Index: llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp =================================================================== --- llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp +++ llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp @@ -785,9 +785,10 @@ break; case ReorderingMode::Opcode: // We accept both Instructions and Undefs, but with different scores. - if ((isa(Op) && + if ((isa(Op) && isa(OpLastLane) && cast(Op)->getOpcode() == cast(OpLastLane)->getOpcode()) || + (isa(OpLastLane) && isa(Op)) || isa(Op)) { // An instruction has a higher score than an undef. unsigned Score = (isa(Op)) ? GoodScore : BestScore; Index: llvm/trunk/test/Transforms/SLPVectorizer/X86/crash_reordering_undefs.ll =================================================================== --- llvm/trunk/test/Transforms/SLPVectorizer/X86/crash_reordering_undefs.ll +++ llvm/trunk/test/Transforms/SLPVectorizer/X86/crash_reordering_undefs.ll @@ -0,0 +1,47 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt -slp-vectorizer -S < %s -mtriple=x86_64-unknown-linux -mcpu=corei7-avx | FileCheck %s + +define i32 @crash_reordering_undefs() { +; CHECK-LABEL: @crash_reordering_undefs( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[OR0:%.*]] = or i64 undef, undef +; CHECK-NEXT: [[CMP0:%.*]] = icmp eq i64 undef, [[OR0]] +; CHECK-NEXT: [[ADD0:%.*]] = select i1 [[CMP0]], i32 65536, i32 65537 +; CHECK-NEXT: [[ADD1:%.*]] = add i32 undef, [[ADD0]] +; CHECK-NEXT: [[CMP1:%.*]] = icmp eq i64 undef, undef +; CHECK-NEXT: [[ADD2:%.*]] = select i1 [[CMP1]], i32 65536, i32 65537 +; CHECK-NEXT: [[ADD3:%.*]] = add i32 [[ADD1]], [[ADD2]] +; CHECK-NEXT: [[CMP2:%.*]] = icmp eq i64 undef, undef +; CHECK-NEXT: [[ADD4:%.*]] = select i1 [[CMP2]], i32 65536, i32 65537 +; CHECK-NEXT: [[ADD5:%.*]] = add i32 [[ADD3]], [[ADD4]] +; CHECK-NEXT: [[ADD6:%.*]] = add i32 [[ADD5]], undef +; CHECK-NEXT: [[ADD7:%.*]] = add i32 [[ADD6]], undef +; CHECK-NEXT: [[ADD8:%.*]] = add i32 [[ADD7]], undef +; CHECK-NEXT: [[OR1:%.*]] = or i64 undef, undef +; CHECK-NEXT: [[CMP3:%.*]] = icmp eq i64 undef, [[OR1]] +; CHECK-NEXT: [[ADD9:%.*]] = select i1 [[CMP3]], i32 65536, i32 65537 +; CHECK-NEXT: [[ADD10:%.*]] = add i32 [[ADD8]], [[ADD9]] +; CHECK-NEXT: [[ADD11:%.*]] = add i32 [[ADD10]], undef +; CHECK-NEXT: ret i32 [[ADD11]] +; +entry: + %or0 = or i64 undef, undef + %cmp0 = icmp eq i64 undef, %or0 + %add0 = select i1 %cmp0, i32 65536, i32 65537 + %add1 = add i32 undef, %add0 + %cmp1 = icmp eq i64 undef, undef + %add2 = select i1 %cmp1, i32 65536, i32 65537 + %add3 = add i32 %add1, %add2 + %cmp2 = icmp eq i64 undef, undef + %add4 = select i1 %cmp2, i32 65536, i32 65537 + %add5 = add i32 %add3, %add4 + %add6 = add i32 %add5, undef + %add7 = add i32 %add6, undef + %add8 = add i32 %add7, undef + %or1 = or i64 undef, undef + %cmp3 = icmp eq i64 undef, %or1 + %add9 = select i1 %cmp3, i32 65536, i32 65537 + %add10 = add i32 %add8, %add9 + %add11 = add i32 %add10, undef + ret i32 %add11 +}