TAU Performance System Training 2025

TAU Performance System: A Versatile Performance Evaluation Tool at OLCF

August 11, 2pm – 4pm EDT

The TAU Performance System® [http://tau.uoregon.edu] is a versatile profiling and tracing toolkit that supports AMD CPUs and GPUs with multiple languages, compilers, and runtime systems. The tutorial will cover generating performance profiles and traces with memory utilization and headroom, I/O, and interfaces to ROCm including ROCprofiler-SDK [https://github.com/ROCm/rocprofiler-sdk] with support for event-based sampling on CPU and GPUs and collecting hardware performance data.  It will cover instrumentation of OpenMP programs using OpenMP Tools Interface (OMPT) including support for target offload and measurement of a program’s memory footprint. We will demonstrate scalable tracing using OTF2 and visualization using the Vampir trace analysis tool. Performance data analysis using ParaProf and PerfExplorer will be demonstrated using the performance data management framework (TAUdb) that includes TAU’s performance database. TAU supports AMD’s HIPCC compiler with compiler-based instrumentation using TAU’s LLVM plugin for selective instrumentation. It will describe using TAU in the ECP Extreme-Scale Scientific Software Stack (E4S) [https://e4s.io] using container technology. Users and developers are welcome to contact the instructor ahead of time to begin collecting data using TAU.

Presenter: Dr. Sameer Shende, University of Oregon

Bio: Sameer Shende serves as a Research Professor and the Director of the Performance Research Laboratory at the University of Oregon and the President and Director of ParaTools, Inc. (USA) and ParaTools, SAS (France). He serves as the Technical Lead of the Extreme-scale Scientific Software Stack (E4S), ParaTools Pro for E4S(TM), TAU Performance System, and Program Database Toolkit (PDT) projects. His research interests include scientific software stacks, performance instrumentation, compiler optimizations, measurement, and analysis tools for HPC.