[PATCH] D152798: [AMDGPU][ValueTracking] Handle amdgcn intrinsics that cannot create poison

[Jay Foad via Phabricator via llvm-commits]

foad added a comment.

In D152798#4417027 <https://reviews.llvm.org/D152798#4417027>, @nikic wrote:

> Just to give an obvious counter-example: Load-like intrinsics tend to produce poison (because there might be poison in memory).

I was wondering about that case myself. I don't see the benefit of saying that a load-like intrinsic can return poison, unless the compiler recognizes it as a load well enough to do things like forwarding a previously stored value through it.

In the AMDGPU backend we have lots of load-like intrinsics that are mostly opaque to the compiler, except that it knows they read from some address space.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D152798/new/

https://reviews.llvm.org/D152798