[PATCH] D41651: AMDGPU: Add 32-bit constant address space

[Marek Olšák via Phabricator via llvm-commits]

mareko added inline comments.


================
Comment at: llvm/trunk/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp:232
 
+  if (MMO->getAddrSpace() == AMDGPUAS::CONSTANT_ADDRESS_32BIT)
+    return true;
----------------
alex-t wrote:
> Is it still uniform even if depends on divergent data?
> Like this:
>   %tid = tail call i32 @llvm.amdgcn.workgroup.id.x()
>   %gep = getelementptr  i32 addrspace(6)* %tid
>   %val = load i32, i32 addrspace(6)*  %gep
> 
> This is not correct
> Moreover, this violates Divergence Analysis results
The address space implies uniformity and is geared towards shader resource descriptor loads where uniformity is required. Non-uniform addresses result in v_readfirstlane. In the future, the implementation can be extended to support non-divergent data and VMEM loads/stores/atomics.


Repository:
  rL LLVM

https://reviews.llvm.org/D41651