Skip to Content.
Sympa Menu

charm - Re: [charm] [ppl] current results on LLNL cluster

charm AT lists.cs.illinois.edu

Subject: Charm++ parallel programming system

List archive

Re: [charm] [ppl] current results on LLNL cluster


Chronological Thread 
  • From: "Bennion, Brian" <Bennion1 AT llnl.gov>
  • To: Abhinav Bhatele <bhatele AT illinoisalumni.org>
  • Cc: "charm AT cs.uiuc.edu" <charm AT cs.uiuc.edu>
  • Subject: Re: [charm] [ppl] current results on LLNL cluster
  • Date: Thu, 8 Sep 2011 15:30:07 -0700
  • Accept-language: en-US
  • Acceptlanguage: en-US
  • List-archive: <http://lists.cs.uiuc.edu/pipermail/charm>
  • List-id: CHARM parallel programming system <charm.cs.uiuc.edu>

I neglect to state that all were built with --with-production except the
mpi-smp which would only compile with debug symbols included.


-----Original Message-----
From:
bhatele AT gmail.com

[mailto:bhatele AT gmail.com]
On Behalf Of Abhinav Bhatele
Sent: Thursday, September 08, 2011 3:25 PM
To: Bennion, Brian
Subject: Re: [ppl] [charm] current results on LLNL cluster

Brian,

Just a minor note. When you are decided on which version of charm to use for
your production runs, don't forget to build charm with --with-production.
That will kick off all the optimization flags for a given platform.

- Abhinav



On Thu, Sep 8, 2011 at 10:21 AM, Bennion, Brian
<Bennion1 AT llnl.gov>
wrote:


Hello,

Compilation of all the suggested versions of charm++ have been
completed.
They were:
mpi-linux-x86_64
mpi-linux-x86_64 smp
net-linux-x86_64 ivberbs
net-linux-x86_64 ibverbs smp

It appears that the first charmm build is the best for namd2.8. I
saw a 25% speedup on my regular jobs using the same processor counts. No
extra tricks were employed in compiling charm++ or namd2.8.

The ibverbs version did compile for charm++ and namd2.8 and was even
able to start. however, sockets closed prematurely on some node and the
whole things burns to the ground.

Two quick thoughts here. First, looking at the charm.XXXXX files
that are created, they look for some /tmp/charm.XXXX directories that are not
going to be available. The tmp filesystem goes by username it
/tmp/bennion1/XXXXX
Second, I will check with our admins to see if using ib layer is even
permissible.

Brian

_______________________________________________
charm mailing list

charm AT cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/charm
_______________________________________________
ppl mailing list

ppl AT cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/ppl





--
Abhinav Bhatele
Postdoctoral Research Staff Member
Center for Applied Scientific Computing
Lawrence Livermore National Laboratory






Archive powered by MHonArc 2.6.16.

Top of Page