Lines Matching refs:sse41
5 ; NOTE: This should use IR equivalent to what is generated by clang/test/CodeGen/sse41-builtins.c
71 %call = call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> %arg0, <16 x i8> %arg1, <16 x i8> %arg2)
75 declare <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8>, <16 x i8>, <16 x i8>) nounwind readnone
93 …%res = call <2 x double> @llvm.x86.sse41.blendvpd(<2 x double> %a0, <2 x double> %a1, <2 x double>…
96 declare <2 x double> @llvm.x86.sse41.blendvpd(<2 x double>, <2 x double>, <2 x double>) nounwind re…
114 …%res = call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2)
117 declare <4 x float> @llvm.x86.sse41.blendvps(<4 x float>, <4 x float>, <4 x float>) nounwind readno…
129 %res = call <2 x double> @llvm.x86.sse41.round.pd(<2 x double> %a0, i32 2)
132 declare <2 x double> @llvm.x86.sse41.round.pd(<2 x double>, i32) nounwind readnone
144 %res = call <4 x float> @llvm.x86.sse41.round.ps(<4 x float> %a0, i32 2)
147 declare <4 x float> @llvm.x86.sse41.round.ps(<4 x float>, i32) nounwind readnone
159 %res = call <2 x double> @llvm.x86.sse41.round.sd(<2 x double> %a0, <2 x double> %a1, i32 2)
162 declare <2 x double> @llvm.x86.sse41.round.sd(<2 x double>, <2 x double>, i32) nounwind readnone
174 %res = call <4 x float> @llvm.x86.sse41.round.ss(<4 x float> %a0, <4 x float> %a1, i32 2)
177 declare <4 x float> @llvm.x86.sse41.round.ss(<4 x float>, <4 x float>, i32) nounwind readnone
402 %res = call <2 x double> @llvm.x86.sse41.dppd(<2 x double> %a0, <2 x double> %a1, i8 7)
405 declare <2 x double> @llvm.x86.sse41.dppd(<2 x double>, <2 x double>, i8) nounwind readnone
417 %res = call <4 x float> @llvm.x86.sse41.dpps(<4 x float> %a0, <4 x float> %a1, i8 7)
420 declare <4 x float> @llvm.x86.sse41.dpps(<4 x float>, <4 x float>, i8) nounwind readnone
483 %res = call <2 x double> @llvm.x86.sse41.round.pd(<2 x double> %a0, i32 1)
497 %res = call <4 x float> @llvm.x86.sse41.round.ps(<4 x float> %a0, i32 1)
511 %res = call <2 x double> @llvm.x86.sse41.round.sd(<2 x double> %a0, <2 x double> %a1, i32 1)
525 %res = call <4 x float> @llvm.x86.sse41.round.ss(<4 x float> %a0, <4 x float> %a1, i32 1)
588 %res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i8 4)
591 declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i8) nounwind readnone
748 %res = call <8 x i16> @llvm.x86.sse41.phminposuw(<8 x i16> %arg0)
752 declare <8 x i16> @llvm.x86.sse41.phminposuw(<8 x i16>) nounwind readnone
766 %res = call <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8> %arg0, <16 x i8> %arg1, i8 1)
770 declare <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8>, <16 x i8>, i8) nounwind readnone
784 %res = call <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32> %arg0, <4 x i32> %arg1)
787 declare <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32>, <4 x i32>) nounwind readnone
818 %res = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %arg0, <4 x i32> %arg1)
822 declare <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32>, <4 x i32>) nounwind readnone
834 %res = call <2 x double> @llvm.x86.sse41.round.pd(<2 x double> %a0, i32 4)
848 %res = call <4 x float> @llvm.x86.sse41.round.ps(<4 x float> %a0, i32 4)
862 %res = call <2 x double> @llvm.x86.sse41.round.sd(<2 x double> %a0, <2 x double> %a1, i32 4)
876 %res = call <4 x float> @llvm.x86.sse41.round.ss(<4 x float> %a0, <4 x float> %a1, i32 4)
892 %res = call <2 x i64> @llvm.x86.sse41.movntdqa(i8* %arg0)
895 declare <2 x i64> @llvm.x86.sse41.movntdqa(i8*) nounwind readnone
913 %res = call i32 @llvm.x86.sse41.ptestc(<2 x i64> %a0, <2 x i64> <i64 -1, i64 -1>)
916 declare i32 @llvm.x86.sse41.ptestc(<2 x i64>, <2 x i64>) nounwind readnone
932 %res = call i32 @llvm.x86.sse41.ptestz(<2 x i64> %a0, <2 x i64> %a1)
935 declare i32 @llvm.x86.sse41.ptestz(<2 x i64>, <2 x i64>) nounwind readnone
951 %res = call i32 @llvm.x86.sse41.ptestnzc(<2 x i64> %a0, <2 x i64> %a1)
954 declare i32 @llvm.x86.sse41.ptestnzc(<2 x i64>, <2 x i64>) nounwind readnone
970 %res = call i32 @llvm.x86.sse41.ptestc(<2 x i64> %a0, <2 x i64> %a1)
988 %res = call i32 @llvm.x86.sse41.ptestnzc(<2 x i64> %a0, <2 x i64> %a1)
1006 %res = call i32 @llvm.x86.sse41.ptestz(<2 x i64> %a0, <2 x i64> %a1)