[llvm-dev] Loop Access Analysis

[Min-Yih Hsu via llvm-dev]

The Loop Optimization Working Group had a survey about “canonical” loop required by each loop transformation or analysis. That is, what should we normalize a loop before running a certain loop pass.

Here is the survey result: https://tinyurl.com/rhuzny2
(Note that there are two workspaces: “By precondition” and “Breakdown”)

Best
- Min

> On Dec 22, 2019, at 2:40 AM, Shraiysh Vaishay via llvm-dev <llvm-dev at lists.llvm.org> wrote:
> 
> Hi all,
> 
> Just putting this here in case someone else stumbles upon this.
> 
> So, it looks like it is important to rotate the loop for the pass to run properly. Running `-passes="function(mem2reg,loop(rotate))"` started displaying proper analysis.
> A related issue was mentioned earlier [here](https://lists.llvm.org/pipermail/llvm-dev/2013-May/062260.html <https://lists.llvm.org/pipermail/llvm-dev/2013-May/062260.html>)
> 
> Regards,
> Shraiysh
> 
> 
> On Sat, Dec 21, 2019 at 3:33 PM Shraiysh Vaishay <cs17btech11050 at iith.ac.in <mailto:cs17btech11050 at iith.ac.in>> wrote:
> Hi all,
> 
> What kind of input loop is expected for the loop-access pass to run smoothly?
> Also, what passes (like mem2reg) should be run to ensure the desired form is attained. Is running mem2reg, indvars and loop-simplify enough for that?
> 
> Any help will be appreciated.
> 
> Thanks and regards,
> Shraiysh
> _______________________________________________
> LLVM Developers mailing list
> llvm-dev at lists.llvm.org
> https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20191222/bedd494a/attachment.html>