Scalable Heuristic Algorithms for the Parallel Execution of Data Flow Acyclic Digraphs

Data flow acyclic directed graphs (digraphs) can be applied to accurately describe the data dependency for a wide range of grid-based scientific computing applications ranging from numerical algebra to realistic applications of radiation or neutron transport. The parallel computing of these applicat...

Full description

Saved in:
Bibliographic Details
Published in:SIAM journal on scientific computing Vol. 31; no. 5; pp. 3626 - 3642
Main Authors: Mo, Zeyao, Zhang, Aiqing, Wittum, Gabriel
Format: Journal Article
Language:English
Published: Philadelphia Society for Industrial and Applied Mathematics 01.01.2009
Subjects:
Algorithms
Applied mathematics
Applied physics
Computation
Computational mathematics
Computational physics
Equivalence
Fluid mechanics
Geometry
Graph theory
Graphs
Heuristic
Heuristic methods
Laboratories
Optimization
Radiation
Strategy
Transport
ISSN:1064-8275, 1095-7197
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Data flow acyclic directed graphs (digraphs) can be applied to accurately describe the data dependency for a wide range of grid-based scientific computing applications ranging from numerical algebra to realistic applications of radiation or neutron transport. The parallel computing of these applications is equivalent to the parallel execution of digraphs. This paper presents a framework of scalable heuristic algorithms for the parallel execution of digraphs. This framework consists of three components: the heuristic partitioning method of a digraph, the parallel sweeping algorithm for a partitioned digraph, and the heuristic strategy for vertex scheduling and vertex packing. Evaluation rules of heuristic algorithms are presented for better theoretical understanding and performance optimization. Parallel benchmarks for the multigroup neutron or radiation $S_n$ transport using processors from 100 to 2048 on two massively parallel machines show that these heuristic algorithms scale well.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
content type line 14
ObjectType-Feature-2
content type line 23
ISSN:1064-8275
1095-7197
DOI:10.1137/050634554