[PATCH] D28368: Give higher full-unroll boosting when the loop iteration is small.

[Hal Finkel via Phabricator via llvm-commits]

hfinkel added a comment.

In https://reviews.llvm.org/D28368#637335, @danielcdh wrote:

> In https://reviews.llvm.org/D28368#637192, @hfinkel wrote:
>
> > So 464.h264ref is getting a bit larger and faster or slower?
>
>
> Yes, it's 3% larger (text size). The performance difference is in noise range (it disappears in a different run).


Is that a concern, or is it just a small benchmark?


https://reviews.llvm.org/D28368