Improving the scalability of performance evaluation tools

Authors:
Sameer Suresh Shende;Allen D. Malony;Alan Morris
Affiliations:
Performance Research Laboratory, Department of Computer and Information Science, University of Oregon, Eugene, OR;Performance Research Laboratory, Department of Computer and Information Science, University of Oregon, Eugene, OR;Performance Research Laboratory, Department of Computer and Information Science, University of Oregon, Eugene, OR
Venue:
PARA'10 Proceedings of the 10th international conference on Applied Parallel and Scientific Computing - Volume 2
Year:
2010

Citing 7
Cited 0

A tool framework for static and dynamic analysis of object-oriented software with templates

Proceedings of the 2000 ACM/IEEE conference on Supercomputing
An API for Runtime Code Patching

International Journal of High Performance Computing Applications
The Tau Parallel Performance System

International Journal of High Performance Computing Applications
A Generic and Configurable Source-Code Instrumentation Component

ICCS 2009 Proceedings of the 9th International Conference on Computational Science
Scalable massively parallel I/O to task-local files

Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis
TAUmon: scalable online performance data analysis in TAU

Euro-Par 2010 Proceedings of the 2010 conference on Parallel processing
Simplifying Memory, I/O, and Communication Performance Assessment Using TAU

HPCMP-UGC '10 Proceedings of the 2010 DoD High Performance Computing Modernization Program Users Group Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

Performance evaluation tools play an important role in helping understand application performance, diagnose performance problems and guide tuning decisions on modern HPC systems. Tools to observe parallel performance must evolve to keep pace with the ever-increasing complexity of these systems. In this paper, we describe our experience in building novel tools and techniques in the TAU Performance System® to observe application performance effectively and efficiently at scale. It describes the extensions to TAU to contend with large data volumes associated with increasing core counts. These changes include new instrumentation choices, efficient handling of disk I/O operations in the measurement layer, and strategies for visualization of performance data at scale in TAU's analysis layer, among others. We also describe some techniques that allow us to fully characterize the performance of applications running on hundreds of thousands of cores.