Volume 7, Issue 1 -
Spring/Summer 1999

Volume 6, Issue 3
Fall 1998

Volume 6, Issue 2
Spring/Summer 1998

Volume 6, Issue 1
Winter 1998

Volume 5, Issue 4
Fall 1997

Volume 5, Issue 3
Summer 1997

Volume 5, Issue 2
Spring 1997

Volume 5, Issue 1
Winter 1997

Volume 4, Issue 4
Fall 1996

Volume 4, Issue 3
Summer 1996

Volume 4, Issue 2
Spring 1996

Volume 4, Issue 1
Winter 1996

Volume 3, Issue 4
Fall 1995

Volume 3, Issue 3
Summer 1995

Volume 3, Issue 2
Spring 1995

Volume 3, Issue 1
January 1995

Volume 2, Issue 4
October 1994

Volume 2, Issue 3
July 1994

Volume 2, Issue 2
April 1994

Volume 2, Issue 1
January 1994

Volume 1, Issue 4
October 1993

Volume 1, Issue 3
July 1993

Volume 1, Issue 2
April 1993

Volume 1, Issue 1
January 1993

Student Research: CRPC-sponsored Graduate Students Win Best Paper Awards at SUPERCOMPUTING '92

Three of the five finalists in the SUPERCOMPUTING '92 student paper competition completed their work through CRPC programs. Gregor von Laszewski, a graduate student at Syracuse University, was the overall winner of the competition. His paper (with Manish Parashar, also a graduate student at Syracuse), entitled "On the Parallelization of Blocked LU Factorization Algorithms for Distributed Memory Architectures," was submitted in the algorithms and applications category. The paper presents the parallelization of blocked algorithms for LU factorization. The researchers isolated problems inherent to sequential block algorithms and provided approaches to overcome them on distributed memory architectures. The performance of proposed algorithms are demonstrated on iPSC/860 hypercube. The work presented in this paper is a part of a CRPC project to create the HPF/Fortran-D benchmark suite.

The paper, "Compiler Blockability of Numerical Algorithms," authored by Steve Carr (with Ken Kennedy), a post-doctorate researcher at the CRPC, won the award in the category of compilers. The paper describes an investigation into compiler technology designed to render machine- specific programming of the memory hierarchy unnecessary. Results revealed that through the use of compiler optimizations, many numerical algorithms can be expressed in a natural form while retaining good memory performance. The investigation, conducted while Carr was still a graduate student, paid particular attention to linear algebra algorithms. Since finishing his dissertation in September 1992, Carr has been working within the CRPC on other memory hierarchy issues and an implementation in the scalar compiler being built by Keith Cooper and colleagues at Rice University. The compiler is designed to optimize for single nodes of a parallel system.

Rajeev Thakur and Ravi Ponnusamy, graduate students at Syracuse University, were given the award for best student paper in the performance measurement category. Their paper was entitled "Scheduling Regular and Irregular Communication Patterns on the CM-5." In this paper they discuss performance effects of scheduling regular and irregular communication patterns on a specific architecture of CM-5. In addition, they implemented and tested different algorithms for scheduling irregular communication using several synthetic and real problems such as 2D FFT, the conjugate gradient solver and the Euler Solver.


Table of Contents