1. Empirical Optimization for a Sparse Linear Solver: A Case Study
- Author
-
Robert F. Lucas, Yoon-Ju Lee, Pedro C. Diniz, and Mary Hall
- Subjects
Computer science ,business.industry ,Performance tuning ,Machine learning ,computer.software_genre ,Theoretical Computer Science ,Software ,Computer engineering ,Theory of computation ,Benchmark (computing) ,Code (cryptography) ,Linear solver ,Artificial intelligence ,Sensitivity (control systems) ,business ,computer ,Information Systems - Abstract
This paper describes initial experiences with semi-automated performance tuning of a sparse linear solver in LS-DYNA, a large, widely used engineering application. Through a collection of tools supporting empirical optimization, we alleviate the burden of performance tuning for mapping today's sophisticated engineering software to increasingly complex hardware platforms. We describe a tool that automatically isolates code segments to create benchmark subsets for the purposes of performance tuning. We present a collection of automatically generated empirical results that demonstrate the sensitivity of the application's performance to optimization parameters. Through this case study, we demonstrate the importance of developing automatic performance tuning support for performance-sensitive applications.
- Published
- 2005
- Full Text
- View/download PDF