[PATCH] D154822: Support '-fgpu-default-stream=per-thread' for NVIDIA CUDA

[boxu.zhang via Phabricator via cfe-commits]

boxu-zhang added a comment.

In D154822#4485700 <https://reviews.llvm.org/D154822#4485700>, @tra wrote:

> Looking at CUDA headers, it appears that changing only compiler-generated-glue may be insufficient. A lot of other CUDA API calls need to be changed to `_ptsz` variant and for that we need to have `CUDA_API_PER_THREAD_DEFAULT_STREAM` defined.

CUDA_API_PER_THREAD_DEFAULT_STREAM is defined now.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D154822/new/

https://reviews.llvm.org/D154822