[PATCH] D29423: [AMDGPU] Account workgroup size in LDS occupancy limits

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec updated this revision to Diff 86724.
rampitec added a comment.

Removed LDS size initialization, it is present in features.
Updated test.


Repository:
  rL LLVM

https://reviews.llvm.org/D29423

Files:
  lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
  lib/Target/AMDGPU/AMDGPUSubtarget.cpp
  lib/Target/AMDGPU/AMDGPUSubtarget.h
  lib/Target/AMDGPU/GCNSchedStrategy.cpp
  test/CodeGen/AMDGPU/indirect-private-64.ll
  test/CodeGen/AMDGPU/large-work-group-promote-alloca.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D29423.86724.patch
Type: text/x-patch
Size: 11193 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170201/03655d48/attachment.bin>