Index: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp =================================================================== --- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp +++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp @@ -5269,11 +5269,17 @@ unsigned I1 = cast(Op1.getOperand(1))->getZExtValue(); if (i * 2 < NumElts) { - if (V0.getOpcode() == ISD::UNDEF) + if (V0.getOpcode() == ISD::UNDEF) { V0 = Op0.getOperand(0); + if (V0.getValueType() != VT) + return false; + } } else { - if (V1.getOpcode() == ISD::UNDEF) + if (V1.getOpcode() == ISD::UNDEF) { V1 = Op0.getOperand(0); + if (V1.getValueType() != VT) + return false; + } if (i * 2 == NumElts) ExpectedVExtractIdx = BaseIdx; } @@ -5423,10 +5429,16 @@ SubFound = true; // Update InVec0 and InVec1. - if (InVec0.getOpcode() == ISD::UNDEF) + if (InVec0.getOpcode() == ISD::UNDEF) { InVec0 = Op0.getOperand(0); - if (InVec1.getOpcode() == ISD::UNDEF) + if (InVec0.getValueType() != VT) + return SDValue(); + } + if (InVec1.getOpcode() == ISD::UNDEF) { InVec1 = Op1.getOperand(0); + if (InVec1.getValueType() != VT) + return SDValue(); + } // Make sure that operands in input to each add/sub node always // come from a same pair of vectors. Index: llvm/trunk/test/CodeGen/X86/sse3-avx-addsub-2.ll =================================================================== --- llvm/trunk/test/CodeGen/X86/sse3-avx-addsub-2.ll +++ llvm/trunk/test/CodeGen/X86/sse3-avx-addsub-2.ll @@ -315,4 +315,17 @@ ; CHECK-NOT: addsubps ; CHECK: ret - +define <2 x float> @test_v2f32(<2 x float> %v0, <2 x float> %v1) { + %v2 = extractelement <2 x float> %v0, i32 0 + %v3 = extractelement <2 x float> %v1, i32 0 + %v4 = extractelement <2 x float> %v0, i32 1 + %v5 = extractelement <2 x float> %v1, i32 1 + %sub = fsub float %v2, %v3 + %add = fadd float %v5, %v4 + %res0 = insertelement <2 x float> undef, float %sub, i32 0 + %res1 = insertelement <2 x float> %res0, float %add, i32 1 + ret <2 x float> %res1 +} +; CHECK-LABEL: test_v2f32 +; CHECK: addsubps %xmm1, %xmm0 +; CHECK-NEXT: retq