Runtime incremental parallel scheduling (RIPS) on distributed memory computers

被引：19

作者：

Shu, W

Wu, MY

机构：

[1] Department of Computer Science, State University of New York at Buffalo, Buffalo

来源：

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS | 1996年 / 7卷 / 06期

关键词：

runtime load balancing; incremental scheduling; parallel scheduling; irregular and dynamic applications; distributed memory computers;

D O I：

10.1109/71.506702

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Runtime Incremental Parallel Scheduling (RIPS) is an alternative strategy to the commonly used dynamic scheduling. in this scheduling strategy, the system scheduling activity alternates with the underlying computation work. RIPS utilizes the advanced parallel scheduling technique to produce a low-overhead, high-quality load balancing as well as adapting to irregular applications. This paper presents methods for scheduling a single job on a dedicated parallel machine.

引用

页码：637 / 649

页数：13

共 40 条

[1]

Ahmad I., 1995, Proceedings 9th International Parallel Processing Symposium (Cat. No.95TH8052), P289, DOI 10.1109/IPPS.1995.395947

[2]

AHMAD I, 1995, P 2 AUTR C PAR REAL

[3]

ATHAS WC, 1987, THESIS CALTECH

[4]

BADEN SB, 1986, 22584 L BERK LAB

[5]

BERGER M, 1987, IEEE T COMPUT, V26, P570

[6]

CASAVANT TL, 1987, P 7 INT C DISTR COMP, P185

[7]

CHAKRABARTI S, 1994, PROCEEDINGS OF THE SCALABLE HIGH-PERFORMANCE COMPUTING CONFERENCE, P666, DOI 10.1109/SHPCC.1994.296705

[8]

CHUNG Y, 1992, SUPERCOMPUTER 92

[9] DYNAMIC LOAD BALANCING FOR DISTRIBUTED MEMORY MULTIPROCESSORS [J].

CYBENKO, G .

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 1989, 7 (02) :279-301

[10]

Dragon K. M., 1989, Proceedings of the Fourth Conference on Hypercubes, Concurrent Computers and Applications, P583

← 1 2 3 4 →