[Openmp-commits] [PATCH] D62393: [OPENMP][NVPTX]Mark parallel level counter as volatile.

Sat Oct 5 14:59:48 PDT 2019

ABataev added a comment.

In D62393#1696341 <https://reviews.llvm.org/D62393#1696341>, @jdoerfert wrote:

> So this changed over time, we for sure need to update the name and maybe commit message.
>
> As @JonChesterfield pointed out, the wrapping of the accesses in function calls is fine.
>  The two functions with inline assembly should live in the target_impl.h though.
>
> At some point it was said this fixes a problem that only occurs with D62318 <https://reviews.llvm.org/D62318> applied.
>  Is this still the case? If not, we need to specify exactly how we can reproduce this issue, e.g., in a comment next to the target offload region.

Yes, it still the case. The cuda8 compiler is too optimistic and makes some incorrect optimizations with D62318 <https://reviews.llvm.org/D62318>. This patch prevents these optimizations. Cuda9 and later have no such problems.

Repository:
  rOMP OpenMP

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D62393/new/

https://reviews.llvm.org/D62393