[PATCH] D73444: AMDGPU/GlobalISel: Legalize TFE image result loads

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added a comment.

In D73444#1842406 <https://reviews.llvm.org/D73444#1842406>, @nhaehnle wrote:

> Correct, TFE does not apply to store or atomic. Stores or atomics to unmapped partially-resident images will simply be ignored by the hardware (and atomic return values are undefined).
>
> Do all cases still work in terms of how the intended semantics for the (super ugly) unpacked f16 case are represented? It seems a bit fragile.


I think so. In the unpacked f16 case, this will load in a way that looks identical to f32, except with the truncates after to the natural packed type


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D73444/new/

https://reviews.llvm.org/D73444