[PATCH] D89566: [LV] Epilogue Vectorization with Optimal Control Flow

Mon Nov 9 02:27:49 PST 2020

mivnay added a comment.

In D89566#2380882 <https://reviews.llvm.org/D89566#2380882>, @Prashanth wrote:

> In D89566#2379562 <https://reviews.llvm.org/D89566#2379562>, @SjoerdMeijer wrote:
>
>> I also think "blocking" is not the right terminology here. But I was asking about this because first we had D88819 <https://reviews.llvm.org/D88819>, then came this one, so we have 2 options. In the end it's pretty simple I guess, because we go for the one with the best code-gen, and this patch looks like the one with the most potential. But would be nice to get that confirmed.
>
> On Thunderx2 , x264, 1c, rate : 
> Base : 3.31
> With this patch : 3.50
> With D88819 <https://reviews.llvm.org/D88819> : 3.60

Here are the numbers with `-O3 -flto -fuse-ld=lld` : F13796211: Screenshot from 2020-11-09 15-56-26.png <https://reviews.llvm.org/F13796211>

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D89566/new/

https://reviews.llvm.org/D89566