Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp =================================================================== --- lib/CodeGen/SelectionDAG/DAGCombiner.cpp +++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp @@ -13325,24 +13325,39 @@ EVT VT = LHSOp.getValueType(); EVT RVT = RHSOp.getValueType(); - if (RVT != VT) { - // Integer BUILD_VECTOR operands may have types larger than the element - // size (e.g., when the element type is not legal). Prior to type - // legalization, the types may not match between the two BUILD_VECTORS. - // Truncate one of the operands to make them match. - if (RVT.getSizeInBits() > VT.getSizeInBits()) { - RHSOp = DAG.getNode(ISD::TRUNCATE, SDLoc(N), VT, RHSOp); - } else { - LHSOp = DAG.getNode(ISD::TRUNCATE, SDLoc(N), RVT, LHSOp); - VT = RVT; - } + EVT ST = VT; + + if (RVT.getSizeInBits() < VT.getSizeInBits()) + ST = RVT; + + // Integer BUILD_VECTOR operands may have types larger than the element + // size (e.g., when the element type is not legal). Prior to type + // legalization, the types may not match between the two BUILD_VECTORS. + // Truncate the operands to make them match. + if (VT.getSizeInBits() != LHS.getValueType().getScalarSizeInBits()) { + EVT ScalarT = LHS.getValueType().getScalarType(); + LHSOp = DAG.getNode(ISD::TRUNCATE, SDLoc(N), ScalarT, LHSOp); + VT = LHSOp.getValueType(); + } + if (RVT.getSizeInBits() != RHS.getValueType().getScalarSizeInBits()) { + EVT ScalarT = RHS.getValueType().getScalarType(); + RHSOp = DAG.getNode(ISD::TRUNCATE, SDLoc(N), ScalarT, RHSOp); + RVT = RHSOp.getValueType(); } + SDValue FoldOp = DAG.getNode(N->getOpcode(), SDLoc(LHS), VT, LHSOp, RHSOp); + + // We need the resulting constant to be legal, so zero extend to the + // smallest operand type if required. + if (ST != VT) + FoldOp = DAG.getNode(ISD::ZERO_EXTEND, SDLoc(LHS), ST, FoldOp); + if (FoldOp.getOpcode() != ISD::UNDEF && FoldOp.getOpcode() != ISD::Constant && FoldOp.getOpcode() != ISD::ConstantFP) break; + Ops.push_back(FoldOp); AddToWorklist(FoldOp.getNode()); } Index: test/CodeGen/AArch64/aarch64-smax-constantfold.ll =================================================================== --- /dev/null +++ test/CodeGen/AArch64/aarch64-smax-constantfold.ll @@ -0,0 +1,12 @@ +; RUN: llc -mtriple=aarch64-none-linux-gnu < %s -o -| FileCheck %s + +; Function Attrs: nounwind readnone +declare <4 x i16> @llvm.aarch64.neon.smax.v4i16(<4 x i16>, <4 x i16>) + +; CHECK-LABEL: test +define <4 x i16> @test() { +entry: +; CHECK: movi d{{[0-9]+}}, #0000000000000000 + %0 = tail call <4 x i16> @llvm.aarch64.neon.smax.v4i16(<4 x i16> , <4 x i16> zeroinitializer) + ret <4 x i16> %0 +}