[PATCH] D114779: [LV][X86] Sink `LoopVectorizationCostModel::useEmulatedMaskMemRefHack()` further into TTI, disable for X86/AVX2+

[Roman Lebedev via Phabricator via llvm-commits]

lebedev.ri added a comment.

In D114779#3261615 <https://reviews.llvm.org/D114779#3261615>, @RKSimon wrote:

> In D114779#3260815 <https://reviews.llvm.org/D114779#3260815>, @lebedev.ri wrote:
>
>> As per @fhahn's "someone more familiar with X86 cost modeling should review the claim the cost model is fixed :)"
>
> Sorry - I haven't been following this ticket much at all. Where did @fhahn says this and in what context? I can't see that here or D43208 <https://reviews.llvm.org/D43208>

Sorry, that was an IRC disscussion.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D114779/new/

https://reviews.llvm.org/D114779