[PATCH] D67948: [LV] Interleaving should not exceed estimated loop trip count.

[Aaron H Liu via Phabricator via llvm-commits]

AaronLiu added a comment.

In D67948#2083216 <https://reviews.llvm.org/D67948#2083216>, @xbolva00 wrote:

> In D67948#1731021 <https://reviews.llvm.org/D67948#1731021>, @hsaito wrote:
>
> > We have observed some performance regressions, presumably because the vectorized code started to kick-in on short estimated trip count loops (as opposed to skipping vector code and execute scalar code). We'll try following up with cost model tuning. I'm not too surprised if others also hit a similar issue. Overall, though, that's the right direction to head to.
>
>
> This was fixed?


>From my testing, one of the bmk degraded 20+% at peak last year, but now with the patch in D81416 <https://reviews.llvm.org/D81416> it is confirmed that it can get 50+% performance gain.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D67948/new/

https://reviews.llvm.org/D67948