diff options
| -rw-r--r-- | llvm/test/CodeGen/X86/vector-shuffle-combining-xop.ll | 23 |
1 files changed, 23 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-combining-xop.ll b/llvm/test/CodeGen/X86/vector-shuffle-combining-xop.ll index d7073d6f67a..b81b57f9474 100644 --- a/llvm/test/CodeGen/X86/vector-shuffle-combining-xop.ll +++ b/llvm/test/CodeGen/X86/vector-shuffle-combining-xop.ll @@ -272,6 +272,29 @@ define <4 x i32> @combine_vpperm_10zz32BA(<4 x i32> %a0, <4 x i32> %a1) { ret <4 x i32> %res3 } +define void @buildvector_v4f23_0404(float %a, float %b, <4 x float>* %ptr) { +; X32-LABEL: buildvector_v4f23_0404: +; X32: # BB#0: +; X32-NEXT: movl {{[0-9]+}}(%esp), %eax +; X32-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero +; X32-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3] +; X32-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0] +; X32-NEXT: vmovaps %xmm0, (%eax) +; X32-NEXT: retl +; +; X64-LABEL: buildvector_v4f23_0404: +; X64: # BB#0: +; X64-NEXT: vpermil2ps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[0],xmm1[0] +; X64-NEXT: vmovaps %xmm0, (%rdi) +; X64-NEXT: retq + %v0 = insertelement <4 x float> undef, float %a, i32 0 + %v1 = insertelement <4 x float> %v0, float %b, i32 1 + %v2 = insertelement <4 x float> %v1, float %a, i32 2 + %v3 = insertelement <4 x float> %v2, float %b, i32 3 + store <4 x float> %v3, <4 x float>* %ptr + ret void +} + define <2 x double> @constant_fold_vpermil2pd() { ; X32-LABEL: constant_fold_vpermil2pd: ; X32: # BB#0: |
