[llvm-dev] LoopSimplify pass prevents loop unrolling

[Balaram Makam via llvm-dev]

I will try to reduce a test case for the regression I found and will update.

 

Thanks,

Balaram

 

From: Friedman, Eli [mailto:efriedma at codeaurora.org] 
Sent: Friday, June 30, 2017 2:54 PM
To: Balaram Makam <bmakam at codeaurora.org>; llvm-dev at lists.llvm.org
Subject: Re: [llvm-dev] LoopSimplify pass prevents loop unrolling

 

On 6/30/2017 11:38 AM, Balaram Makam wrote:

Thanks Eli,

 

I was looking at this code which keeps track of loop headers but is checking
if the destination of branch is a loop header sufficient? This prevents
merging empty preheaders into the loop headers as well.


There isn't really any reason to collapse preheaders anyway; LoopSimplify
will recreate them, and they don't really block other optimizations as far
as I know.




Is that reasonable approach or do we need to skip only if the original
unconditional branch was a backedge and folding this branch might result in
additional backedges? I made a quick hack to find the function backedges and
skip simplifycfg to merge the latch block into the loop header when it
results in an additional backedge. Although it solves my purpose I am not
sure if this the right approach, as finding the backedges looks expensive.


Well, not that expensive to calculate if you cache it, but probably tricky
to keep the cache up-to-date, yes.




I also found a regression with this patch where a huge switch statement with
multiple empty blocks have been skipped from merging resulting in bad code.
Instead, should loopsimplify try to unify multiple exit blocks and collapse
multiple backedges whenever possible instead of splitting it out into a
nested loop?


I'm not sure I follow the issue here.  Could you give an example?



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20170630/462f6d34/attachment.html>