[PATCH] D143138: AMDGPU: Use module flag to get code object version at IR level

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp:414
     bool SupportsGetDoorbellID = InfoCache.supportsGetDoorbellID(*F);
+    unsigned COV = AMDGPU::getCodeObjectVersion(*F->getParent());
 
----------------
cfang wrote:
> arsenm wrote:
> > Cann move this into AMDGPUInformationCache
> Should we introduce a private field of Module *M in AMDGPUInformationCache? 
> InformationCache itself does not have this field.
> Otherwise, we will have to pass a Module parameter in the call to check code object version each time.
> 
You can directly parse the code object version into the info cache, it won't be shared between modules 


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D143138/new/

https://reviews.llvm.org/D143138