) ; <<8 x float>> [#uses=1]
1875 %a30 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a29, i8 28) ; <<8 x float>> [#uses=1]
1877 %a31 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a30, i8 29) ; <<8 x float>> [#uses=1]
1879 %a32 = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a31, i8 30) ; <<8 x float>> [#uses=1]
1881 %res = call <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float> %a0, <8 x float> %a32, i8 31) ; <<8 x float>> [#uses=1]
1884 declare <8 x float> @llvm.x86.avx.cmp.ps.256(<8 x float>, <8 x float>, i8) nounwind readnone
1889 %res = call <4 x float> @llvm.x86.avx.cvt.pd2.ps.256(<4 x double> %a0) ; <<4 x float>> [#uses=1]
1892 declare <4 x float> @llvm.x86.avx.cvt.pd2.ps.256(<4 x double>) nounwind readnone
1897 %res = call <4 x i32> @llvm.x86.avx.cvt.pd2dq.256(<4 x double> %a0) ; <<4 x i32>> [#uses=1]
1900 declare <4 x i32> @llvm.x86.avx.cvt.pd2dq.256(<4 x double>) nounwind readnone
1905 %res = call <4 x double> @llvm.x86.avx.cvt.ps2.pd.256(<4 x float> %a0) ; <<4 x double>> [#uses=1]
1908 declare <4 x double> @llvm.x86.avx.cvt.ps2.pd.256(<4 x float>) nounwind readnone
1913 %res = call <8 x i32> @llvm.x86.avx.cvt.ps2dq.256(<8 x float> %a0) ; <<8 x i32>> [#uses=1]
1916 declare <8 x i32> @llvm.x86.avx.cvt.ps2dq.256(<8 x float>) nounwind readnone
1921 %res = call <4 x double> @llvm.x86.avx.cvtdq2.pd.256(<4 x i32> %a0) ; <<4 x double>> [#uses=1]
1924 declare <4 x double> @llvm.x86.avx.cvtdq2.pd.256(<4 x i32>) nounwind readnone
1929 %res = call <8 x float> @llvm.x86.avx.cvtdq2.ps.256(<8 x i32> %a0) ; <<8 x float>> [#uses=1]
1932 declare <8 x float> @llvm.x86.avx.cvtdq2.ps.256(<8 x i32>) nounwind readnone
1937 %res = call <4 x i32> @llvm.x86.avx.cvtt.pd2dq.256(<4 x double> %a0) ; <<4 x i32>> [#uses=1]
1940 declare <4 x i32> @llvm.x86.avx.cvtt.pd2dq.256(<4 x double>) nounwind readnone
1945 %res = call <8 x i32> @llvm.x86.avx.cvtt.ps2dq.256(<8 x float> %a0) ; <<8 x i32>> [#uses=1]
1948 declare <8 x i32> @llvm.x86.avx.cvtt.ps2dq.256(<8 x float>) nounwind readnone
1953 %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]
1956 declare <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
1961 %res = call <4 x double> @llvm.x86.avx.hadd.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
1964 declare <4 x double> @llvm.x86.avx.hadd.pd.256(<4 x double>, <4 x double>) nounwind readnone
1969 %res = call <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
1972 declare <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float>, <8 x float>) nounwind readnone
1977 %res = call <4 x double> @llvm.x86.avx.hsub.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
1980 declare <4 x double> @llvm.x86.avx.hsub.pd.256(<4 x double>, <4 x double>) nounwind readnone
1985 %res = call <8 x float> @llvm.x86.avx.hsub.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
1988 declare <8 x float> @llvm.x86.avx.hsub.ps.256(<8 x float>, <8 x float>) nounwind readnone
1993 %res = call <32 x i8> @llvm.x86.avx.ldu.dq.256(i8* %a0) ; <<32 x i8>> [#uses=1]
1996 declare <32 x i8> @llvm.x86.avx.ldu.dq.256(i8*) nounwind readonly
2001 %res = call <2 x double> @llvm.x86.avx.maskload.pd(i8* %a0, <2 x double> %a1) ; <<2 x double>> [#uses=1]
2004 declare <2 x double> @llvm.x86.avx.maskload.pd(i8*, <2 x double>) nounwind readonly
2009 %res = call <4 x double> @llvm.x86.avx.maskload.pd.256(i8* %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
2012 declare <4 x double> @llvm.x86.avx.maskload.pd.256(i8*, <4 x double>) nounwind readonly
2017 %res = call <4 x float> @llvm.x86.avx.maskload.ps(i8* %a0, <4 x float> %a1) ; <<4 x float>> [#uses=1]
2020 declare <4 x float> @llvm.x86.avx.maskload.ps(i8*, <4 x float>) nounwind readonly
2025 %res = call <8 x float> @llvm.x86.avx.maskload.ps.256(i8* %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
2028 declare <8 x float> @llvm.x86.avx.maskload.ps.256(i8*, <8 x float>) nounwind readonly
2033 call void @llvm.x86.avx.maskstore.pd(i8* %a0, <2 x double> %a1, <2 x double> %a2)
2036 declare void @llvm.x86.avx.maskstore.pd(i8*, <2 x double>, <2 x double>) nounwind
2041 call void @llvm.x86.avx.maskstore.pd.256(i8* %a0, <4 x double> %a1, <4 x double> %a2)
2044 declare void @llvm.x86.avx.maskstore.pd.256(i8*, <4 x double>, <4 x double>) nounwind
2049 call void @llvm.x86.avx.maskstore.ps(i8* %a0, <4 x float> %a1, <4 x float> %a2)
2052 declare void @llvm.x86.avx.maskstore.ps(i8*, <4 x float>, <4 x float>) nounwind
2057 call void @llvm.x86.avx.maskstore.ps.256(i8* %a0, <8 x float> %a1, <8 x float> %a2)
2060 declare void @llvm.x86.avx.maskstore.ps.256(i8*, <8 x float>, <8 x float>) nounwind
2065 %res = call <4 x double> @llvm.x86.avx.max.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
2068 declare <4 x double> @llvm.x86.avx.max.pd.256(<4 x double>, <4 x double>) nounwind readnone
2073 %res = call <8 x float> @llvm.x86.avx.max.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
2076 declare <8 x float> @llvm.x86.avx.max.ps.256(<8 x float>, <8 x float>) nounwind readnone
2081 %res = call <4 x double> @llvm.x86.avx.min.pd.256(<4 x double> %a0, <4 x double> %a1) ; <<4 x double>> [#uses=1]
2084 declare <4 x double> @llvm.x86.avx.min.pd.256(<4 x double>, <4 x double>) nounwind readnone
2089 %res = call <8 x float> @llvm.x86.avx.min.ps.256(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
2092 declare <8 x float> @llvm.x86.avx.min.ps.256(<8 x float>, <8 x float>) nounwind readnone
2097 %res = call i32 @llvm.x86.avx.movmsk.pd.256(<4 x double> %a0) ; <i32> [#uses=1]
2100 declare i32 @llvm.x86.avx.movmsk.pd.256(<4 x double>) nounwind readnone
2105 %res = call i32 @llvm.x86.avx.movmsk.ps.256(<8 x float> %a0) ; <i32> [#uses=1]
2108 declare i32 @llvm.x86.avx.movmsk.ps.256(<8 x float>) nounwind readnone
2119 %res = call i32 @llvm.x86.avx.ptestc.256(<4 x i64> %a0, <4 x i64> %a1) ; <i32> [#uses=1]
2122 declare i32 @llvm.x86.avx.ptestc.256(<4 x i64>, <4 x i64>) nounwind readnone
2129 %res = call i32 @llvm.x86.avx.ptestnzc.256(<4 x i64> %a0, <4 x i64> %a1) ; <i32> [#uses=1]
2132 declare i32 @llvm.x86.avx.ptestnzc.256(<4 x i64>, <4 x i64>) nounwind readnone
2139 %res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a0, <4 x i64> %a1) ; <i32> [#uses=1]
2142 declare i32 @llvm.x86.avx.ptestz.256(<4 x i64>, <4 x i64>) nounwind readnone
2147 %res = call <8 x float> @llvm.x86.avx.rcp.ps.256(<8 x float> %a0) ; <<8 x float>> [#uses=1]
2150 declare <8 x float> @llvm.x86.avx.rcp.ps.256(<8 x float>) nounwind readnone
2155 %res = call <4 x double> @llvm.x86.avx.round.pd.256(<4 x double> %a0, i32 7) ; <<4 x double>> [#uses=1]
2158 declare <4 x double> @llvm.x86.avx.round.pd.256(<4 x double>, i32) nounwind readnone
2163 %res = call <8 x float> @llvm.x86.avx.round.ps.256(<8 x float> %a0, i32 7) ; <<8 x float>> [#uses=1]
2166 declare <8 x float> @llvm.x86.avx.round.ps.256(<8 x float>, i32) nounwind readnone
2171 %res = call <8 x float> @llvm.x86.avx.rsqrt.ps.256(<8 x float> %a0) ; <<8 x float>> [#uses=1]
2174 declare <8 x float> @llvm.x86.avx.rsqrt.ps.256(<8 x float>) nounwind readnone
2179 %res = call <4 x double> @llvm.x86.avx.sqrt.pd.256(<4 x double> %a0) ; <<4 x double>> [#uses=1]
2182 declare <4 x double> @llvm.x86.avx.sqrt.pd.256(<4 x double>) nounwind readnone
2187 %res = call <8 x float> @llvm.x86.avx.sqrt.ps.256(<8 x float> %a0) ; <<8 x float>> [#uses=1]
2190 declare <8 x float> @llvm.x86.avx.sqrt.ps.256(<8 x float>) nounwind readnone
2198 call void @llvm.x86.avx.storeu.dq.256(i8* %a0, <32 x i8> %a2)
2201 declare void @llvm.x86.avx.storeu.dq.256(i8*, <32 x i8>) nounwind
2208 call void @llvm.x86.avx.storeu.pd.256(i8* %a0, <4 x double> %a2)
2211 declare void @llvm.x86.avx.storeu.pd.256(i8*, <4 x double>) nounwind
2216 call void @llvm.x86.avx.storeu.ps.256(i8* %a0, <8 x float> %a1)
2219 declare void @llvm.x86.avx.storeu.ps.256(i8*, <8 x float>) nounwind
2224 %res = call <4 x double> @llvm.x86.avx.vbroadcast.sd.256(i8* %a0) ; <<4 x double>> [#uses=1]
2227 declare <4 x double> @llvm.x86.avx.vbroadcast.sd.256(i8*) nounwind readonly
2232 %res = call <4 x double> @llvm.x86.avx.vbroadcastf128.pd.256(i8* %a0) ; <<4 x double>> [#uses=1]
2235 declare <4 x double> @llvm.x86.avx.vbroadcastf128.pd.256(i8*) nounwind readonly
2240 %res = call <8 x float> @llvm.x86.avx.vbroadcastf128.ps.256(i8* %a0) ; <<8 x float>> [#uses=1]
2243 declare <8 x float> @llvm.x86.avx.vbroadcastf128.ps.256(i8*) nounwind readonly
2248 %res = call <4 x float> @llvm.x86.avx.vbroadcast.ss(i8* %a0) ; <<4 x float>> [#uses=1]
2251 declare <4 x float> @llvm.x86.avx.vbroadcast.ss(i8*) nounwind readonly
2256 %res = call <8 x float> @llvm.x86.avx.vbroadcast.ss.256(i8* %a0) ; <<8 x float>> [#uses=1]
2259 declare <8 x float> @llvm.x86.avx.vbroadcast.ss.256(i8*) nounwind readonly
2264 %res = call <2 x double> @llvm.x86.avx.vextractf128.pd.256(<4 x double> %a0, i8 7) ; <<2 x double>> [#uses=1]
2267 declare <2 x double> @llvm.x86.avx.vextractf128.pd.256(<4 x double>, i8) nounwind readnone
2272 %res = call <4 x float> @llvm.x86.avx.vextractf128.ps.256(<8 x float> %a0, i8 7) ; <<4 x float>> [#uses=1]
2275 declare <4 x float> @llvm.x86.avx.vextractf128.ps.256(<8 x float>, i8) nounwind readnone
2280 %res = call <4 x i32> @llvm.x86.avx.vextractf128.si.256(<8 x i32> %a0, i8 7) ; <<4 x i32>> [#uses=1]
2283 declare <4 x i32> @llvm.x86.avx.vextractf128.si.256(<8 x i32>, i8) nounwind readnone
2288 %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]
2291 declare <4 x double> @llvm.x86.avx.vinsertf128.pd.256(<4 x double>, <2 x double>, i8) nounwind readnone
2296 %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]
2299 declare <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float>, <4 x float>, i8) nounwind readnone
2304 %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]
2307 declare <8 x i32> @llvm.x86.avx.vinsertf128.si.256(<8 x i32>, <4 x i32>, i8) nounwind readnone
2312 %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]
2315 declare <4 x double> @llvm.x86.avx.vperm2f128.pd.256(<4 x double>, <4 x double>, i8) nounwind readnone
2320 %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]
2323 declare <8 x float> @llvm.x86.avx.vperm2f128.ps.256(<8 x float>, <8 x float>, i8) nounwind readnone
2328 %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]
2331 declare <8 x i32> @llvm.x86.avx.vperm2f128.si.256(<8 x i32>, <8 x i32>, i8) nounwind readnone
2336 %res = call <2 x double> @llvm.x86.avx.vpermil.pd(<2 x double> %a0, i8 7) ; <<2 x double>> [#uses=1]
2339 declare <2 x double> @llvm.x86.avx.vpermil.pd(<2 x double>, i8) nounwind readnone
2344 %res = call <4 x double> @llvm.x86.avx.vpermil.pd.256(<4 x double> %a0, i8 7) ; <<4 x double>> [#uses=1]
2347 declare <4 x double> @llvm.x86.avx.vpermil.pd.256(<4 x double>, i8) nounwind readnone
2352 %res = call <4 x float> @llvm.x86.avx.vpermil.ps(<4 x float> %a0, i8 7) ; <<4 x float>> [#uses=1]
2355 declare <4 x float> @llvm.x86.avx.vpermil.ps(<4 x float>, i8) nounwind readnone
2360 %res = call <8 x float> @llvm.x86.avx.vpermil.ps.256(<8 x float> %a0, i8 7) ; <<8 x float>> [#uses=1]
2363 declare <8 x float> @llvm.x86.avx.vpermil.ps.256(<8 x float>, i8) nounwind readnone
2368 %res = call <2 x double> @llvm.x86.avx.vpermilvar.pd(<2 x double> %a0, <2 x i64> %a1) ; <<2 x double>> [#uses=1]
2371 declare <2 x double> @llvm.x86.avx.vpermilvar.pd(<2 x double>, <2 x i64>) nounwind readnone
2376 %res = call <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double> %a0, <4 x i64> %a1) ; <<4 x double>> [#uses=1]
2379 declare <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double>, <4 x i64>) nounwind readnone
2384 %res = call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float> %a0, <4 x i32> %a1) ; <<4 x float>> [#uses=1]
2390 %res = call <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float> %a0, <4 x i32> %a2) ; <<4 x float>> [#uses=1]
2393 declare <4 x float> @llvm.x86.avx.vpermilvar.ps(<4 x float>, <4 x i32>) nounwind readnone
2398 %res = call <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float> %a0, <8 x i32> %a1) ; <<8 x float>> [#uses=1]
2401 declare <8 x float> @llvm.x86.avx.vpermilvar.ps.256(<8 x float>, <8 x i32>) nounwind readnone
2407 %res = call i32 @llvm.x86.avx.vtestc.pd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
2410 declare i32 @llvm.x86.avx.vtestc.pd(<2 x double>, <2 x double>) nounwind readnone
2416 %res = call i32 @llvm.x86.avx.vtestc.pd.256(<4 x double> %a0, <4 x double> %a1) ; <i32> [#uses=1]
2419 declare i32 @llvm.x86.avx.vtestc.pd.256(<4 x double>, <4 x double>) nounwind readnone
2425 %res = call i32 @llvm.x86.avx.vtestc.ps(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
2428 declare i32 @llvm.x86.avx.vtestc.ps(<4 x float>, <4 x float>) nounwind readnone
2434 %res = call i32 @llvm.x86.avx.vtestc.ps.256(<8 x float> %a0, <8 x float> %a1) ; <i32> [#uses=1]
2437 declare i32 @llvm.x86.avx.vtestc.ps.256(<8 x float>, <8 x float>) nounwind readnone
2444 %res = call i32 @llvm.x86.avx.vtestnzc.pd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
2447 declare i32 @llvm.x86.avx.vtestnzc.pd(<2 x double>, <2 x double>) nounwind readnone
2454 %res = call i32 @llvm.x86.avx.vtestnzc.pd.256(<4 x double> %a0, <4 x double> %a1) ; <i32> [#uses=1]
2457 declare i32 @llvm.x86.avx.vtestnzc.pd.256(<4 x double>, <4 x double>) nounwind readnone
2464 %res = call i32 @llvm.x86.avx.vtestnzc.ps(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
2467 declare i32 @llvm.x86.avx.vtestnzc.ps(<4 x float>, <4 x float>) nounwind readnone
2474 %res = call i32 @llvm.x86.avx.vtestnzc.ps.256(<8 x float> %a0, <8 x float> %a1) ; <i32> [#uses=1]
2477 declare i32 @llvm.x86.avx.vtestnzc.ps.256(<8 x float>, <8 x float>) nounwind readnone
2484 %res = call i32 @llvm.x86.avx.vtestz.pd(<2 x double> %a0, <2 x double> %a1) ; <i32> [#uses=1]
2487 declare i32 @llvm.x86.avx.vtestz.pd(<2 x double>, <2 x double>) nounwind readnone
2494 %res = call i32 @llvm.x86.avx.vtestz.pd.256(<4 x double> %a0, <4 x double> %a1) ; <i32> [#uses=1]
2497 declare i32 @llvm.x86.avx.vtestz.pd.256(<4 x double>, <4 x double>) nounwind readnone
2504 %res = call i32 @llvm.x86.avx.vtestz.ps(<4 x float> %a0, <4 x float> %a1) ; <i32> [#uses=1]
2507 declare i32 @llvm.x86.avx.vtestz.ps(<4 x float>, <4 x float>) nounwind readnone
2514 %res = call i32 @llvm.x86.avx.vtestz.ps.256(<8 x float> %a0, <8 x float> %a1) ; <i32> [#uses=1]
2517 declare i32 @llvm.x86.avx.vtestz.ps.256(<8 x float>, <8 x float>) nounwind readnone
2522 call void @llvm.x86.avx.vzeroall()
2525 declare void @llvm.x86.avx.vzeroall() nounwind
2530 call void @llvm.x86.avx.vzeroupper()
2533 declare void @llvm.x86.avx.vzeroupper() nounwind
2540 tail call void @llvm.x86.sse3.monitor(i8* %P, i32 %E, i32 %H)
2543 declare void @llvm.x86.sse3.monitor(i8*, i32, i32) nounwind
2548 tail call void @llvm.x86.sse3.mwait(i32 %E, i32 %H)
2551 declare void @llvm.x86.sse3.mwait(i32, i32) nounwind
2556 tail call void @llvm.x86.sse.sfence()
2559 declare void @llvm.x86.sse.sfence() nounwind
2564 tail call void @llvm.x86.sse2.lfence()
2567 declare void @llvm.x86.sse2.lfence() nounwind
2572 tail call void @llvm.x86.sse2.mfence()
2575 declare void @llvm.x86.sse2.mfence() nounwind
2580 tail call void @llvm.x86.sse2.clflush(i8* %p)
2583 declare void @llvm.x86.sse2.clflush(i8*) nounwind
2587 %tmp = call i32 @llvm.x86.sse42.crc32.32.8(i32 %a, i8 %b)
2590 declare i32 @llvm.x86.sse42.crc32.32.8(i32, i8) nounwind
2594 %tmp = call i32 @llvm.x86.sse42.crc32.32.16(i32 %a, i16 %b)
2597 declare i32 @llvm.x86.sse42.crc32.32.16(i32, i16) nounwind
2601 %tmp = call i32 @llvm.x86.sse42.crc32.32.32(i32 %a, i32 %b)
2604 declare i32 @llvm.x86.sse42.crc32.32.32(i32, i32) nounwind
2609 tail call void @llvm.x86.avx.movnt.dq.256(i8* %p, <4 x i64> %a2) nounwind
2612 declare void @llvm.x86.avx.movnt.dq.256(i8*, <4 x i64>) nounwind
2616 tail call void @llvm.x86.avx.movnt.ps.256(i8* %p, <8 x float> %a) nounwind
2619 declare void @llvm.x86.avx.movnt.ps.256(i8*, <8 x float>) nounwind
2625 tail call void @llvm.x86.avx.movnt.pd.256(i8* %p, <4 x double> %a2) nounwind
2628 declare void @llvm.x86.avx.movnt.pd.256(i8*, <4 x double>) nounwind
2634 %res = call <2 x i64> @llvm.x86.pclmulqdq(<2 x i64> %a0, <2 x i64> %a1, i8 0) ; <<2 x i64>> [#uses=1]
2637 declare <2 x i64> @llvm.x86.pclmulqdq(<2 x i64>, <2 x i64>, i8) nounwind readnone
