An efficient approach for self-scheduling parallel loops on multiprogrammed parallel computers

Authors:
Arun Kejariwal;Alexandru Nicolau;Constantine D. Polychronopoulos
Affiliations:
Center for Embedded Computer Systems, University of California at Irvine, Irvine, CA;Center for Embedded Computer Systems, University of California at Irvine, Irvine, CA;Center for Supercomputing Research and Development, University of Illinois at Urbana-Champaign, Urbana, IL
Venue:
LCPC'05 Proceedings of the 18th international conference on Languages and Compilers for Parallel Computing
Year:
2005

Citing 4
Cited 2

Allocating Independent Subtasks on Parallel Processors

IEEE Transactions on Software Engineering
Guided self-scheduling: A practical scheduling scheme for parallel supercomputers

IEEE Transactions on Computers
Scheduling in multiprogrammed parallel systems

SIGMETRICS '88 Proceedings of the 1988 ACM SIGMETRICS conference on Measurement and modeling of computer systems
Using Processor Affinity in Loop Scheduling on Shared-Memory Multiprocessors

IEEE Transactions on Parallel and Distributed Systems

Derivation of self-scheduling algorithms for heterogeneous distributed computer systems: Application to internet-based grids of computers

Future Generation Computer Systems
Probablistic self-scheduling

Euro-Par'06 Proceedings of the 12th international conference on Parallel Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Clusters and grids have increasingly become standard platforms for high performance computing as they provide extremely high execution rates with great cost effectiveness. Such systems are designed to support concurrent execution of multiple jobs. It calls for multiprogrammed scheduling of the different jobs for effective system utilization and for keeping average response times low. Although a significant amount of work has been done in scheduling parallel jobs on multiprocessor systems, the problem of scheduling parallel tasks of an individual job on a multiprogrammed parallel system has not been given enough attention so far. In this paper, we present a dynamic scheduling technique for scheduling iterations of a DOALL loop (of a single application) to achieve load balance between a given set of processors. Experimental results show the effectiveness of our approach.