An efficient heuristic for code partitioning

In this paper, we propose a heuristic for code partitioning for distributed memory multiprocessors (DMMs). Our method is data-flow based where all levels of parallelism can potentially be exploited. Given a weighted directed acyclic graph (DAG) representation of the program, our partitioning algorit...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Parallel computing Ročník 26; číslo 4; s. 399 - 426
Hlavní autori: Ayed, Moez, Gaudiot, Jean-Luc
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 01.03.2000
Predmet:
Critical path
Directed acyclic graph (DAG)
Distributed memory multiprocessor (DMM)
Partition
Processing element (PE)
Task
Task clustering
Task graph
Task merging
Distributed memory multiprocessor (DMM)
Partition
Task
Processing element (PE)
Directed acyclic graph (DAG)
Task graph
Critical path
Task merging
Task clustering
ISSN:0167-8191, 1872-7336
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In this paper, we propose a heuristic for code partitioning for distributed memory multiprocessors (DMMs). Our method is data-flow based where all levels of parallelism can potentially be exploited. Given a weighted directed acyclic graph (DAG) representation of the program, our partitioning algorithm automatically determines the granularity of parallelism by partitioning the graph into tasks to be scheduled on the DMM. The granularity of parallelism depends only on the program to be executed and on the target machine parameters. The output of our algorithm is passed on as input to the scheduling phase. Unlike the scheduling problem as defined by Yang [A. Gerasoulis, T. Yang, IEEE Transactions on Parallel and Distributed Systems 4 (6) (1993) 686–701; T. Yang, Ph.D. Thesis, Rutgers University, New Brunswick, NJ, May 1993; T. Yang, A. Gerasoulis, IEEE Transactions on Parallel and Distributed Systems 5 (9) (1994) 951–967], the method presented in this paper uses task merging rather than task clustering. Finding an optimal solution to this problem is NP-complete. Due to the high cost of graph algorithms, it is nearly impossible to come up with close to optimal solutions that do not have very high cost (higher order polynomial). Therefore, our goal is to find a heuristic that gives good performance, and that has relatively low cost. Given a DAG with E edges and N nodes, the time complexity of our partitioning algorithm is O( E· N 3) in the worst case. For some cases, the average time complexity of the algorithm is O( N( E+ N)).
Bibliografia:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0167-8191
1872-7336
DOI:10.1016/S0167-8191(99)00110-6