Courseware - Computational Science (CN)

Parallel Computation

How to Analyze the Performance of Parallel Codes 101: A Case Study with Open|SpeedShop

Material Type:

Lecture / Presentation

ISN Logo

Technical Format:

PDF document


Go to materials

Date Added:


Date Modified:



Jim Galarowicz, Krell Institute
Don Maghrak, Krell Institute
David Montoya , Lawrence Livermore National Laboratory
Mahesh Rajan , Sandia National Laboratories
Martin Schulz, Lawrence Livermore National Laboratory

Performance analysis is an essential step in the development of HPC codes. It will even gain in importance with the rising complexity of machines and applications that we are seeing today. Many tools exist to help with this analysis, but the user is too often left alone with interpreting the results. In this tutorial we will provide a practical road map for the performance analysis of HPC codes and will provide users step by step advice on how to approach the optimization of their codes as well as on how to investigate observed performance bottlenecks in detail. We will cover both on-node performance and communication optimization. Throughout this tutorial will show live demos using Open|SpeedShop, a comprehensive and easy to use performance analysis tool set, to demonstrate the individual analysis steps. All techniques will, however, apply broadly to any tool and we will point out alternative tools where useful.

Recommended Audience:

Advanced programmers, Beginning programmers, Graduate students, Secondary School students, Undergraduate students




Performance, analysis, HPC, Jim Galarowicz, Don Maghrak, Mahesh Rajan, David Montoya, Martin Schulz
For more complete information about compiler optimizations, see our Optimization Notice.