[petsc-dev] Reference for application of implicit problem with 500 billion unknowns

[Matthew Knepley]

On Mon, Jan 9, 2017 at 12:05 PM, Jed Brown <jed at jedbrown.org> wrote:

> Gautam Bisht <gbisht at lbl.gov> writes:
>
> > All,
> >
> > Is there a reference that PETSc Tutorial slides
> > <http://www.mcs.anl.gov/petsc/documentation/tutorials/
> TutorialCEMRACS2016.pdf>
> > (slide-20) reports
> > on using "PFLOTRAN with 500 billion unknowns"?
>
> I think that was UNIC, circa 2009 on BG/P.  It is higher now (recent
> Gordon Bells), though I find this metric next to meaningless.
>

If by meaningless you mean it will not help YOU judge a piece of software,
fine. However,
if you mean its meaningless to put in a proposal, I think you are wrong,
since many people
might be convinced by this.

   Matt

-- 
What most experimenters take for granted before they begin their
experiments is infinitely more interesting than any results to which their
experiments lead.
-- Norbert Wiener
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20170109/a10155a5/attachment.html>