[PATCH] D31762: AMDGPU: Add new amdgcn.init.exec intrinsics

[Nicolai Hähnle via Phabricator via llvm-commits]

nhaehnle added a comment.

In https://reviews.llvm.org/D31762#735590, @mareko wrote:

> In https://reviews.llvm.org/D31762#735585, @nhaehnle wrote:
>
> > Is it at all possible to get merged shaders where either part has thread_count == 0? We might want a way to annotate branches so that the skip-jump for EXEC=0 is not introduced.
>
>
> Yes, thread_count == 0 is possible, and it's explained here: https://patchwork.freedesktop.org/patch/152356/


Ah, so that's why the barrier instruction is needed between shader parts? Interesting.


https://reviews.llvm.org/D31762