[PATCH] D25963: [LoopUnroll] Implement profile-based loop peeling

[Gerolf Hoflehner via llvm-commits]

> On Oct 26, 2016, at 12:39 PM, Xinliang David Li <davidxl at google.com> wrote:
> 
> 
> 
> On Wed, Oct 26, 2016 at 10:08 AM, Gerolf Hoflehner <ghoflehner at apple.com <mailto:ghoflehner at apple.com>> wrote:
> Gerolf added a comment.
> 
> Hi,
> 
> Could you provide more background on this idea?  What is your motivational use case? When the trip count is low why optimize?
> 
> Low trip count loop can be hot too.

But then you would optimize differently. Can you share the example where you actually see gains? 

Thanks
Gerolf

> 
> David
> 
>  
> If the profile is wrong and it actually is a hot loop for a regular/different input set peeling could hurt. There are also side effects on code size, register pressure etc. that could hurt performance.
> 
> Thanks
> Gerolf
> 
> 
> https://reviews.llvm.org/D25963 <https://reviews.llvm.org/D25963>
> 
> 
> 
> 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20161027/f0e11cc8/attachment.html>