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

[Alexey Bataev via Phabricator via Openmp-commits]

ABataev added a comment.

In D62393#1698433 <https://reviews.llvm.org/D62393#1698433>, @JonChesterfield wrote:

> > I'm *very* unhappy to claim "The cuda8 compiler is too optimistic and makes some incorrect optimizations" without actually understanding what the problem is
>
> That seems fair. At the least, the comment could be more specific.
>
> I thought the salient part of the patch was `"memory"` working around a compiler bug that reordered memory accesses incorrectly. On a closer look though, the comment suggests the fix is actually the `.volatile.` qualifier on the instruction influencing ptxas. If so, a volatile qualifier on the byte array would presumably also be a fix. Why is the underlying byte array not volatile qualified?


I will fix the description and the title. The fix is strictly for cuda8, cuda9 and later do not have this problem.
as tot he volatile modifi3r, read the whole thread. There was a big discussion about it.


Repository:
  rOMP OpenMP

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

https://reviews.llvm.org/D62393