[PATCH] D28907: [SLP] Fix for PR30787: Failure to beneficially vectorize 'copyable' elements in integer binary ops.

Sat May 22 17:09:43 PDT 2021

ABataev added a comment.

In D28907#2775629 <https://reviews.llvm.org/D28907#2775629>, @xbolva00 wrote:

> In D28907#2770984 <https://reviews.llvm.org/D28907#2770984>, @ABataev wrote:
>
>> In D28907#2770982 <https://reviews.llvm.org/D28907#2770982>, @SjoerdMeijer wrote:
>>
>>> Hello, this work was brought to my attention in D102748 <https://reviews.llvm.org/D102748>. Would be good to get this in, and seems almost finished too. Any plans to pick this up? Otherwise I think I would be interested in doing that.
>>
>> This should be much easier to implement after non-power-2 in SLP support.
>
> Can you explain why?
>
> x1 + 1
> x2
> x3 + 6
> x4 + 8
>
> How that patch will help you? You need to add “fake” noop addition  “ + 0” for x2.

It is pretty similar to non-pow-2 functionality, just instead of undefs need to use 0 for adds, 1 for mul etc. I can't provide more details currently but I'm going to revive it after non-pow-2 patch. I assume we won't need to change scheduling model.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D28907/new/

https://reviews.llvm.org/D28907