NERSCPowering Scientific Discovery Since 1974

S10: Scaling to Petascale and Beyond: Performance Analysis and Optimization of Applications

Sunday, Nov. 13
8:30-5:00

Glenn Brook, University of Tennessee, Knoxville
Donald Frederick, Lawrence Livermore National Laboratory
Richard Gerber, NERSC / Lawrence Berkeley National Laboratory
Jeff Larkin, Cray, Inc.

 

http://sc11.supercomputing.org/schedule/event_detail.php?evid=tut146

ABSTRACT:

Current supercomputer systems have architectures with many thousands of cores. Application developers are faced with the task of designing for parallel scalability at ever higher levels. The effective use of such platforms, requires application developers to focus on achieving parallel scalability through application design and optimization driven by performance analysis. This tutorial provides developers with the background in system features, program design and performance analysis to aid in producing efficient programs on modern supercomputers.

 

Last login: Fri Nov 11 07:29:11 on console
Welcome to Darwin!
**********************************************************************
 *                                                                    *
 *                            NOTICE TO USERS                         *
 *                            ---------------                         *
 *                                                                    *
 *  Lawrence Berkeley National Laboratory operates this computer      *
 *  system under contract to the U.S. Department of Energy. This      *
 *  system is the property of the United States Government and is     *
 *  for authorized use only. Users (authorized or unauthorized) have  *
 *  no explicit or implicit expectation of privacy.                   *
 *                                                                    *
 *  Any or all uses of this system and all files on this system may   *
 *  be intercepted, monitored, recorded, copied, audited, inspected,  *
 *  and disclosed to site, Department of Energy, and law enforcement  *
 *  personnel, as well as authorized officials of other agencies,     *
 *  both domestic and foreign. By using this system, the user consents*
 *  to such interception, monitoring, recording, copying, auditing,   *
 *  inspection and disclosure at the discretion of authorized site    *
 *  or Department of Energy personnel.                                *
 *                                                                    *
 *  Unauthorized or improper use of this system may result in         *
 *  administrative disciplinary action and civil and criminal         *
 *  penalties. By continuing to use this system, you indicate your    *
 *  awareness of and consent to these terms and conditions of use.    *
 *  LOG OFF IMMEDIATELY if you do not agree to the conditions stated  *
 *  in this warning.                                                  *                 
 **********************************************************************
Richard-DOE6897715:~% vi blah
I/O on Lustre Filesystems - 20 minutes - Richard Gerber
2.2.2 Multi-core Performance Analysis
HPC Computation - 40 minutes - Jeff Larkin
Introduction and General Methodology - 30 minutes Don Frederick and Glenn
Brook 
Profiling with Open SpeedShop - 45 minutes Don Frederick
2.2.3 Extreme Scaling on Petascale-class Systems
Cray XT Architecture, System Software, and Scientific Libraries - 15 minutes
- Jeff Larkin
Cray XT Porting, Scaling, and Optimization - 1 hour - Jeff Larkin
IBM Blue Gene P Architecture, System Software, and Scientific Libraries – 15
minutes - Don Frederick
IBM Blue Gene P Porting, Scaling and Optimization Case Studies – 1 hour -
Don Frederick
-- INSERT --

 

AGENDA:

Design Considerations

 

8:30 - Introduction to Petascale Systems –  Richard Gerber

8:50 - HPC Communication  - Glenn Brook

9:45 - HPC IO & Lustre File Systems  - Richard Gerber

10:00 - Break 

10:20 - HPC IO & Lustre File Systems Continued - Richard Gerber

11:15 - HPC Computation - 40 minutes - Jeff Larkin

Lunch (12:00-1:15)

 

Multi-Core Performance Analysis

 

1:15 - Introduction and General Methodology -   Don Frederick

1:35 - Profiling with Open SpeedShop - Don Frederick

Extreme Scaling on Petascale-class Systems

 

2:20 - Cray XT Architecture, System Software, and Scientific Libraries -  Jeff Larkin

2:35 - Cray XT Porting, Scaling, and Optimization -  Jeff Larkin

3:00 - Break

3:15 - Cray XT Porting, Scaling, and Optimization Continued

4:00 - IBM Blue Gene P Architecture, System Software, and Scientific Libraries  - Don Frederick

4:15 - IBM Blue Gene P Porting, Scaling and Optimization Case Studies – Don Frederick

5:00 - Adjourn

 

Downloads