[PATCH] D138443: [AMDGPU] Fix GCNSubtarget::getMinNumVGPRs, add unit test to check consistency between GCNSubtarget's getMinNumVGPRs, getMaxNumVGPRs and getOccupancyWithNumVGPRs.

[Valery Pykhtin via Phabricator via llvm-commits]

vpykhtin updated this revision to Diff 477411.
vpykhtin marked 2 inline comments as done.
vpykhtin edited the summary of this revision.
vpykhtin added a comment.

Per review issues:

- Don't rely on arch name, use feature bits for wave32.
- Refactored common code for unit tests, unified test namings.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D138443/new/

https://reviews.llvm.org/D138443

Files:
  llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
  llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
  llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
  llvm/test/CodeGen/AMDGPU/occupancy-levels.ll
  llvm/unittests/Target/AMDGPU/AMDGPUUnitTests.cpp
  llvm/unittests/Target/AMDGPU/AMDGPUUnitTests.h
  llvm/unittests/Target/AMDGPU/CMakeLists.txt
  llvm/unittests/Target/AMDGPU/DwarfRegMappings.cpp
  llvm/unittests/Target/AMDGPU/ExecMayBeModifiedBeforeAnyUse.cpp

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D138443.477411.patch
Type: text/x-patch
Size: 14384 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20221123/f59c8e20/attachment.bin>