Charm++ parallel programming system

[Pritish Jetley <pjetley2 AT uiuc.edu>]

Sorry for the confusion. If you look at the script, it has all the relevant commands to obtain the code:

#!/bin/bash

[line 2] git clone git://charm.cs.uiuc.edu/benchmarks/barnes

[line 8] git checkout origin/jetley/oct

[line 10] git clone git://charm.cs.uiuc.edu/cosmo/utility

You will have to make the MeshStreamer library. The default version of code should work just fine. Let me know if you need help understanding the code. 

Pritish

On Mon, Jan 9, 2012 at 8:55 PM, Kale, Laxmikant V <kale AT illinois.edu> wrote:

Pritish, I think they are interested in the cource code, rather than the executable. I assume it is easy to find (but the instructions about the right repositories, and branch might be confusing in that respect. I assume the BH code is invariant, but just that it needs the new MeshStreamer library, which requires a particular branch of charm++..  right?

--
Laxmikant Kale                  http://charm.cs.uiuc.edu
Professor, Computer Science     kale AT cs.uiuc.edu
201 N. Goodwin Avenue           Ph:  (217) 244-0094
Urbana, IL  61801-2302          FAX: (217) 265-6582

---

From: pritish.jetley AT gmail.com [pritish.jetley AT gmail.com] on behalf of Pritish Jetley [pjetley2 AT uiuc.edu]
Sent: Monday, January 09, 2012 2:08 PM
To: Padma Raghavan
Cc: Shad Kirmani; charm AT cs.uiuc.edu; Kale, Laxmikant V
Subject: Re: [charm] leanMD like code for N-body calc

Yes, there is such a piece of code, called CharmBH. Please follow these steps to get an executable:

1. Obtain a copy of Charm++

2. build the 'MeshStreamer' library in Charm++: go to the tmp/libs/ck-libs/MeshStreamer directory and do a 'make'

3. Run the attached script to get an executable of barnes. The only argument to the script should be the path to your Charm++ installation. The script will clone the relevant repositories and switch to the correct branch before starting the compilation.

./install.sh <path to charm++ installation> 

Please let me know if you run into errors.

Pritish

On Mon, Jan 9, 2012 at 12:08 PM, Padma Raghavan <raghavan AT cse.psu.edu> wrote:

We are specifically looking for a barnes-hut type tree-code. Thanks, Padma

On 1/9/12 1:07 PM, Shad Kirmani wrote:

Hello,

We are looking for a lightweight code that does the N-Body calculations. ChaNGa is there but it is a very heavy code. Is there something available, like leanMD, for N-body calculations?

Thanks,

Shad

--

Padma Raghavan                         

Director, Institute for CyberScience 

Professor, Computer Science and Engineering       

The Pennsylvania State University      

Phone: 814-865-9233                    

E-mail: raghavan AT psu.edu

Html: http://www.ics.psu.edu

      http://www.cse.psu.edu/~raghavan

Staff: Louise Troxell

E-mail: slt29 AT psu.edu

Phone:814-867-1467

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

--
Pritish Jetley
Doctoral Candidate, Computer Science
University of Illinois at Urbana-Champaign

--
Pritish Jetley
Doctoral Candidate, Computer Science
University of Illinois at Urbana-Champaign