University of North Texas Digital Library (University of North Texas) · 2003 · 28 citations · 0 references
Open access
ComputingComputer ScienceHigh-performance ComputingCluster ComputingParallel ComputingScientific ComputingParallel ArchitecturesParallel Computing SystemsParallel Performance AnalysisPerformance Bottleneck AnalysisPerformance ModelingPerformance OptimizationAnalytical ModelsCluster Performance ModelingHigh-performance Computing PerformanceHigh-performance Computing SystemsParallel Computing PerformancePerformance BenchmarkingPerformance ScalabilitySupercomputer Architecture
In this paper we describe how we improved the effective performance of ASCI Q, the world's second-fastest supercomputer, to meet our expectations. Using an arsenal of performance-analysis techniques including analytical models, custom microbenchmarks, full applications, and simulators, we succeeded in observing a serious-but previously undetectable-performance problem. We identified the source of the problem, eliminated the problem, and 'closed the loop' by demonstrating improved application performance. We present our methodology and provide insight into performance analysis that is immediately applicable to other large-scale cluster-based supercomputers.