[PATCH] D110704: [X86][Costmodel] Load/store i8 Stride=2 VF=4 interleaving costs

Wed Sep 29 06:57:03 PDT 2021

lebedev.ri added a comment.

In D110704#3030176 <https://reviews.llvm.org/D110704#3030176>, @lebedev.ri wrote:

> In D110704#3030093 <https://reviews.llvm.org/D110704#3030093>, @RKSimon wrote:
>
>> Before we go any further - do we gain anything by updating BaseT::getInterleavedMemoryOpCost to use getScalarizationOverhead?
>
> It depends on your definition of "anything". It basically doesn't help,
> because the only improvement that gives us not overestimating XMM subreg insertion/extraction from YMM,
> The costs still bogusly high.

FWIW i agree that this is not really great, but what we need is D100486 <https://reviews.llvm.org/D100486>,
and afterwards we should materialize shuffle masks and query their costs.
I was planning on doing that, as i have noted previously in some review.
But even that will overestimate the cost.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D110704/new/

https://reviews.llvm.org/D110704