Supporting a flexible parallel programming model on a network of workstations

Shih Chen Huang, Zvi Kedem

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We introduce a shared memory software prototype system for executing programs with nested parallelism on a network of workstations. This programming model exhibits a very convenient and natural programming style and provides functionality similar to a subset of Compositional C++. Such programming model is especially suitable for computations whose complexity and parallelism emerges only during their execution, as in divide and conquer problems. To both support and take advantage of the flexibility inherent in the programming model, we develop an architecture, which distributes both the shared memory management and the computation, removing bottlenecks inherent in centralization, thus also providing scalability and dependability. The system supports also dynamic load balancing, and fault tolerance - both transparently to the programmer. The prototype performs well using the realistic platforms of non-dedicated network of workstation. We describe encouraging performance experiments on a network in which some of the machines became slow unpredictably (to the application program). The system coped well with such dynamic behavior.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Distributed Computing Systems
PublisherIEEE
Pages75-82
Number of pages8
StatePublished - 1996
EventProceedings of the 1996 16th International Conference on Distributed Computing Systems - Hong Kong, Hong Kong
Duration: May 27 1996May 30 1996

Other

OtherProceedings of the 1996 16th International Conference on Distributed Computing Systems
CityHong Kong, Hong Kong
Period5/27/965/30/96

Fingerprint

Parallel programming
Computer workstations
Computer networks
Data storage equipment
Dynamic loads
Fault tolerance
Computer programming
Application programs
Resource allocation
Scalability
Computer systems
Experiments

ASJC Scopus subject areas

  • Hardware and Architecture

Cite this

Huang, S. C., & Kedem, Z. (1996). Supporting a flexible parallel programming model on a network of workstations. In Proceedings - International Conference on Distributed Computing Systems (pp. 75-82). IEEE.

Supporting a flexible parallel programming model on a network of workstations. / Huang, Shih Chen; Kedem, Zvi.

Proceedings - International Conference on Distributed Computing Systems. IEEE, 1996. p. 75-82.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Huang, SC & Kedem, Z 1996, Supporting a flexible parallel programming model on a network of workstations. in Proceedings - International Conference on Distributed Computing Systems. IEEE, pp. 75-82, Proceedings of the 1996 16th International Conference on Distributed Computing Systems, Hong Kong, Hong Kong, 5/27/96.
Huang SC, Kedem Z. Supporting a flexible parallel programming model on a network of workstations. In Proceedings - International Conference on Distributed Computing Systems. IEEE. 1996. p. 75-82
Huang, Shih Chen ; Kedem, Zvi. / Supporting a flexible parallel programming model on a network of workstations. Proceedings - International Conference on Distributed Computing Systems. IEEE, 1996. pp. 75-82
@inproceedings{5974552636624eafab976cb07ff51d0b,
title = "Supporting a flexible parallel programming model on a network of workstations",
abstract = "We introduce a shared memory software prototype system for executing programs with nested parallelism on a network of workstations. This programming model exhibits a very convenient and natural programming style and provides functionality similar to a subset of Compositional C++. Such programming model is especially suitable for computations whose complexity and parallelism emerges only during their execution, as in divide and conquer problems. To both support and take advantage of the flexibility inherent in the programming model, we develop an architecture, which distributes both the shared memory management and the computation, removing bottlenecks inherent in centralization, thus also providing scalability and dependability. The system supports also dynamic load balancing, and fault tolerance - both transparently to the programmer. The prototype performs well using the realistic platforms of non-dedicated network of workstation. We describe encouraging performance experiments on a network in which some of the machines became slow unpredictably (to the application program). The system coped well with such dynamic behavior.",
author = "Huang, {Shih Chen} and Zvi Kedem",
year = "1996",
language = "English (US)",
pages = "75--82",
booktitle = "Proceedings - International Conference on Distributed Computing Systems",
publisher = "IEEE",

}

TY - GEN

T1 - Supporting a flexible parallel programming model on a network of workstations

AU - Huang, Shih Chen

AU - Kedem, Zvi

PY - 1996

Y1 - 1996

N2 - We introduce a shared memory software prototype system for executing programs with nested parallelism on a network of workstations. This programming model exhibits a very convenient and natural programming style and provides functionality similar to a subset of Compositional C++. Such programming model is especially suitable for computations whose complexity and parallelism emerges only during their execution, as in divide and conquer problems. To both support and take advantage of the flexibility inherent in the programming model, we develop an architecture, which distributes both the shared memory management and the computation, removing bottlenecks inherent in centralization, thus also providing scalability and dependability. The system supports also dynamic load balancing, and fault tolerance - both transparently to the programmer. The prototype performs well using the realistic platforms of non-dedicated network of workstation. We describe encouraging performance experiments on a network in which some of the machines became slow unpredictably (to the application program). The system coped well with such dynamic behavior.

AB - We introduce a shared memory software prototype system for executing programs with nested parallelism on a network of workstations. This programming model exhibits a very convenient and natural programming style and provides functionality similar to a subset of Compositional C++. Such programming model is especially suitable for computations whose complexity and parallelism emerges only during their execution, as in divide and conquer problems. To both support and take advantage of the flexibility inherent in the programming model, we develop an architecture, which distributes both the shared memory management and the computation, removing bottlenecks inherent in centralization, thus also providing scalability and dependability. The system supports also dynamic load balancing, and fault tolerance - both transparently to the programmer. The prototype performs well using the realistic platforms of non-dedicated network of workstation. We describe encouraging performance experiments on a network in which some of the machines became slow unpredictably (to the application program). The system coped well with such dynamic behavior.

UR - http://www.scopus.com/inward/record.url?scp=0029702998&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029702998&partnerID=8YFLogxK

M3 - Conference contribution

SP - 75

EP - 82

BT - Proceedings - International Conference on Distributed Computing Systems

PB - IEEE

ER -