[PATCH] D80639: AMDGPU: Support non-entry block static sized allocas

[Johannes Doerfert via Phabricator via llvm-commits]

jdoerfert added a comment.

In D80639#2070155 <https://reviews.llvm.org/D80639#2070155>, @ronlieb wrote:

> Johannes: here is a reduce source test case, let me know what else you might need?
>
> #include <stdio.h>
>
> int main (void)
>  {
>
>   int ng =12;
>   int nxyz = 5000;
>   #pragma omp target teams distribute 
>   for (int gid = 0; gid < nxyz; gid++) {
>     #pragma omp parallel for
>     for (unsigned int g = 0; g < ng; g++) {
>         int a = 0;
>     }  
>   }
>   return 0;
>
> }


@ronlieb Thx. This is a "bug" in OpenMPOpt we need to address there. I'll put it on my (mental) to do list.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80639/new/

https://reviews.llvm.org/D80639