SCALA: A Performance System for Scalable Computing
Authors: X.-H. Sun, T. Fahringer, M. Pantano
Date: January, 2002
Venue: International Journal of High Performance Computing Applications (IJHPCA), Vol. 16, No. 4, Autumn 2002
Type: Journal
Abstract
Lack of effective performance-evaluation environments is a major barrier to the broader use of high perfor- mance computing. Conventional performance environ- ments are based on profiling and event instrumentation. It becomes problematic as parallel systems scale to hun- dreds of nodes and beyond. A framework of developing an integrated performance modeling and prediction sys- tem, SCALability Analyzer (SCALA), is presented in this study. In contrast to existing performance tools, the pro- gram performance model generated by SCALA is based on scalability analysis. SCALA assumes the availability of modern compiler technology, adopts statistical and symbolic methodologies, and has the support of browser interface. These technologies, together with a new ap- proach of scalability analysis, enable SCALA to provide the user with a more intuitive level of performance anal- ysis for scalable computing. A prototype SCALA system has been implemented. Initial experimental results show that SCALA is unique in its ability of revealing the scal- ing properties of a computing system.