[petsc-dev] [Ideas-team] Seeking OLCF users complaining about poor build times

[Mark Adams]

Sorry, I did not mean any disrespect to ORNL.  I (my colleague) was
painting with a broad brush and our experience is not with scientists.  And
I am sure that our experience with ORNL management does not reflect the
attitude of all of ORNL management.  I'm glad to hear that there are
important project to ORNL that are behind PETSc.

Our project has been told _explicitly_ to seek alternatives to PETSc
because they say PETSC will not run well on SUMMIT (something about Barry
not liking threads).  We have had to put risk mitigation material in
proposals to the effect "we will use hypre if PETSc does not work".
Nothing against hypre but this is silly.

Mark

On Fri, Feb 27, 2015 at 2:57 PM, Bartlett, Roscoe A. <bartlettra at ornl.gov>
wrote:

>  If ORNL hates PETSc, then they forgot to tell the CASL codes J
>
>
>
> -Ross
>
>
>
>
>
> *From:* ideas-team-bounces at lists.mcs.anl.gov [mailto:
> ideas-team-bounces at lists.mcs.anl.gov] *On Behalf Of *Mark Adams
> *Sent:* Friday, February 27, 2015 2:06 PM
> *To:* Todd Gamblin
> *Cc:* petsc-dev; ideas-team at lists.mcs.anl.gov
> *Subject:* Re: [Ideas-team] [petsc-dev] Seeking OLCF users complaining
> about poor build times
>
>
>
> FWIW, I have some log files from Edison and Titan in the last week using
> thread safe configuration, SuperLU, hypre, & Metis. Its not clear to me if
> the external packages were built before.  That is, I am not sure these were
> clean builds.  Like Nathan Titan is good:
>
>
>
> 11m  config
>
> 3min  make
>
>
>
> and Edison is not good:
>
>
>
> 1hr 34min config
>
> 17 min make
>
>
>
> And unless you are doing git bisect who cares if it take more than a
> minute you have a context switch anyway.  And I have probably configure
> PETSc at least 20 times this past week on Edison and Hopper.
>
>
>
> BTW, One of my PIs told me recently "ORNL hates PETSc", and I said PETSc
> is like Broccoli, you like it or you don't, and what if next week ORNL
> hates MPI?  (my PI seemed to appreciate that) ... or FORTRAN (I should have
> said that too).
>
>
>
> Mark
>
>
>
>
>
>
>
> On Fri, Feb 27, 2015 at 1:10 PM, Todd Gamblin <tgamblin at llnl.gov> wrote:
>
> CMake test stuff too, so it has the same problem.  At the very least it
> tests the compiler id and ends up creating a bunch of directories and
> files in the CMakeFiles directory.
>
> So you're still in the same boat with CMake... But you don't have to
> maintain your own elaborate build system on the side.
>
>
> On 2/27/15, 10:06 AM, "Barry Smith" <bsmith at mcs.anl.gov> wrote:
>
> >
> >> On Feb 27, 2015, at 12:00 PM, Jed Brown <jed at jedbrown.org> wrote:
> >>
> >> Barry Smith <bsmith at mcs.anl.gov> writes:
> >>>   Actually the parallel compiles of the 1000+ files on the "regular"
> >>>   filesystems at ANL and LBL is taking less than 2 minutes so I can't
> >>>   blame the filesystem bandwidth.
> >>
> >> I think bandwidth is adequate, but latency (especially for metadata) is
> >> rather high.  Normal make uses parallelism to mitigate, but configure is
> >> sequential, so gets hit harder.
> >
> >    Yup, that was my conclusion. So the solution is 1) apply pressure to
> >improve latency on these systems a bit and 2) incorporate more
> >parallelism in ./configure without making it even more complicated.  Or
> >switch to cmake where you don't test anything but just read the machines
> >capabilities from an outdated database :-).
> >
> >  Barry
> >
> >
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20150227/2ad27feb/attachment.html>