Paper Info
Title
A Refinement Methodology for Developing Data-Parallel Applications
Abstract
Data-parallelism is a relatively well-understood form of parallel computation, yet developing simple applications can involve substantial efforts to express the problem in low-level data-parallel notations. We describe a process of software development for data-parallel applications starting from high-level specifications, generating repeated re- finements of designs to match different architectural models and performance constraints, supporting a development activity with cost-benefit analysis. Primary issues are algorithm choice, correctness and efficiency, followed by data decomposition, load balancing and message-passing coordination. Development of a data-parallel multitarget tracking appli- cation is used as a case study, showing the progression from high to low-level refinements. We conclude by describing tool support for the process.
Year
DOI
Venue
1996
10.1007/3-540-61626-8_18
Euro-Par, Vol. I
Keywords
Field
DocType
data-parallel applications,refinement methodology,message passing,cost benefit analysis,parallel computer,load balance,software development
Notation,Load balancing (computing),Computer science,Correctness,Parallel computing,Data decomposition,Software development,Distributed computing
Conference
ISBN
Citations 
PageRank 
3-540-61626-8
2
0.36
References 
Authors
9
6
Name
Order
Citations
PageRank
Lars S. Nyland1596.26
Jan Prins226723.14
Allen Goldberg355878.36
Peter H. Mills4162.78
John H. Reif54180810.75
Robert A. Wagner61783802.73