Skip to search boxSkip to navigationSkip to main content

Landing CG on EARTH - A Case Study of Fine-Grained Multithreading on an Evolutionary Path.: A case study of fine-grained multithreading on an evolutionary path

  • Kevin B. Theobald
    ,
  • Gagan Agrawal
    ,
  • Rishi Kumar
    ,
  • Gerd Heber
    ,
  • Guang R. Gao
    ,
  • Paul Stodghill
  • University of Delaware
    ,
  • Cornell University
Scholary Output:
Chapter in Book/Report/Conference proceeding
Conference contribution
Research

Related Event

Title

2000 ACM/IEEE Conference on Supercomputing, SC 2000

Event type

Conference

Date

11/04/2000 - 11/10/2000

Location

DallasUnited States

Abstract

<p>We report on our work in developing a fine-grained multithreaded solution for the communication-intensive Conjugate Gradient (CG) problem. In our recent work, we developed a simple yet efficient program for sparse matrix-vector multiply on a multithreaded system. This paper presents an effective mechanism for the reduction-broadcast phase, which is integrated with the sparse MVM, resulting in a scalable implementation of the complete CG application. Three major observations from our experiments on the EARTH multithreaded testbed are: (1) The scalability of our CG implementation is impressive, e.g., absolute speedup is 90 on 120 processors for the NAS CG class B input. (2) Our dataflow-style reduction-broadcast network based on fine-grain multithreading is twice as fast as a serial reduction scheme on the same system. (3) By slowing down the network by a factor of 2, no notable degradation of overall CG performance was observed.</p>

Publication Information

Output type

Scholary Output:
Chapter in Book/Report/Conference proceeding
Conference contribution
Research

Original language

English (US)

Pages from-to (Number of pages)

Pages 4

Publication milestones

  • Published - 2000

Publication status

Published - 2000

Publisher

Association for Computing Machinery

Publication series

  • Publication series name: Proceedings of the International Conference on Supercomputing
    Volume: 2000-November

ISBN (Electronic)

0780398025

Publication IDs

  • Scopus: 77955203874

Host publication title

SC 2000 - Proceedings of the 2000 ACM/IEEE Conference on Supercomputing

Publication metrics

Metrics

Scopus
citations
Fractional count
1
Fractional count
0.14
Fractional count
6
Fractional count
0.86
Fractional count
1
Fractional count
1

PlumX, opens in new tab

Citation count
7
Captures
10