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

[Marek Olšák via Phabricator via llvm-commits]

mareko updated this revision to Diff 129282.
mareko added a comment.

Only scalar loads support 32-bit pointers. An address in a VGPR will
fail to compile. That's OK because the results of loads will only be used
in places where VGPRs are forbidden.

Updated AMDGPUAliasAnalysis and used SReg_64_XEXEC.
The tests cover all uses cases we need for Mesa.

I don't know whether handling CONSTANT_ADDRESS_32BIT everywhere
is necessary. Comments welcome.


https://reviews.llvm.org/D41651

Files:
  lib/Target/AMDGPU/AMDGPU.h
  lib/Target/AMDGPU/AMDGPUAliasAnalysis.cpp
  lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
  lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
  lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
  lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
  lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
  lib/Target/AMDGPU/SIISelLowering.cpp
  lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
  lib/Target/AMDGPU/SIMachineFunctionInfo.h
  lib/Target/AMDGPU/SMInstructions.td
  lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
  test/CodeGen/AMDGPU/constant-address-space-32bit.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D41651.129282.patch
Type: text/x-patch
Size: 23553 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180110/6e4afe8d/attachment-0001.bin>