Abstract
Processor self-scheduling is an efficient dynamic scheduling for multiprocessors. This paper discusses the impact of the self-scheduling order on the performance of multiply-nested parallel loops. It is shown that, due to data synchronization for cross-iteration data dependences, the completion time of a multiply-nested loop is reduced when the nesting parallel loops with smaller delays are moved to the inside. The best performance is achieved when a shortest-delay scheduling order is used. The performance of the shortest-delay self-scheduling is compared to other self-scheduling orders and to compile-time static scheduling order proposed elsewhere. Program transformation needed to implement shortest-delay self-scheduling is also included.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings of the 2nd International Conference on Supercomputing, ICS 1988 |
| Editors | J. Lenfant |
| Publisher | Association for Computing Machinery |
| Pages | 593-603 |
| Number of pages | 11 |
| ISBN (Electronic) | 0897912721 |
| DOIs | |
| State | Published - Jun 1 1988 |
| Event | 2nd International Conference on Supercomputing, ICS 1988 - St. Malo, France Duration: Jul 4 1988 → Jul 8 1988 |
Publication series
| Name | Proceedings of the International Conference on Supercomputing |
|---|---|
| Volume | Part F130184 |
Other
| Other | 2nd International Conference on Supercomputing, ICS 1988 |
|---|---|
| Country/Territory | France |
| City | St. Malo |
| Period | 7/4/88 → 7/8/88 |
Bibliographical note
Funding Information:This work was supported in part by the National Foundation under Grant No. US NSF h4IP-8410110, Department of Energy under Grant US DOE DE FG02-85ER25001, by the donations and DEC Corporations.
Publisher Copyright:
© 1988 ACM.