Processor allocation vs. job scheduling on hypercube computers
- 10 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
The roles of processor allocation and job scheduling in achieving good performance on hypercube computers are compared. It is shown that the choice of job scheduling discipline has a dramatic effect on performance. A family of scheduling disciplines, called Scan, with particular performance advantages is proposed. Furthermore, it is shown that if Scan scheduling is used, the choice of processor allocation strategy has negligible effect on performance. As a result, complex allocation strategies can be replaced by a simple O(n) strategy.Keywords
This publication has 11 references indexed in Scilit:
- Scheduling independent jobs on partitionable hypercubesJournal of Parallel and Distributed Computing, 1991
- A top-down processor allocation scheme for hypercube computersIEEE Transactions on Parallel and Distributed Systems, 1991
- The performance of multiprogrammed multiprocessor scheduling algorithmsPublished by Association for Computing Machinery (ACM) ,1990
- Preemptive scheduling of independent jobs on a hypercubeInformation Processing Letters, 1988
- Topological properties of hypercubesIEEE Transactions on Computers, 1988
- Reevaluating Amdahl's lawCommunications of the ACM, 1988
- Scheduling in multiprogrammed parallel systemsPublished by Association for Computing Machinery (ACM) ,1988
- On allocating subcubes in a hypercube multiprocessorPublished by Association for Computing Machinery (ACM) ,1988
- Processor Allocation in an N-Cube Multiprocessor Using Gray CodesIEEE Transactions on Computers, 1987
- A comparative analysis of disk scheduling policiesCommunications of the ACM, 1972