Abstract | ||
---|---|---|
The complexity of parallel I/O systems imposes significant challenge in managing and utilizing the available system resources to meet application performance, portability and usability goals. We believe that a parallel I/O system that automatically selects efficient I/O plans for user applications is a solution to this problem. In this paper, we present such an automatic performance optimization approach for scientific applications performing collective I/O requests on multidimensional arrays. The approach is based on a high level description of the target workload and execution environment characteristics, and applies genetic algorithms to select high quality I/O plans. We have validated this approach in the Panda parallel I/O library. Our performance evaluations on the IBM SP show that this approach can select high quality I/O plans under a variety of system conditions with a low overhead, and the genetic algorithm-selected I/O plans are in general better than the default plans used in Panda. |
Year | DOI | Venue |
---|---|---|
1998 | 10.1109/HPDC.1998.709968 | HPDC |
Keywords | Field | DocType |
genetic algorithms,available system resource,o performance optimization,o library,high level description,o plan,application performance,high quality,automatic performance optimization approach,o system,o request,panda parallel,optimization,automatic parallelization,genetic algorithm,computer science,usability goals,resource management,application software,usability,engines,parallel programming,parallel algorithms,resource allocation | Computer science,Parallel algorithm,Usability goals,Resource allocation,Software portability,Application software,Parallel I/O,Genetic algorithm,Distributed computing,Automatic programming | Conference |
ISBN | Citations | PageRank |
0-8186-8579-4 | 7 | 0.52 |
References | Authors | |
9 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Y. Chen | 1 | 88 | 12.81 |
Marianne Winslett | 2 | 3519 | 744.78 |
Y. Cho | 3 | 83 | 8.35 |
S. Kuo | 4 | 50 | 4.66 |