[Openmp-commits] [PATCH] D51875: [OPENMP][NVPTX] Add support for lastprivates/reductions handling in SPMD constructs with lightweight runtime.

[Jonas Hahnfeld via Phabricator via Openmp-commits]

Hahnfeld added a comment.

In https://reviews.llvm.org/D51875#1249019, @ABataev wrote:

> No, you're not correct here.
>
>   void outlined_target_fn(int *last) {
>     int *last_ds = /* get data sharing frame from runtime */
>     for (/* distribute loop from 0 to 9999 */) {
>       outlined_parallel_fn(lb, ub, last_ds);
>     }
>     if (/* received last chunk */) {
>       *last = *last_ds;
>     }
>   }
>
>
> This code is for the distribute loop. And here you have conflict without the datasharing scheme. The problem here is that this check `/* received last chunk */` is `true` for all inner loop iterations for inner `for` directive and `*last_ds` may come not from the last iteration of `for` loop, but from some other iterations. To solve this problem, we need to share the same `last_ds` between all the threads in the team.


Yes, that's the current solution in Clang and actually what I described above:

In https://reviews.llvm.org/D51875#1248997, @Hahnfeld wrote:

> In SPMD constructs all CUDA threads are executing the `distribute` loop, but only the thread executing the last iteration of the `for` loop has seen the `lastprivate` value. However the information of which thread this is has been lost at the end of the `parallel` region. So data sharing is used to communicate the `lastprivate` value to all threads in the team that is executing the last `distribute` chunk.


I'm assuming that the pointer returned by `/* get data sharing frame from runtime */` is shared between all threads in a team.


Repository:
  rL LLVM

https://reviews.llvm.org/D51875