A high performance message-passing system for network of workstations

Sung Yong Park, Salim A Hariri

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

With the proliferation of Network of Workstations (NOW) environment, there has been a great demand for a high performance message-passing system to implement High Performance Distributed Computing (HPDC) applications over NOW environment. NYNET (ATM wide area network testbed in New York state) Communication System (NCS) is a multithreaded message-passing system developed at Syracuse University that provides low-latency and high-throughput communication services over the Asynchronous Transfer Mode (ATM) based HPDC environment. NCS provides High Performance Application Communication Interface (HPI) to support applications that demand high-throughput and low-latency communication services. This paper outlines the general architecture of NCS and presents the implementation approach of NCS HPI over an ATM network. This interface has been developed by modifying Fore Systems' ATM Application Programming Interface (API) and its device driver. NCS HPI uses read/write trap routines to bypass traditional operating system calls and kernel-level communication interface (e.g., UNIX System V Streams). It reduces latency, data transfer time, and avoid using traditional communication protocols (e.g., TCP/IP). This substantially improves the communication performance.

Original languageEnglish (US)
Pages (from-to)159-179
Number of pages21
JournalJournal of Supercomputing
Volume11
Issue number2
StatePublished - 1997
Externally publishedYes

Fingerprint

Network of Workstations
Message passing
Message Passing
Asynchronous transfer mode
High Performance
Communication
Latency
Distributed computer systems
Distributed Computing
High Throughput
Throughput
Asynchronous Systems
TCP/IP
UNIX
Wide area networks
Communication Protocol
Data Transfer
Data transfer
Proliferation
Testbeds

Keywords

  • Application Programming Interface
  • ATM
  • High Performance Distributed Computing
  • Message-Passing Tool
  • Multithreading
  • Network of Workstations

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Hardware and Architecture
  • Electrical and Electronic Engineering
  • Theoretical Computer Science

Cite this

A high performance message-passing system for network of workstations. / Park, Sung Yong; Hariri, Salim A.

In: Journal of Supercomputing, Vol. 11, No. 2, 1997, p. 159-179.

Research output: Contribution to journalArticle

@article{5d58ec51d8134e05b9130460c3fb55ff,
title = "A high performance message-passing system for network of workstations",
abstract = "With the proliferation of Network of Workstations (NOW) environment, there has been a great demand for a high performance message-passing system to implement High Performance Distributed Computing (HPDC) applications over NOW environment. NYNET (ATM wide area network testbed in New York state) Communication System (NCS) is a multithreaded message-passing system developed at Syracuse University that provides low-latency and high-throughput communication services over the Asynchronous Transfer Mode (ATM) based HPDC environment. NCS provides High Performance Application Communication Interface (HPI) to support applications that demand high-throughput and low-latency communication services. This paper outlines the general architecture of NCS and presents the implementation approach of NCS HPI over an ATM network. This interface has been developed by modifying Fore Systems' ATM Application Programming Interface (API) and its device driver. NCS HPI uses read/write trap routines to bypass traditional operating system calls and kernel-level communication interface (e.g., UNIX System V Streams). It reduces latency, data transfer time, and avoid using traditional communication protocols (e.g., TCP/IP). This substantially improves the communication performance.",
keywords = "Application Programming Interface, ATM, High Performance Distributed Computing, Message-Passing Tool, Multithreading, Network of Workstations",
author = "Park, {Sung Yong} and Hariri, {Salim A}",
year = "1997",
language = "English (US)",
volume = "11",
pages = "159--179",
journal = "Journal of Supercomputing",
issn = "0920-8542",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - A high performance message-passing system for network of workstations

AU - Park, Sung Yong

AU - Hariri, Salim A

PY - 1997

Y1 - 1997

N2 - With the proliferation of Network of Workstations (NOW) environment, there has been a great demand for a high performance message-passing system to implement High Performance Distributed Computing (HPDC) applications over NOW environment. NYNET (ATM wide area network testbed in New York state) Communication System (NCS) is a multithreaded message-passing system developed at Syracuse University that provides low-latency and high-throughput communication services over the Asynchronous Transfer Mode (ATM) based HPDC environment. NCS provides High Performance Application Communication Interface (HPI) to support applications that demand high-throughput and low-latency communication services. This paper outlines the general architecture of NCS and presents the implementation approach of NCS HPI over an ATM network. This interface has been developed by modifying Fore Systems' ATM Application Programming Interface (API) and its device driver. NCS HPI uses read/write trap routines to bypass traditional operating system calls and kernel-level communication interface (e.g., UNIX System V Streams). It reduces latency, data transfer time, and avoid using traditional communication protocols (e.g., TCP/IP). This substantially improves the communication performance.

AB - With the proliferation of Network of Workstations (NOW) environment, there has been a great demand for a high performance message-passing system to implement High Performance Distributed Computing (HPDC) applications over NOW environment. NYNET (ATM wide area network testbed in New York state) Communication System (NCS) is a multithreaded message-passing system developed at Syracuse University that provides low-latency and high-throughput communication services over the Asynchronous Transfer Mode (ATM) based HPDC environment. NCS provides High Performance Application Communication Interface (HPI) to support applications that demand high-throughput and low-latency communication services. This paper outlines the general architecture of NCS and presents the implementation approach of NCS HPI over an ATM network. This interface has been developed by modifying Fore Systems' ATM Application Programming Interface (API) and its device driver. NCS HPI uses read/write trap routines to bypass traditional operating system calls and kernel-level communication interface (e.g., UNIX System V Streams). It reduces latency, data transfer time, and avoid using traditional communication protocols (e.g., TCP/IP). This substantially improves the communication performance.

KW - Application Programming Interface

KW - ATM

KW - High Performance Distributed Computing

KW - Message-Passing Tool

KW - Multithreading

KW - Network of Workstations

UR - http://www.scopus.com/inward/record.url?scp=0031351714&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031351714&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0031351714

VL - 11

SP - 159

EP - 179

JO - Journal of Supercomputing

JF - Journal of Supercomputing

SN - 0920-8542

IS - 2

ER -