Charm++ parallel programming system

[Chee Wai Lee <cheewai1972 AT gmail.com>]

Hi Haowei,

Yes, and it would be very helpful to get feedback on the use of this feature outside of NAMD. The instructions (for NAMD) can be found here: http://www.nic.uoregon.edu/tau-wiki/Guide:NAMDTAU. These instructions will assume you have a working version of TAU built (craycnl, I assume) on the Cray.

I have previously checked-in the code for TAU support into the Charm++ repository, so it should have been released along with Charm 6.2. I will verify that the instructions still do work with the current repository or release versions of Charm++ and get back to you. Please let us know if you have any questions or difficulties. Feel free to ask Scott or myself about TAU and Charm++. I am still familiar with the inner workings of Projections as well, so if you have questions there, I can try my best to answer them.

Best Regards,

Chee Wai Lee

Computer Scientist, Performance Research Lab,

NeuroInformatics Center,

University of Oregon.

On Jun 20, 2010, at 6:52 AM, Haowei Huang wrote:

 Hi,
 
      You just mentioned a trace-based tool called Projections in the charm++ manual. How can we use TAU to profile Charm++ applications on Cray? I used pgi MPI as MPI configuration to build TAU on Cray. Should we add configuration related to charm++ library when we build TAU on Cray machine? Thank you so much.      

--
Haowei Huang
Ph.D. student
Technische Universitaet Muenchen
Institut fuer Informatik, I10
Boltzmannstr. 3
D-85748 Garching
Room 01.06.061
Phone: +49 (89) 289 18477
mailto: huangh AT in.tum.de
_______________________________________________
charm mailing list
charm AT cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/charm