Title: Performance Technology for Productive, High Performance Computing
Author: Sameer Shende, University of Oregon.
Dr. Shende's current research interests include parallel performance evaluation tools, instrumentation, measurement, and analysis techniques, and compiler optimizations. He is the lead developer of the TAU performance system (TM) and the Program Database Toolkit software tools. He is the President of ParaTools, Inc. and a research faculty in the Performance Research Laboratory at the University of Oregon.
High-end applications and systems are evolving towards more sophisticated modes of operation, higher levels of abstraction, and larger scales of execution. These trends challenge the state of technology for performance evaluation and optimization. While scalable toolsets for parallel and distributed system performance analysis exist, offering a range of capabilities and sophistication in performance observation and analysis, the tools are not as widely used by HPC application groups nor as broadly integrated in the application development, engineering, and tuning processes as they could and should be. This talk will discuss our current and future work on improving the utility of parallel performance tools and evolving their capabilities to meet high-end application requirements. We will present the use of TAU to observe the performance of applications running on multi-core cpus using MPI and hybrid (MPI+OpenMP) execution models. New developments in the TAU parallel performance system will be presented, primarily in relation to how they are better directed to application-specific concerns. This talk describes the integration of performance system technology for robust instrumentation, measurement, and analysis with new tools for performance management and performance data mining in support of performance knowledge discovery in the TAU performance system (TM).