Message from the General and Program Chairs

The workshop addresses all areas of massively parallel processing. In organizing this workshop, we recognize that computer solutions to many problems facing modern civilization require a level of computational power that far exceeds current capabilities. Consequently, we desired to solicit papers on research that extends current computational capacity boundaries and gives solutions to currently inaccessible computationally intensive problems, such as some of the grand challenge problems.

General areas of interest include synchronous and asynchronous parallel computation, algorithms and models, systems architecture, hardware, systems software and languages, component technology, and applications. Specific topics of interest include SIMD and MIMD massively parallel systems case studies; teraflop and petaflop system development and applications; intelligent RAM, IRAM, and PIM system development; data parallel and associative computing; case studies and performance analysis of massively parallel systems and applications; resource management for massively parallel applications; domain specific libraries and applications; experience with commercial and experimental massively parallel systems; and systems software and tools for massively parallel computing.

We hope that you will enjoy the selection of manuscripts that are contained in this conference program.

Schedule

• Session 1 (Opening Session) -- 8:30-10:00
  (Session Chair -- Johnnie Baker, Kent State University)

  • Opening Remarks
  • (Keynote Address) Massive Parallelism in the HTMT Project: A Retrospective
    Peter M. Kogge
    Notre Dame University
    This talk will address one of the most ambitious massively parallel computer efforts of the last decade - a multi-institutional attempt to define a machine with a sustainable performance in excess of a petaflop. The talk will overview the technologies, organization, and execution models behind the HTMT, with emphasis on the memory hierarchy, where coordination across literally millions of "memory nodes" (using Processing-In-Memory technology) becomes a necessity.
  • Improved One-to-All Broadcasting Algorithms on Faulty SIMD Hypercubes
    Y. Chen
    Aletheia University
    
    

• Break -- 10:00-10:30

• Session 2 (Algorithms) -- 10:30-12:00
  (Session Chair -- Phil Wilsey, University of Cincinnati)

  • An Associative Implementation of a Parallel Iterative Convex Algorithm
    M. Atwah and J. B. Baker
    Hiram College / Kent State University
  • Radar Signal Processing Using Pipelines Optical Hypercube Interconnects
    H. Forsberg, B. Svensson, A. Ahlander, and M. Jonsson
    Chalmers University of Technology / Ericsson/Halmstad University
  • Predictability for Real-Time Command and Control
    W. Meilander, J. Baker, and J. Potter
    Kent State University
    
    

• Lunch -- 12:00-1:30

• Session 3 (Architectures) -- 1:30-3:00
  (Session Chair -- Maher Atwah, Hiram College)

  • Implementing Associative Processing: Rethinking Earlier Architectural Decisions
    R. Walker, J. Potter, Y. Wang, and M. Wu
    Kent State University
  • Architectural Support for Data-intensive Applications
    K. K. Rangan, N. Pisolkar, N. B. Abu-Ghazaleh, and P. A. Wilsey
    University of Cincinnati / SUNY at Binghamton
  • Cyclical Cascade Chains: A Dynamic Barrier Synchronization Mechanism for Multiprocessor Systems
    T. A. Johnson and R. R. Hoare
    University of Pittsburgh
    
    

• Break -- 3:00-3:30

• Session 4 (Modeling) -- 3:30-5:00
  (Session Chair -- Robert Walker, Kent State University)

  • Timings for Associative Operations on the MASC Model
    M. Jin, J. Baker, and K. Batcher
    Kent State University
  • Benchmark Design for Characterization of Balanced High-Performance Architectures
    A. E. Koniges, R. Rabenseifner, and K. Solchenbach
    Lawrence Livermore National Lab
  • Emulating PetaFLOPS Machines and Blue Gene
    N. Saboo, A. K. Singla, J. M. Unger, and L. V. Kale
    University of Illinois
    
    

• Post-Workshop Wrap-up & Planning for Next Year -- 5:00-5:30

Workshop Organizers

• Organizing Committee:
  • General Chair: Johnnie Baker (baker@mcs.kent.edu)
  • Program Chair: Philip A. Wilsey (paw@ececs.uc.edu)
  • Webmaster: Robert Walker (walker@mcs.kent.edu)
• Program Committee:
  • Nael Abu-Ghazaleh, SUNY Binghamton
  • Johnnie Baker, Kent State University
  • Hank Dietz, University of Kentucky
  • Ray Hoare, University of Pittsburgh
  • Mahmut Kandemir, Penn State University
  • Alice Koniges, LLNL
  • H. J. Siegel, Purdue University
  • Theo Ungerer, University of Karlsruhe
  • Robert Walker, Kent State University
  • Philip A. Wilsey, University of Cincinnati
• Publicity Committee:
  • Nael Abu-Ghazaleh, SUNY Binghamton
  • Maher Atwah, Hiram College
  • Ray Hoare, University of Pittsburgh