[PATCH] D75475: AMDGPU: Fix computation for getOccupancyWithLocalMemSize

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added reviewers: rampitec, kzhuravl, t-tye.
Herald added subscribers: llvm-commits, kerbowa, hiraditya, tpr, dstuttard, yaxunl, nhaehnle, wdng, jvesely.
Herald added a project: LLVM.

The computation here didn't really make sense to me, and reported
wildy different results depending on the flat work group size
attribute.

      

I think this should really report a range derived from the possible
work group size bounds, and only allow an occupancy that is a multiple
of the group size.


https://reviews.llvm.org/D75475

Files:
  llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
  llvm/test/CodeGen/AMDGPU/occupancy-levels.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D75475.247697.patch
Type: text/x-patch
Size: 5935 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200302/86c22735/attachment.bin>