diff options
Diffstat (limited to 'llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp')
| -rw-r--r-- | llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp | 11 |
1 files changed, 9 insertions, 2 deletions
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp b/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp index 0574c99..13b4b50 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp +++ b/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp @@ -24,16 +24,23 @@ AMDGPUMachineFunction::AMDGPUMachineFunction(const MachineFunction &MF) : NoSignedZerosFPMath(MF.getTarget().Options.NoSignedZerosFPMath), MemoryBound(false), WaveLimiter(false) { + const AMDGPUSubtarget &ST = AMDGPUSubtarget::get(MF); + // FIXME: Should initialize KernArgSize based on ExplicitKernelArgOffset, // except reserved size is not correctly aligned. + const Function &F = MF.getFunction(); if (auto *Resolver = MF.getMMI().getResolver()) { if (AMDGPUPerfHintAnalysis *PHA = static_cast<AMDGPUPerfHintAnalysis*>( Resolver->getAnalysisIfAvailable(&AMDGPUPerfHintAnalysisID, true))) { - MemoryBound = PHA->isMemoryBound(&MF.getFunction()); - WaveLimiter = PHA->needsWaveLimiter(&MF.getFunction()); + MemoryBound = PHA->isMemoryBound(&F); + WaveLimiter = PHA->needsWaveLimiter(&F); } } + + CallingConv::ID CC = F.getCallingConv(); + if (CC == CallingConv::AMDGPU_KERNEL || CC == CallingConv::SPIR_KERNEL) + ExplicitKernArgSize = ST.getExplicitKernArgSize(F, MaxKernArgAlign); } unsigned AMDGPUMachineFunction::allocateLDSGlobal(const DataLayout &DL, |