Performance Database Technology for SciDAC Applications Shirley Moore, University of Tennessee

As part of the Performance Engineering Research Institute (PERI) effort, the Performance Database Working Group, which involves PERI researchers as well as outside researchers at the University of Oregon, Portland State University, and Texas A&M University, has developed technology for storing performance data collected by a number of performance measurement and analysis tools, including TAU, PerfTrack, Prophesy, and SvPablo. In addition to the performance data, metadata capturing the experimental setup and conditions (e.g., source code version; input data; platform, compiler, library, and operating system versions and configurations; runtime environment) are exported to a common metadata schema, along with some basic performance information. The exported information can be viewed from a common web interface, and a link or contact information is provided for accessing the original performance data in its home database. Analysis tools provided by the individual databases support tasks such as parallel profile browsing and analysis, cross-experiment analysis, and scalability studies. Performance data are currently being collected and analyzed for the GTC and MILC SciDAC applications. The tools are being installed on machines used by SciDAC researchers so that they can easily collect data and upload it to an associated performance database.