diff options
| author | Pankaj Dwivedi <pankajkumar.divedi@amd.com> | 2025-10-29 11:56:43 +0530 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-10-29 11:56:43 +0530 |
| commit | 20532c0aab266b39cd6e1047f5985585e8c92551 (patch) | |
| tree | fca9b9f639e01f0eca7be311ff8a527a67c21797 /llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp | |
| parent | 09262656f32ab3f2e1d82e5342ba37eecac52522 (diff) | |
[AMDGPU] make AMDGPUUniformIntrinsicCombine a function pass (#165265)
There has been an issue(using function analysis inside the module pass
in OPM) integrating this pass into the LLC pipeline, which currently
lacks NPM support. I tried finding a way to get the per-function
analysis, but it seems that in OPM, we don't have that option.
So the best approach would be to make it a function pass.
Ref: https://github.com/llvm/llvm-project/pull/116953
Diffstat (limited to 'llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp')
| -rw-r--r-- | llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp | 7 |
1 files changed, 4 insertions, 3 deletions
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp index 6214f4db87e1..75a94ac89181 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp +++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp @@ -619,6 +619,7 @@ extern "C" LLVM_ABI LLVM_EXTERNAL_VISIBILITY void LLVMInitializeAMDGPUTarget() { initializeAMDGPUPreloadKernArgPrologLegacyPass(*PR); initializeAMDGPUWaitSGPRHazardsLegacyPass(*PR); initializeAMDGPUPreloadKernelArgumentsLegacyPass(*PR); + initializeAMDGPUUniformIntrinsicCombineLegacyPass(*PR); } static std::unique_ptr<TargetLoweringObjectFile> createTLOF(const Triple &TT) { @@ -887,9 +888,6 @@ void AMDGPUTargetMachine::registerPassBuilderCallbacks(PassBuilder &PB) { if (EarlyInlineAll && !EnableFunctionCalls) PM.addPass(AMDGPUAlwaysInlinePass()); - - if (EnableUniformIntrinsicCombine) - PM.addPass(AMDGPUUniformIntrinsicCombinePass()); }); PB.registerPeepholeEPCallback( @@ -900,6 +898,9 @@ void AMDGPUTargetMachine::registerPassBuilderCallbacks(PassBuilder &PB) { FPM.addPass(AMDGPUUseNativeCallsPass()); if (EnableLibCallSimplify) FPM.addPass(AMDGPUSimplifyLibCallsPass()); + + if (EnableUniformIntrinsicCombine) + FPM.addPass(AMDGPUUniformIntrinsicCombinePass()); }); PB.registerCGSCCOptimizerLateEPCallback( |