[PATCH] Unrolling improvements (target indep. and for x86)

[Chandler Carruth]

On Sun, Feb 23, 2014 at 4:57 PM, Nadav Rotem <nrotem at apple.com> wrote:

> On Feb 21, 2014, at 11:19 PM, Hal Finkel <hfinkel at anl.gov> wrote:
>
> Currently, the vectorizer unrolls only for ILP (or latency hiding),
> subject to the register pressure estimate, and having it also unroll for
> size would be a change to the current behavior. Is that your desire?
>
>
> The loop vectorizer also has a basic size threshold to prevent cases where
> the loop body is too big to fit in the uOp cache.
>

Exactly. My thinking is that both should use the same size threshold.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20140223/fbc8ff3e/attachment.html>