[PATCH] D111460: [X86][LoopVectorize] "Fix" `X86TTIImpl::getAddressComputationCost()`

Sat Oct 16 06:02:39 PDT 2021

lebedev.ri added a comment.

In D111460#3068296 <https://reviews.llvm.org/D111460#3068296>, @pengfei wrote:

> In D111460#3068291 <https://reviews.llvm.org/D111460#3068291>, @lebedev.ri wrote:
>
>> In D111460#3068289 <https://reviews.llvm.org/D111460#3068289>, @pengfei wrote:
>>
>>> In D111460#3068279 <https://reviews.llvm.org/D111460#3068279>, @lebedev.ri wrote:
>>>
>>>> In D111460#3068276 <https://reviews.llvm.org/D111460#3068276>, @pengfei wrote:
>>>>
>>>>> Sorry, I don't think favoring interleaved loads over gather is always correct.
>>>>
>>>> Where am i doing that?
>>>
>>> Doesn't comments in X86TargetTransformInfo.cpp say this patch is a hack to do that? Or I just understood it the other way around?
>>
>> It's precisely the other way around.
>
> Awkward :( Sorry for that.

No, i agree, this is really confusing.

> Anyway, I want to hold for a while until I'm confident with this patch.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D111460/new/

https://reviews.llvm.org/D111460