[PATCH] D153744: [LoopUnroll] adjust for new `convergent` semantics

Mon Jun 26 07:13:02 PDT 2023

sameerds added a comment.

In D153744#4448501 <https://reviews.llvm.org/D153744#4448501>, @JonChesterfield wrote:

> It's been a multi-year thing with multiple authors, I doubt trawling the history will provide anyone with an accurate idea of what we're currently trying to build.
>
> This stack is revising how control flow is modelled in llvm for GPUs. The failure modes are substantial. Could part of the implementation effort be directed to writing down what the overall algorithm is intended to be, somewhere that is visible outside of AMD? Hopefully that's a direct adaption of whatever design document you are working from internally.

This review points to earlier "parent" reviews. In particular:

D147116 <https://reviews.llvm.org/D147116>: [RFC] Introduce convergence control intrinsics

That's the very first review in this stack.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D153744/new/

https://reviews.llvm.org/D153744