AMDGPU/SI: Don't promote alloca to vector for atomic load/store
Summary:
Don't promote alloca to vector for atomic load/store
Reviewer:
arsenm
Differential Revision:
https://reviews.llvm.org/D46085
Description
Description
Details
Details
- Committed
chfang May 17 2018, 2:49 PM - Differential Revision
- D46085: AMDGPU/SI: Don't promote alloca to vector for atomic load/store
- Parents
- rL332672: Revert "[pdb] Change /DEBUG:GHASH to emit 8 byte hashes."
- Branches
- Unknown
- Tags