[PATCH] D18340: AMDGPU: allow specifying a workgroup size that needs to fit in a compute unit
Bas Nieuwenhuizen via llvm-commits
llvm-commits at lists.llvm.org
Thu Mar 24 14:28:32 PDT 2016
bnieuwenhuizen updated this revision to Diff 51602.
bnieuwenhuizen added a comment.
v3: - adjust reqd_work_group_size FIXME
- removed anonymous namespace
- Use one set of calculations for getMaxWorkGroupSGPRCount
- Add alignDown
http://reviews.llvm.org/D18340
Files:
include/llvm/Support/MathExtras.h
lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
lib/Target/AMDGPU/SIMachineFunctionInfo.h
lib/Target/AMDGPU/SIRegisterInfo.cpp
lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
test/CodeGen/AMDGPU/large-work-group-promote-alloca.ll
test/CodeGen/AMDGPU/large-work-group-registers.ll
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D18340.51602.patch
Type: text/x-patch
Size: 16916 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160324/ed1660f8/attachment.bin>
More information about the llvm-commits
mailing list