From 6953b324750de9978e7c9d1d50c269a12fb38cc1 Mon Sep 17 00:00:00 2001 From: Pierre Gousseau Date: Thu, 9 Feb 2017 14:43:58 +0000 Subject: [PATCH] [X86][btver2] PR31902: Fix a crash in combineOrCmpEqZeroToCtlzSrl under fast math. In combineOrCmpEqZeroToCtlzSrl, replace "getConstantOperand == 0" by "isNullConstant" to account for floating point constants. Differential Revision: https://reviews.llvm.org/D29756 llvm-svn: 294588 --- llvm/lib/Target/X86/X86ISelLowering.cpp | 2 +- llvm/test/CodeGen/X86/lzcnt-zext-cmp.ll | 31 +++++++++++++++++++++++++ 2 files changed, 32 insertions(+), 1 deletion(-) diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp index 6f9f6771e33a..1ca1402a1a9e 100644 --- a/llvm/lib/Target/X86/X86ISelLowering.cpp +++ b/llvm/lib/Target/X86/X86ISelLowering.cpp @@ -31166,7 +31166,7 @@ static SDValue combineOrCmpEqZeroToCtlzSrl(SDNode *N, SelectionDAG &DAG, return N->getOpcode() == X86ISD::SETCC && N->hasOneUse() && X86::CondCode(N->getConstantOperandVal(0)) == X86::COND_E && N->getOperand(1).getOpcode() == X86ISD::CMP && - N->getOperand(1).getConstantOperandVal(1) == 0 && + isNullConstant(N->getOperand(1).getOperand(1)) && N->getOperand(1).getValueType().bitsGE(MVT::i32); }; diff --git a/llvm/test/CodeGen/X86/lzcnt-zext-cmp.ll b/llvm/test/CodeGen/X86/lzcnt-zext-cmp.ll index c69dbf573f46..6465e370c974 100644 --- a/llvm/test/CodeGen/X86/lzcnt-zext-cmp.ll +++ b/llvm/test/CodeGen/X86/lzcnt-zext-cmp.ll @@ -341,3 +341,34 @@ entry: %lor.ext = zext i1 %0 to i32 ret i32 %lor.ext } + +; PR31902 Fix a crash in combineOrCmpEqZeroToCtlzSrl under fast math. +define i32 @test_zext_cmp11(double %a, double %b) "no-nans-fp-math"="true" { +; CHECK-LABEL: test_zext_cmp11: +; CHECK: # BB#0: # %entry +; CHECK-NEXT: vxorps %xmm2, %xmm2, %xmm2 +; CHECK-NEXT: vucomisd %xmm2, %xmm0 +; CHECK-NEXT: sete %al +; CHECK-NEXT: vucomisd %xmm2, %xmm1 +; CHECK-NEXT: sete %cl +; CHECK-NEXT: orb %al, %cl +; CHECK-NEXT: movzbl %cl, %eax +; CHECK-NEXT: retq +; +; NOFASTLZCNT-LABEL: test_zext_cmp11: +; NOFASTLZCNT: # BB#0: # %entry +; NOFASTLZCNT-NEXT: vxorps %xmm2, %xmm2, %xmm2 +; NOFASTLZCNT-NEXT: vucomisd %xmm2, %xmm0 +; NOFASTLZCNT-NEXT: sete %al +; NOFASTLZCNT-NEXT: vucomisd %xmm2, %xmm1 +; NOFASTLZCNT-NEXT: sete %cl +; NOFASTLZCNT-NEXT: orb %al, %cl +; NOFASTLZCNT-NEXT: movzbl %cl, %eax +; NOFASTLZCNT-NEXT: retq +entry: + %cmp = fcmp fast oeq double %a, 0.000000e+00 + %cmp1 = fcmp fast oeq double %b, 0.000000e+00 + %0 = or i1 %cmp, %cmp1 + %conv = zext i1 %0 to i32 + ret i32 %conv +}