diff options
Diffstat (limited to 'llvm/lib/Target')
| -rw-r--r-- | llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp | 2 | ||||
| -rw-r--r-- | llvm/lib/Target/AMDGPU/SIPeepholeSDWA.cpp | 9 |
2 files changed, 5 insertions, 6 deletions
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp index c6c20b81352..f03adfc66fa 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp +++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp @@ -105,7 +105,7 @@ static cl::opt<bool> EarlyInlineAll( static cl::opt<bool> EnableSDWAPeephole( "amdgpu-sdwa-peephole", cl::desc("Enable SDWA peepholer"), - cl::init(false)); + cl::init(true)); // Enable address space based alias analysis static cl::opt<bool> EnableAMDGPUAliasAnalysis("enable-amdgpu-aa", cl::Hidden, diff --git a/llvm/lib/Target/AMDGPU/SIPeepholeSDWA.cpp b/llvm/lib/Target/AMDGPU/SIPeepholeSDWA.cpp index 67c86c3b8b9..599c9d71552 100644 --- a/llvm/lib/Target/AMDGPU/SIPeepholeSDWA.cpp +++ b/llvm/lib/Target/AMDGPU/SIPeepholeSDWA.cpp @@ -233,11 +233,10 @@ static bool isSubregOf(const MachineOperand &SubReg, if (SuperReg.getReg() != SubReg.getReg()) return false; - LaneBitmask::Type SuperMask = - TRI->getSubRegIndexLaneMask(SuperReg.getSubReg()).getAsInteger(); - LaneBitmask::Type SubMask = - TRI->getSubRegIndexLaneMask(SubReg.getSubReg()).getAsInteger(); - return TRI->regmaskSubsetEqual(&SubMask, &SuperMask); + LaneBitmask SuperMask = TRI->getSubRegIndexLaneMask(SuperReg.getSubReg()); + LaneBitmask SubMask = TRI->getSubRegIndexLaneMask(SubReg.getSubReg()); + SuperMask |= ~SubMask; + return SuperMask.all(); } uint64_t SDWASrcOperand::getSrcMods() const { |

