Distributed S-Net: High-Level Message Passing without the Hassle

C. Grelck, Jukka Julku, F. Penczek

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

S-N ET is a declarative coordination language and component technology primarily aimed at modern multi-core/many-core chip architectures. It builds on the concept of stream processing to structure dynamically evolving networks of communicating asynchronous components, which themselves are implemented using a conventional language suitable for the application domain. We sketch out the design and implementation of Distributed S-N ET, a conservative extension of S-N ET aimed at distributed memory architectures ranging from many-core chip architectures with hierarchical memory organisations to more traditional clusters of workstations and supercomputers. Three case studies illustrate how to use Distributed S-N ET to implement different models of parallel execution, i.e. pipelined signal processing, client-server and domain decomposition. Runtimes obtained on a workstation cluster demonstrate how Distributed S-N ET allows programmers with little or no background in parallel programming to make effective use of distributed memory architectures with minimal programming effort
Original languageEnglish
Title of host publication1st ACM SIGPLAN Workshop on Advances in Message Passing (AMP'10), Toronto, Canada, 2010
PublisherAssociation for Computing Machinery ACM
Number of pages10
Publication statusPublished - 2010
MoE publication typeA4 Article in a conference publication
EventThe 1st ACM SIGPLAN Workshop on Advances in Message Passing (AMP'10). Toronto, Canada -
Duration: 1 Jan 2010 → …

Conference

ConferenceThe 1st ACM SIGPLAN Workshop on Advances in Message Passing (AMP'10). Toronto, Canada
Period1/01/10 → …

Fingerprint

Memory architecture
Message passing
Parallel programming
Computer workstations
Supercomputers
Computer programming
Signal processing
Servers
Decomposition
Data storage equipment
Processing

Keywords

  • stream processing
  • component coordination
  • cluster computing
  • message passing

Cite this

Grelck, C., Julku, J., & Penczek, F. (2010). Distributed S-Net: High-Level Message Passing without the Hassle. In 1st ACM SIGPLAN Workshop on Advances in Message Passing (AMP'10), Toronto, Canada, 2010 Association for Computing Machinery ACM.
Grelck, C. ; Julku, Jukka ; Penczek, F. / Distributed S-Net: High-Level Message Passing without the Hassle. 1st ACM SIGPLAN Workshop on Advances in Message Passing (AMP'10), Toronto, Canada, 2010. Association for Computing Machinery ACM, 2010.
@inproceedings{c001f309fa784bfc9dec34bfce8328e4,
title = "Distributed S-Net: High-Level Message Passing without the Hassle",
abstract = "S-N ET is a declarative coordination language and component technology primarily aimed at modern multi-core/many-core chip architectures. It builds on the concept of stream processing to structure dynamically evolving networks of communicating asynchronous components, which themselves are implemented using a conventional language suitable for the application domain. We sketch out the design and implementation of Distributed S-N ET, a conservative extension of S-N ET aimed at distributed memory architectures ranging from many-core chip architectures with hierarchical memory organisations to more traditional clusters of workstations and supercomputers. Three case studies illustrate how to use Distributed S-N ET to implement different models of parallel execution, i.e. pipelined signal processing, client-server and domain decomposition. Runtimes obtained on a workstation cluster demonstrate how Distributed S-N ET allows programmers with little or no background in parallel programming to make effective use of distributed memory architectures with minimal programming effort",
keywords = "stream processing, component coordination, cluster computing, message passing",
author = "C. Grelck and Jukka Julku and F. Penczek",
year = "2010",
language = "English",
booktitle = "1st ACM SIGPLAN Workshop on Advances in Message Passing (AMP'10), Toronto, Canada, 2010",
publisher = "Association for Computing Machinery ACM",
address = "United States",

}

Grelck, C, Julku, J & Penczek, F 2010, Distributed S-Net: High-Level Message Passing without the Hassle. in 1st ACM SIGPLAN Workshop on Advances in Message Passing (AMP'10), Toronto, Canada, 2010. Association for Computing Machinery ACM, The 1st ACM SIGPLAN Workshop on Advances in Message Passing (AMP'10). Toronto, Canada, 1/01/10.

Distributed S-Net: High-Level Message Passing without the Hassle. / Grelck, C.; Julku, Jukka; Penczek, F.

1st ACM SIGPLAN Workshop on Advances in Message Passing (AMP'10), Toronto, Canada, 2010. Association for Computing Machinery ACM, 2010.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Distributed S-Net: High-Level Message Passing without the Hassle

AU - Grelck, C.

AU - Julku, Jukka

AU - Penczek, F.

PY - 2010

Y1 - 2010

N2 - S-N ET is a declarative coordination language and component technology primarily aimed at modern multi-core/many-core chip architectures. It builds on the concept of stream processing to structure dynamically evolving networks of communicating asynchronous components, which themselves are implemented using a conventional language suitable for the application domain. We sketch out the design and implementation of Distributed S-N ET, a conservative extension of S-N ET aimed at distributed memory architectures ranging from many-core chip architectures with hierarchical memory organisations to more traditional clusters of workstations and supercomputers. Three case studies illustrate how to use Distributed S-N ET to implement different models of parallel execution, i.e. pipelined signal processing, client-server and domain decomposition. Runtimes obtained on a workstation cluster demonstrate how Distributed S-N ET allows programmers with little or no background in parallel programming to make effective use of distributed memory architectures with minimal programming effort

AB - S-N ET is a declarative coordination language and component technology primarily aimed at modern multi-core/many-core chip architectures. It builds on the concept of stream processing to structure dynamically evolving networks of communicating asynchronous components, which themselves are implemented using a conventional language suitable for the application domain. We sketch out the design and implementation of Distributed S-N ET, a conservative extension of S-N ET aimed at distributed memory architectures ranging from many-core chip architectures with hierarchical memory organisations to more traditional clusters of workstations and supercomputers. Three case studies illustrate how to use Distributed S-N ET to implement different models of parallel execution, i.e. pipelined signal processing, client-server and domain decomposition. Runtimes obtained on a workstation cluster demonstrate how Distributed S-N ET allows programmers with little or no background in parallel programming to make effective use of distributed memory architectures with minimal programming effort

KW - stream processing

KW - component coordination

KW - cluster computing

KW - message passing

M3 - Conference article in proceedings

BT - 1st ACM SIGPLAN Workshop on Advances in Message Passing (AMP'10), Toronto, Canada, 2010

PB - Association for Computing Machinery ACM

ER -

Grelck C, Julku J, Penczek F. Distributed S-Net: High-Level Message Passing without the Hassle. In 1st ACM SIGPLAN Workshop on Advances in Message Passing (AMP'10), Toronto, Canada, 2010. Association for Computing Machinery ACM. 2010