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

WORKSHOP ADDRESSES STRATEGIES FOR PETAFLOPS SYSTEM DEVELOPMENT

The Workshop on Petaflops Software Models, held January 28 and 29 in San Diego, was the latest in a series of meetings addressing key technical issues in developing petaflops systems that will make ultra-high performance computers usable. The workshop focused on identifying critical software problems and evaluating a "layered" approach to software development that could enable the co-development of hardware and software, achieve code reuse across petaflops computers, and reduce software development costs.

The workshop was attended by 25 researchers in the high performance computing community, including Ian Foster (chair), Geoffrey Fox, Ken Kennedy, Paul Messina, Dan Reed, and Rick Stevens, all of the CRPC. The workshop built on the findings of a June 1996 PetaSoft meeting that identified deep memory hierarchies, high degrees of concurrency, and scalable operating system services as key technical challenges. The January workshop included four diverse white papers that presented new perspectives on the petaflops software problem.

The participants identified three key areas in which substantial progress is required: management of parallelism and latency, operating systems scalability, and performance and debugging tools. They determined that advances in any or all of these areas would have an immediate impact on the usability of today's highly parallel computer systems. They established quantitative measures for both required capabilities and the current state of the art in each area, providing concrete goals for future research and development activities.

For more information, see http://www.hq.nasa.gov/hpcc/petaflops/ .