[PATCH] D149281: Must unroll epilogue loops after vectorization on AMDGPU target

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec added a comment.

In D149281#4299934 <https://reviews.llvm.org/D149281#4299934>, @fhahn wrote:

> In D149281#4299890 <https://reviews.llvm.org/D149281#4299890>, @rampitec wrote:
>
>> Add a test?
>
> That would be helpful. It would be good to understand why runtime unrolling is needed here. Does the interleave heuristic not kick in?

I actually meant a simpler formal test to check that unroll works on AMDGPU. I am not sure @alex-t will be able to produce a reasonable test showing performance problem. The loop in question triggered the regression is quite complex to begin with.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D149281/new/

https://reviews.llvm.org/D149281