Lines Matching refs:avx2
1 ; RUN: llc -O3 -disable-peephole -mtriple=x86_64-unknown-unknown -mattr=+avx2 < %s | FileCheck %s
20 declare <4 x double> @llvm.x86.avx2.vbroadcast.sd.pd.256(<2 x double>) nounwind readonly
31 declare <4 x float> @llvm.x86.avx2.vbroadcast.ss.ps(<4 x float>) nounwind readonly
42 declare <8 x float> @llvm.x86.avx2.vbroadcast.ss.ps.256(<4 x float>) nounwind readonly
68 %2 = call <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8> %a0, <32 x i8> %a1, i8 7)
71 declare <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8>, <32 x i8>, i8) nounwind readnone
77 %2 = call <32 x i8> @llvm.x86.avx2.pabs.b(<32 x i8> %a0)
80 declare <32 x i8> @llvm.x86.avx2.pabs.b(<32 x i8>) nounwind readnone
86 %2 = call <8 x i32> @llvm.x86.avx2.pabs.d(<8 x i32> %a0)
89 declare <8 x i32> @llvm.x86.avx2.pabs.d(<8 x i32>) nounwind readnone
95 %2 = call <16 x i16> @llvm.x86.avx2.pabs.w(<16 x i16> %a0)
98 declare <16 x i16> @llvm.x86.avx2.pabs.w(<16 x i16>) nounwind readnone
104 %2 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a0, <8 x i32> %a1)
107 declare <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32>, <8 x i32>) nounwind readnone
113 %2 = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a0, <16 x i16> %a1)
116 declare <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16>, <16 x i16>) nounwind readnone
122 %2 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a0, <8 x i32> %a1)
125 declare <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32>, <8 x i32>) nounwind readnone
131 %2 = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a0, <16 x i16> %a1)
134 declare <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16>, <16 x i16>) nounwind readnone
164 %2 = call <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8> %a0, <32 x i8> %a1)
167 declare <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8>, <32 x i8>) nounwind readnone
173 %2 = call <16 x i16> @llvm.x86.avx2.padds.w(<16 x i16> %a0, <16 x i16> %a1)
176 declare <16 x i16> @llvm.x86.avx2.padds.w(<16 x i16>, <16 x i16>) nounwind readnone
182 %2 = call <32 x i8> @llvm.x86.avx2.paddus.b(<32 x i8> %a0, <32 x i8> %a1)
185 declare <32 x i8> @llvm.x86.avx2.paddus.b(<32 x i8>, <32 x i8>) nounwind readnone
191 %2 = call <16 x i16> @llvm.x86.avx2.paddus.w(<16 x i16> %a0, <16 x i16> %a1)
194 declare <16 x i16> @llvm.x86.avx2.paddus.w(<16 x i16>, <16 x i16>) nounwind readnone
237 %2 = call <32 x i8> @llvm.x86.avx2.pavg.b(<32 x i8> %a0, <32 x i8> %a1)
240 declare <32 x i8> @llvm.x86.avx2.pavg.b(<32 x i8>, <32 x i8>) nounwind readnone
246 %2 = call <16 x i16> @llvm.x86.avx2.pavg.w(<16 x i16> %a0, <16 x i16> %a1)
249 declare <16 x i16> @llvm.x86.avx2.pavg.w(<16 x i16>, <16 x i16>) nounwind readnone
271 %2 = call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> %a1, <32 x i8> %c, <32 x i8> %a0)
274 declare <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8>, <32 x i8>, <32 x i8>) nounwind readnone
280 %2 = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a1, i8 7)
283 declare <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16>, <16 x i16>, i8) nounwind readnone
443 %2 = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a1, <8 x i32> %a0)
446 declare <8 x i32> @llvm.x86.avx2.permd(<8 x i32>, <8 x i32>) nounwind readonly
462 %2 = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a1, <8 x i32> %a0)
465 declare <8 x float> @llvm.x86.avx2.permps(<8 x float>, <8 x i32>) nounwind readonly
481 %2 = call <8 x i32> @llvm.x86.avx2.phadd.d(<8 x i32> %a0, <8 x i32> %a1)
484 declare <8 x i32> @llvm.x86.avx2.phadd.d(<8 x i32>, <8 x i32>) nounwind readnone
490 %2 = call <16 x i16> @llvm.x86.avx2.phadd.sw(<16 x i16> %a0, <16 x i16> %a1)
493 declare <16 x i16> @llvm.x86.avx2.phadd.sw(<16 x i16>, <16 x i16>) nounwind readnone
499 %2 = call <16 x i16> @llvm.x86.avx2.phadd.w(<16 x i16> %a0, <16 x i16> %a1)
502 declare <16 x i16> @llvm.x86.avx2.phadd.w(<16 x i16>, <16 x i16>) nounwind readnone
508 %2 = call <8 x i32> @llvm.x86.avx2.phsub.d(<8 x i32> %a0, <8 x i32> %a1)
511 declare <8 x i32> @llvm.x86.avx2.phsub.d(<8 x i32>, <8 x i32>) nounwind readnone
517 %2 = call <16 x i16> @llvm.x86.avx2.phsub.sw(<16 x i16> %a0, <16 x i16> %a1)
520 declare <16 x i16> @llvm.x86.avx2.phsub.sw(<16 x i16>, <16 x i16>) nounwind readnone
526 %2 = call <16 x i16> @llvm.x86.avx2.phsub.w(<16 x i16> %a0, <16 x i16> %a1)
529 declare <16 x i16> @llvm.x86.avx2.phsub.w(<16 x i16>, <16 x i16>) nounwind readnone
535 %2 = call <16 x i16> @llvm.x86.avx2.pmadd.ub.sw(<32 x i8> %a0, <32 x i8> %a1)
538 declare <16 x i16> @llvm.x86.avx2.pmadd.ub.sw(<32 x i8>, <32 x i8>) nounwind readnone
544 %2 = call <8 x i32> @llvm.x86.avx2.pmadd.wd(<16 x i16> %a0, <16 x i16> %a1)
547 declare <8 x i32> @llvm.x86.avx2.pmadd.wd(<16 x i16>, <16 x i16>) nounwind readnone
553 %2 = call <32 x i8> @llvm.x86.avx2.pmaxs.b(<32 x i8> %a0, <32 x i8> %a1)
556 declare <32 x i8> @llvm.x86.avx2.pmaxs.b(<32 x i8>, <32 x i8>) nounwind readnone
562 %2 = call <8 x i32> @llvm.x86.avx2.pmaxs.d(<8 x i32> %a0, <8 x i32> %a1)
565 declare <8 x i32> @llvm.x86.avx2.pmaxs.d(<8 x i32>, <8 x i32>) nounwind readnone
571 %2 = call <16 x i16> @llvm.x86.avx2.pmaxs.w(<16 x i16> %a0, <16 x i16> %a1)
574 declare <16 x i16> @llvm.x86.avx2.pmaxs.w(<16 x i16>, <16 x i16>) nounwind readnone
580 %2 = call <32 x i8> @llvm.x86.avx2.pmaxu.b(<32 x i8> %a0, <32 x i8> %a1)
583 declare <32 x i8> @llvm.x86.avx2.pmaxu.b(<32 x i8>, <32 x i8>) nounwind readnone
589 %2 = call <8 x i32> @llvm.x86.avx2.pmaxu.d(<8 x i32> %a0, <8 x i32> %a1)
592 declare <8 x i32> @llvm.x86.avx2.pmaxu.d(<8 x i32>, <8 x i32>) nounwind readnone
598 %2 = call <16 x i16> @llvm.x86.avx2.pmaxu.w(<16 x i16> %a0, <16 x i16> %a1)
601 declare <16 x i16> @llvm.x86.avx2.pmaxu.w(<16 x i16>, <16 x i16>) nounwind readnone
607 %2 = call <32 x i8> @llvm.x86.avx2.pmins.b(<32 x i8> %a0, <32 x i8> %a1)
610 declare <32 x i8> @llvm.x86.avx2.pmins.b(<32 x i8>, <32 x i8>) nounwind readnone
616 %2 = call <8 x i32> @llvm.x86.avx2.pmins.d(<8 x i32> %a0, <8 x i32> %a1)
619 declare <8 x i32> @llvm.x86.avx2.pmins.d(<8 x i32>, <8 x i32>) nounwind readnone
625 %2 = call <16 x i16> @llvm.x86.avx2.pmins.w(<16 x i16> %a0, <16 x i16> %a1)
628 declare <16 x i16> @llvm.x86.avx2.pmins.w(<16 x i16>, <16 x i16>) nounwind readnone
634 %2 = call <32 x i8> @llvm.x86.avx2.pminu.b(<32 x i8> %a0, <32 x i8> %a1)
637 declare <32 x i8> @llvm.x86.avx2.pminu.b(<32 x i8>, <32 x i8>) nounwind readnone
643 %2 = call <8 x i32> @llvm.x86.avx2.pminu.d(<8 x i32> %a0, <8 x i32> %a1)
646 declare <8 x i32> @llvm.x86.avx2.pminu.d(<8 x i32>, <8 x i32>) nounwind readnone
652 %2 = call <16 x i16> @llvm.x86.avx2.pminu.w(<16 x i16> %a0, <16 x i16> %a1)
655 declare <16 x i16> @llvm.x86.avx2.pminu.w(<16 x i16>, <16 x i16>) nounwind readnone
661 %2 = call <8 x i32> @llvm.x86.avx2.pmovsxbd(<16 x i8> %a0)
664 declare <8 x i32> @llvm.x86.avx2.pmovsxbd(<16 x i8>) nounwind readnone
670 %2 = call <4 x i64> @llvm.x86.avx2.pmovsxbq(<16 x i8> %a0)
673 declare <4 x i64> @llvm.x86.avx2.pmovsxbq(<16 x i8>) nounwind readnone
703 %2 = call <4 x i64> @llvm.x86.avx2.pmovsxwq(<8 x i16> %a0)
706 declare <4 x i64> @llvm.x86.avx2.pmovsxwq(<8 x i16>) nounwind readnone
712 %2 = call <8 x i32> @llvm.x86.avx2.pmovzxbd(<16 x i8> %a0)
715 declare <8 x i32> @llvm.x86.avx2.pmovzxbd(<16 x i8>) nounwind readnone
721 %2 = call <4 x i64> @llvm.x86.avx2.pmovzxbq(<16 x i8> %a0)
724 declare <4 x i64> @llvm.x86.avx2.pmovzxbq(<16 x i8>) nounwind readnone
730 %2 = call <16 x i16> @llvm.x86.avx2.pmovzxbw(<16 x i8> %a0)
733 declare <16 x i16> @llvm.x86.avx2.pmovzxbw(<16 x i8>) nounwind readnone
739 %2 = call <4 x i64> @llvm.x86.avx2.pmovzxdq(<4 x i32> %a0)
742 declare <4 x i64> @llvm.x86.avx2.pmovzxdq(<4 x i32>) nounwind readnone
748 %2 = call <8 x i32> @llvm.x86.avx2.pmovzxwd(<8 x i16> %a0)
751 declare <8 x i32> @llvm.x86.avx2.pmovzxwd(<8 x i16>) nounwind readnone
757 %2 = call <4 x i64> @llvm.x86.avx2.pmovzxwq(<8 x i16> %a0)
760 declare <4 x i64> @llvm.x86.avx2.pmovzxwq(<8 x i16>) nounwind readnone
766 %2 = call <4 x i64> @llvm.x86.avx2.pmul.dq(<8 x i32> %a0, <8 x i32> %a1)
769 declare <4 x i64> @llvm.x86.avx2.pmul.dq(<8 x i32>, <8 x i32>) nounwind readnone
775 %2 = call <16 x i16> @llvm.x86.avx2.pmul.hr.sw(<16 x i16> %a0, <16 x i16> %a1)
778 declare <16 x i16> @llvm.x86.avx2.pmul.hr.sw(<16 x i16>, <16 x i16>) nounwind readnone
784 %2 = call <16 x i16> @llvm.x86.avx2.pmulhu.w(<16 x i16> %a0, <16 x i16> %a1)
787 declare <16 x i16> @llvm.x86.avx2.pmulhu.w(<16 x i16>, <16 x i16>) nounwind readnone
793 %2 = call <16 x i16> @llvm.x86.avx2.pmulh.w(<16 x i16> %a0, <16 x i16> %a1)
796 declare <16 x i16> @llvm.x86.avx2.pmulh.w(<16 x i16>, <16 x i16>) nounwind readnone
818 %2 = call <4 x i64> @llvm.x86.avx2.pmulu.dq(<8 x i32> %a0, <8 x i32> %a1)
821 declare <4 x i64> @llvm.x86.avx2.pmulu.dq(<8 x i32>, <8 x i32>) nounwind readnone
837 %2 = call <4 x i64> @llvm.x86.avx2.psad.bw(<32 x i8> %a0, <32 x i8> %a1)
840 declare <4 x i64> @llvm.x86.avx2.psad.bw(<32 x i8>, <32 x i8>) nounwind readnone
846 %2 = call <32 x i8> @llvm.x86.avx2.pshuf.b(<32 x i8> %a0, <32 x i8> %a1)
849 declare <32 x i8> @llvm.x86.avx2.pshuf.b(<32 x i8>, <32 x i8>) nounwind readnone
879 %2 = call <32 x i8> @llvm.x86.avx2.psign.b(<32 x i8> %a0, <32 x i8> %a1)
882 declare <32 x i8> @llvm.x86.avx2.psign.b(<32 x i8>, <32 x i8>) nounwind readnone
888 %2 = call <8 x i32> @llvm.x86.avx2.psign.d(<8 x i32> %a0, <8 x i32> %a1)
891 declare <8 x i32> @llvm.x86.avx2.psign.d(<8 x i32>, <8 x i32>) nounwind readnone
897 %2 = call <16 x i16> @llvm.x86.avx2.psign.w(<16 x i16> %a0, <16 x i16> %a1)
900 declare <16 x i16> @llvm.x86.avx2.psign.w(<16 x i16>, <16 x i16>) nounwind readnone
906 %2 = call <8 x i32> @llvm.x86.avx2.psll.d(<8 x i32> %a0, <4 x i32> %a1)
909 declare <8 x i32> @llvm.x86.avx2.psll.d(<8 x i32>, <4 x i32>) nounwind readnone
915 %2 = call <4 x i64> @llvm.x86.avx2.psll.q(<4 x i64> %a0, <2 x i64> %a1)
918 declare <4 x i64> @llvm.x86.avx2.psll.q(<4 x i64>, <2 x i64>) nounwind readnone
924 %2 = call <4 x i32> @llvm.x86.avx2.psllv.d(<4 x i32> %a0, <4 x i32> %a1)
927 declare <4 x i32> @llvm.x86.avx2.psllv.d(<4 x i32>, <4 x i32>) nounwind readnone
933 %2 = call <8 x i32> @llvm.x86.avx2.psllv.d.256(<8 x i32> %a0, <8 x i32> %a1)
936 declare <8 x i32> @llvm.x86.avx2.psllv.d.256(<8 x i32>, <8 x i32>) nounwind readnone
942 %2 = call <2 x i64> @llvm.x86.avx2.psllv.q(<2 x i64> %a0, <2 x i64> %a1)
945 declare <2 x i64> @llvm.x86.avx2.psllv.q(<2 x i64>, <2 x i64>) nounwind readnone
951 %2 = call <4 x i64> @llvm.x86.avx2.psllv.q.256(<4 x i64> %a0, <4 x i64> %a1)
954 declare <4 x i64> @llvm.x86.avx2.psllv.q.256(<4 x i64>, <4 x i64>) nounwind readnone
960 %2 = call <16 x i16> @llvm.x86.avx2.psll.w(<16 x i16> %a0, <8 x i16> %a1)
963 declare <16 x i16> @llvm.x86.avx2.psll.w(<16 x i16>, <8 x i16>) nounwind readnone
969 %2 = call <8 x i32> @llvm.x86.avx2.psra.d(<8 x i32> %a0, <4 x i32> %a1)
972 declare <8 x i32> @llvm.x86.avx2.psra.d(<8 x i32>, <4 x i32>) nounwind readnone
978 %2 = call <4 x i32> @llvm.x86.avx2.psrav.d(<4 x i32> %a0, <4 x i32> %a1)
981 declare <4 x i32> @llvm.x86.avx2.psrav.d(<4 x i32>, <4 x i32>) nounwind readnone
987 %2 = call <8 x i32> @llvm.x86.avx2.psrav.d.256(<8 x i32> %a0, <8 x i32> %a1)
990 declare <8 x i32> @llvm.x86.avx2.psrav.d.256(<8 x i32>, <8 x i32>) nounwind readnone
996 %2 = call <16 x i16> @llvm.x86.avx2.psra.w(<16 x i16> %a0, <8 x i16> %a1)
999 declare <16 x i16> @llvm.x86.avx2.psra.w(<16 x i16>, <8 x i16>) nounwind readnone
1005 %2 = call <8 x i32> @llvm.x86.avx2.psrl.d(<8 x i32> %a0, <4 x i32> %a1)
1008 declare <8 x i32> @llvm.x86.avx2.psrl.d(<8 x i32>, <4 x i32>) nounwind readnone
1014 %2 = call <4 x i64> @llvm.x86.avx2.psrl.q(<4 x i64> %a0, <2 x i64> %a1)
1017 declare <4 x i64> @llvm.x86.avx2.psrl.q(<4 x i64>, <2 x i64>) nounwind readnone
1023 %2 = call <4 x i32> @llvm.x86.avx2.psrlv.d(<4 x i32> %a0, <4 x i32> %a1)
1026 declare <4 x i32> @llvm.x86.avx2.psrlv.d(<4 x i32>, <4 x i32>) nounwind readnone
1032 %2 = call <8 x i32> @llvm.x86.avx2.psrlv.d.256(<8 x i32> %a0, <8 x i32> %a1)
1035 declare <8 x i32> @llvm.x86.avx2.psrlv.d.256(<8 x i32>, <8 x i32>) nounwind readnone
1041 %2 = call <2 x i64> @llvm.x86.avx2.psrlv.q(<2 x i64> %a0, <2 x i64> %a1)
1044 declare <2 x i64> @llvm.x86.avx2.psrlv.q(<2 x i64>, <2 x i64>) nounwind readnone
1050 %2 = call <4 x i64> @llvm.x86.avx2.psrlv.q.256(<4 x i64> %a0, <4 x i64> %a1)
1053 declare <4 x i64> @llvm.x86.avx2.psrlv.q.256(<4 x i64>, <4 x i64>) nounwind readnone
1059 %2 = call <16 x i16> @llvm.x86.avx2.psrl.w(<16 x i16> %a0, <8 x i16> %a1)
1062 declare <16 x i16> @llvm.x86.avx2.psrl.w(<16 x i16>, <8 x i16>) nounwind readnone
1092 %2 = call <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8> %a0, <32 x i8> %a1)
1095 declare <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8>, <32 x i8>) nounwind readnone
1101 %2 = call <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16> %a0, <16 x i16> %a1)
1104 declare <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16>, <16 x i16>) nounwind readnone
1110 %2 = call <32 x i8> @llvm.x86.avx2.psubus.b(<32 x i8> %a0, <32 x i8> %a1)
1113 declare <32 x i8> @llvm.x86.avx2.psubus.b(<32 x i8>, <32 x i8>) nounwind readnone
1119 %2 = call <16 x i16> @llvm.x86.avx2.psubus.w(<16 x i16> %a0, <16 x i16> %a1)
1122 declare <16 x i16> @llvm.x86.avx2.psubus.w(<16 x i16>, <16 x i16>) nounwind readnone