forked from OSchip/llvm-project
7634c64b61
The size of worker_rootS should have been DS_Max_Warp_Number. This reduces memory usage by deviceRTL on AMDGPU from around 2.3GB to around 770MB. Reviewed By: JonChesterfield, jdoerfert Differential Revision: https://reviews.llvm.org/D87084 |
||
---|---|---|
.. | ||
amdgcn | ||
common | ||
nvptx | ||
CMakeLists.txt | ||
interface.h |