diff options
| author | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2017-04-06 18:15:44 +0000 |
|---|---|---|
| committer | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2017-04-06 18:15:44 +0000 |
| commit | 921a42314b411a69a5fb983eeab931eae6f958ab (patch) | |
| tree | 098a8f0cbca9c8d4caaeb0ece5de2c282169446a /llvm/lib/IR/Module.cpp | |
| parent | 95776ad5b8d462432ded2557ad5890cd78b983f3 (diff) | |
| download | llvm-921a42314b411a69a5fb983eeab931eae6f958ab.zip llvm-921a42314b411a69a5fb983eeab931eae6f958ab.tar.gz llvm-921a42314b411a69a5fb983eeab931eae6f958ab.tar.bz2 | |
[AMDGPU] Translate reqd_work_group_size into amdgpu_flat_work_group_size
These two attributes specify the same info in a different way.
AMGPU BE only checks the latter as a target specific attribute
as opposed to language specific reqd_work_group_size.
This change produces amdgpu_flat_work_group_size out of
reqd_work_group_size if specified.
Differential Revision: https://reviews.llvm.org/D31728
llvm-svn: 299678
Diffstat (limited to 'llvm/lib/IR/Module.cpp')
0 files changed, 0 insertions, 0 deletions