Charm++ parallel programming system

["Kale, Laxmikant V" <kale AT illinois.edu>]

We should find the problem with using CrayPat, but to answer the second part of  question: my guess is projections will be best (and adequate) for your purpose. 

-- 

--- 

Laxmikant (Sanjay) Kale         http://charm.cs.uiuc.edu

Professor, Computer Science     kale AT illinois.edu

201 N. Goodwin Avenue           Ph:  (217) 244-0094

Urbana, IL  61801-2302          

From: Yanhua Sun <sun51 AT illinois.edu>
Date: Monday, April 13, 2015 at 11:50 AM
To: "Tharrington, Arnold N." <arnoldt AT ornl.gov>
Cc: "charm AT cs.uiuc.edu" <charm AT cs.uiuc.edu>
Subject: Re: [charm] [ppl] Profiling namd with craypat

Hi Arnold,

What kind of performance data are you trying to get? 

Yanhua

On Sat, Apr 11, 2015 at 3:02 PM, Tharrington, Arnold N. <arnoldt AT ornl.gov> wrote:

Hi

 

I’m trying to profile namd with craypat for some performance work on Titans XK6. I am getting segfaults early during my performance runs. Is it possible to profile namd with craypat or am much better off using the projections software tool for performance work?

 

 

---------------------------------

# Arnold Tharrington, Ph.D.

# Oak Ridge National Laboratory

# National Center of Computational Sciences - Scientific Computing Group

#

# One Bethel Valley Road

# PO Box 2008 Mail Stop 6008

# Oak Ridge, TN 37831-6008

#

# Office: Building 5600, Room C109

# Phone: (865) 241-9393

# Fax: (865) 241-2850

# E-mail: arnoldt AT ornl.gov

#-------------------------------

 

_______________________________________________
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

--

Yours Sincerely,
Yanhua Sun 

University of Illinois at Urbana-Champaign,