Paper Info
Title
Toward Incremental Parallelization Using Navigational Programming
Abstract
The Navigational Programming (NavP) methodology is based on the principle of self-migrating computations. It is a truly incremental methodology for developing parallel programs: each step represents a functioning program, and each intermediate program is an improvement over its predecessor. The transformations are mechanical and straightforward to apply. We illustrate our methodology in the context of matrix multiplication, showing how the transformations lead from a sequential program to a fully parallel program. The NavP methodology is conducive to new ways of thinking that lead to ease of programming and high performance. Even though our parallel algorithm was derived using a sequence of mechanical transformations, it displays certain performance advantages over the classical handcrafted Gentleman's Algorithm.
Year
DOI
Venue
2006
10.1093/ietisy/e89-d.2.390
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
Keywords
Field
DocType
programming methodologies, incremental parallelization, navigational programming (NavP), program transformation, matrix multiplication, gentleman's algorithm, cannon's algorithm
Program transformation,Programming language,Cannon's algorithm,Parallel algorithm,Computer science,Matrix multiplication,Computation
Journal
Volume
Issue
ISSN
E89D
2
1745-1361
Citations 
PageRank 
References 
0
0.34
0
Authors
7
Name
Order
Citations
PageRank
Lei Pan1299.49
Wenhui Zhang286.05
Arthur Asuncion378552.90
Ming Kin Lai4203.71
Michael B. Dillencourt549857.58
Lubomir F. Bic614719.23
Laurence T. Yang76870682.61