[PATCH] Divergence analysis for GPU programs

[Jingyue Wu]

Hi Fernando,

Thanks for writing these papers on divergence analysis! They are really
useful, and I enjoyed reading them.

I should've talked to you earlier. I didn't know you have an LLVM
implementation already; I only saw from your paper that you implemented the
algorithm on Ocelot.

I'll read the journal version. At the same time, if you have a chance, feel
free to share your implementation!

Best,
Jingyue

On Tue, Mar 24, 2015 at 11:21 AM Fernando Magno Quintao Pereira <
fernando at dcc.ufmg.br> wrote:

> Dear Jingyue,
>
>     I shall review your code, as soon as time allows it (OOPSLA's
> deadline is just tomorrow). But, just in case, I would like to point
> you out to this paper: http://dl.acm.org/citation.cfm?id=2523815 I
> believe that nowadays that is the most definitive description of the
> divergence analysis. In particular, your algorithm is Section 3.3.
>
> Regards,
>
> Fernando
>
>
> ---------- Forwarded message ----------
> From: Daniel Berlin <dberlin at dberlin.org>
> Date: Tue, Mar 24, 2015 at 2:56 PM
> Subject: Re: [PATCH] Divergence analysis for GPU programs
> To: reviews+D8576+public+5cb1d077b321f30e at reviews.llvm.org
> Cc: Jingyue Wu <jingyue at google.com>, Owen Anderson <resistor at mac.com>,
> Hal Finkel <hfinkel at anl.gov>, Eli Bendersky <eliben at google.com>, Mark
> Heffernan <meheff at google.com>, Justin Holewinski
> <justin.holewinski at gmail.com>, Commit Messages and Patches for LLVM
> <llvm-commits at cs.uiuc.edu>, fernando at dcc.ufmg.br
>
>
> +fernando, who wrote the paper on divergence analysis you cite (and
> some follow-ons, i believe), and had an LLVM implementation of it.
> It may make sense for him to look over the algorithm itself.
>
>
> (Note that looking at your paper, i'll point out their is a version
> that handles affine constraints, etc at
> https://hal.inria.fr/hal-00650235v1/document.  I have no opinion on
> whether it's better for your usecases, but I know it can be made as
> fast as your current algorithm :P)
>
>
> On Tue, Mar 24, 2015 at 10:48 AM, Eric Christopher <echristo at gmail.com>
> wrote:
> >
> > Drive by review: Needs some code comments explaining the functions
> (though I admit that most of them are pretty straightforward so just a
> simple "this is the point of this function would be good). Otherwise I
> don't see anything in particular. Nice big block comment at the top with
> the explanation. :)
> >
> > -eric
> >
> >
> > http://reviews.llvm.org/D8576
> >
> > EMAIL PREFERENCES
> >   http://reviews.llvm.org/settings/panel/emailpreferences/
> >
> >
> >
> > _______________________________________________
> > llvm-commits mailing list
> > llvm-commits at cs.uiuc.edu
> > http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20150324/66dc2a0d/attachment.html>