Index: lib/Target/X86/X86ISelLowering.cpp =================================================================== --- lib/Target/X86/X86ISelLowering.cpp +++ lib/Target/X86/X86ISelLowering.cpp @@ -38717,8 +38717,7 @@ return true; // See if this is a single use constant which can be constant folded. - SDValue BC = peekThroughOneUseBitcasts(Op); - return ISD::isBuildVectorOfConstantSDNodes(BC.getNode()); + return ISD::isBuildVectorOfConstantSDNodes(Op.getNode()); }; auto TruncateArithmetic = [&](SDValue N0, SDValue N1) { Index: test/CodeGen/X86/pr40891.ll =================================================================== --- /dev/null +++ test/CodeGen/X86/pr40891.ll @@ -0,0 +1,22 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=avx2 | FileCheck %s + +; Make sure this sequence doesn't hang in DAG combine. + +define <8 x i32> @foo(<8 x i64> %x, <4 x i64> %y) { +; CHECK-LABEL: foo: +; CHECK: # %bb.0: +; CHECK-NEXT: vandps %ymm2, %ymm0, %ymm0 +; CHECK-NEXT: vandps {{\.LCPI.*}}, %ymm1, %ymm1 +; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm2 +; CHECK-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2] +; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm2 +; CHECK-NEXT: vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2] +; CHECK-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0 +; CHECK-NEXT: retl + %a = shufflevector <4 x i64> %y, <4 x i64> , <8 x i32> + %b = and <8 x i64> %x, %a + %c = trunc <8 x i64> %b to <8 x i32> + ret <8 x i32> %c +} +