[PATCH] D48586: [AMDGPU] Early expansion of 32 bit udiv/urem

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added a comment.

In https://reviews.llvm.org/D48586#1143253, @rampitec wrote:

> In https://reviews.llvm.org/D48586#1143245, @arsenm wrote:
>
> > Probably should add an update_test_checks test for the full expnasions
>
>
> Probably for scalar cases only. Vectors with scheduler are too unstable. Even scalar will fluctuate with scheduler and RA. Do you think it makes sense to have a separate set of scalar cases?


It's a single IR pass expansion, the scheduler isn't involved


https://reviews.llvm.org/D48586