[Openmp-commits] [PATCH] D40722: Add missing memory barrier for queuing locks

[Jonas Hahnfeld via Phabricator via Openmp-commits]

Hahnfeld added a comment.

In https://reviews.llvm.org/D40722#949468, @pawosm01 wrote:

> +1, although I ran this omp_single_copyprivate.c example in a loop 10000 times on two different AArch64 machines (ARMv8 and ARMv8.1) and didn't observe any hangs, before and after applying this patch.


That's the problem with memory consistency... Did you add the `num_threads` clause when testing without the memory barrier? This made it much more likely for me


Repository:
  rOMP OpenMP

https://reviews.llvm.org/D40722