Revision 220239 exposed a latent bug in method
'TargetInstrInfo::commuteInstruction'. When commuting the operands of a machine
instruction, method 'commuteInstruction' didn't correctly propagate the
'IsUndef' flag to the register operands of the new (commuted) instruction.
Before this patch, the following instruction:
%vreg4<def> = VADDSDrr %vreg14, %vreg5<undef>; FR64:%vreg4,%vreg14,%vreg5
was wrongly converted by method 'commuteInstruction' into:
%vreg4<def> = VADDSDrr %vreg5, %vreg14<undef>; FR64:%vreg4,%vreg5,%vreg14
The correct instruction should have been:
%vreg4<def> = VADDSDrr %vreg5<undef>, %vreg14; FR64:%vreg4,%vreg5,%vreg14
This patch fixes the problem in method 'TargetInstrInfo::commuteInstruction'.
When swapping the operands of a machine instruction, we now make sure that
'IsUndef' flags are correctly set.
Added test case 'pr23103.ll'.
Differential Revision: http://reviews.llvm.org/D9406
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@236258
91177308-0d34-0410-b5e6-
96231b3b80d8
unsigned SubReg2 = MI->getOperand(Idx2).getSubReg();
bool Reg1IsKill = MI->getOperand(Idx1).isKill();
bool Reg2IsKill = MI->getOperand(Idx2).isKill();
+ bool Reg1IsUndef = MI->getOperand(Idx1).isUndef();
+ bool Reg2IsUndef = MI->getOperand(Idx2).isUndef();
// If destination is tied to either of the commuted source register, then
// it must be updated.
if (HasDef && Reg0 == Reg1 &&
MI->getOperand(Idx1).setSubReg(SubReg2);
MI->getOperand(Idx2).setIsKill(Reg1IsKill);
MI->getOperand(Idx1).setIsKill(Reg2IsKill);
+ MI->getOperand(Idx2).setIsUndef(Reg1IsUndef);
+ MI->getOperand(Idx1).setIsUndef(Reg2IsUndef);
return MI;
}
--- /dev/null
+; RUN: llc -verify-machineinstrs -mtriple=x86_64-unknown-unknown -mcpu=generic -mattr=+avx < %s | FileCheck %s
+
+; When commuting a VADDSDrr instruction, verify that the 'IsUndef' flag is
+; correctly propagated to the operands of the resulting instruction.
+; Test for PR23103;
+
+declare zeroext i1 @foo(<1 x double>)
+
+define <1 x double> @pr23103(<1 x double>* align 8 %Vp) {
+; CHECK-LABEL: pr23103:
+; CHECK: vmovsd (%rdi), %xmm0
+; CHECK-NEXT: vmovsd %xmm0, {{.*}}(%rsp) {{.*#+}} 8-byte Spill
+; CHECK-NEXT: callq foo
+; CHECK-NEXT: vaddsd {{.*}}(%rsp), %xmm0, %xmm0 {{.*#+}} 8-byte Folded Reload
+; CHECK: retq
+entry:
+ %V = load <1 x double>, <1 x double>* %Vp, align 8
+ %call = call zeroext i1 @foo(<1 x double> %V)
+ %fadd = fadd <1 x double> %V, undef
+ ret <1 x double> %fadd
+}