Practical Multiprocessor Scheduling Algorithms for Efficient Parallel Processing

MIMD (multiple instruction stream, multiple data stream) parallel processing systems or multiprocessor systems have been employed in a wide variety of computer applications. In order to take advantage of the prospects of parallel processing, an efficient scheduling algorithm must be developed. Such...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on computers Vol. C-33; no. 11; pp. 1023 - 1029
Main Authors: KASAHARA, H, NARITA, S
Format: Journal Article
Language:English
Published: New York, NY IEEE 01.11.1984
Institute of Electrical and Electronics Engineers
Subjects:
Accuracy
Applied sciences
Approximation
Approximation algorithms
branch-and-bound method
Computer science; control theory; systems
Computer systems and distributed systems. User interface
Exact sciences and technology
heuristic algorithm
Heuristic algorithms
Lower bound
MIMD system
multiprocessor scheduling algorithm
optimization
parallel processing
Processor scheduling
Program processors
Schedules
Scheduling algorithms
Software
Sorting
strong NP-hard
task graph
This paper describes practical optimization/ approximation algorithms for scheduling a set of partially ordered computational tasks onto a multiprocessor system so that the schedule length will be minimized. Since this problem belongs to the class of "strong" NP-hard problems
Time complexity
we must foreclose the possibility of constructing not only pseudopolynomial time optimization algorithms but also fully polynomial time approximation schemes unless P = NP
Multiprocessor
Approximation
Branch and bound method
Integrated planning
Heuristic method
Task scheduling
Parallel processing
Algorithm
Optimization
ISSN:0018-9340, 1557-9956
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:MIMD (multiple instruction stream, multiple data stream) parallel processing systems or multiprocessor systems have been employed in a wide variety of computer applications. In order to take advantage of the prospects of parallel processing, an efficient scheduling algorithm must be developed. Such an algorithm must allow the allocation of a set of tasks to the member processors and the determination of the order or sequence of task execution. The present investigation is concerned with the proposal of suitable algorithms, taking into account the Critical Path (CP) /Most Immediate Successors First (MISF) method. This method represents an improved version of the CP-method or HLFET (highest levels first with estimates times) method. Attention is also given to a method which facilitates finding optimum solutions to a large class of problems.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0018-9340
1557-9956
DOI:10.1109/TC.1984.1676376