Collaborative Computing: Networking, Applications and Worksharing. 4th International Conference, CollaborateCom 2008, Orlando, FL, USA, November 13-16, 2008, Revised Selected Papers

Research Article

Archer: A Community Distributed Computing Infrastructure for Computer Architecture Research and Education

Download77 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-03354-4_7,
        author={Renato Figueiredo and P. Boykin and Jos\^{e} Fortes and Tao Li and Jie-Kwon Peir and David Wolinsky and Lizy John and David Kaeli and David Lilja and Sally McKee and Gokhan Memik and Alain Roy and Gary Tyson},
        title={Archer: A Community Distributed Computing Infrastructure for Computer Architecture Research and Education},
        proceedings={Collaborative Computing: Networking, Applications and Worksharing. 4th International Conference, CollaborateCom 2008, Orlando, FL, USA, November 13-16, 2008, Revised Selected Papers},
        proceedings_a={COLLABORATECOM},
        year={2012},
        month={5},
        keywords={virtualization computer architecture simulation collaborative environments Grid computing},
        doi={10.1007/978-3-642-03354-4_7}
    }
    
  • Renato Figueiredo
    P. Boykin
    José Fortes
    Tao Li
    Jie-Kwon Peir
    David Wolinsky
    Lizy John
    David Kaeli
    David Lilja
    Sally McKee
    Gokhan Memik
    Alain Roy
    Gary Tyson
    Year: 2012
    Archer: A Community Distributed Computing Infrastructure for Computer Architecture Research and Education
    COLLABORATECOM
    Springer
    DOI: 10.1007/978-3-642-03354-4_7
Renato Figueiredo1, P. Boykin1, José Fortes1, Tao Li1, Jie-Kwon Peir1, David Wolinsky1, Lizy John2, David Kaeli3, David Lilja4, Sally McKee5, Gokhan Memik6, Alain Roy7, Gary Tyson8
  • 1: University of Florida
  • 2: University of Texas
  • 3: Northeastern University
  • 4: University of Minnesota
  • 5: Cornell University
  • 6: Northwestern University
  • 7: University of Wisconsin
  • 8: Florida State University

Abstract

This paper introduces Archer, a community-based computing infrastructure supporting computer architecture research and education. The Archer system builds on virtualization techniques to provide a collaborative environment that facilitates sharing of computational resources and data among users. It integrates batch scheduling middleware to deliver high-throughput computing services aggregated from resources distributed across wide-area networks and owned by different participating entities in a seamless manner. The paper discusses the motivations that have led to the design of Archer, describes its core middleware components, and presents an analysis of the functionality and performance of the first wide-area deployment of Archer running a representative computer architecture simulation workload.