Introductory: 65% Intermediate: 25% Advanced: 10%

SC Conference - Activity Details

S12: Analyzing the Performance of Parallel Applications with Open|SpeedShop

Martin Schulz  (Lawrence Livermore National Laboratory)
Jim Galarowicz  (Krell Institute)
David Montoya  (Los Alamos National Laboratory)
Don Maghrak  (Krell Institute)
Scott Cranford  (Sandia National Laboratories)
Tutorials Session
Sunday,  01:30PM - 05:00PM
Room TBD
Performance Analysis is an essential step in the development cycle of HPC codes. In this tutorial we will introduce how programmers can approach this important topic and how they can analyze the performance of their codes using the comprehensive open source toolset Open|SpeedShop, which is being developed and made available through a close collaboration between the Krell Institute and ASC/NNSA. In this tutorial we not only will introduce the attendees to O|SS and its wide functionality, but we will directly focus on how they can use Open|SpeedShop's extensive set of performance experiments to step by step understand the performance characteristics of their codes. We will focus both on node local (by studying global profiles, stack trace sampling, hardware counters, as well as I/O properties) and parallel performance (using a combination of tracing experiments and advanced analysis techniques). The latter will cover MPI applications as well as threaded codes.
   IEEE Computer Society  /  ACM     2 0   Y E A R S   -   U N L E A S H I N G   T H E   P O W E R   O F   H P C