Portable petaflop/s programming: Applying distributed computing methodology to the grid within a single machine room

Paul R Woodward, S. E. Anderson

Research output: Contribution to journalConference articlepeer-review

5 Scopus citations

Abstract

Petaflop/s computing platforms will combine deep memory hierarchies in both latency and bandwidth with a need for many-thousand-fold parallelism. Initial users of these systems will most likely be asked to meet these challenges to efficient parallel program design armed only with minimal system software. A candidate for a portable petaflop/s programming model that can enable these important early application programs to be developed while at the same time permitting these same applications to run efficiently on the most capable computing systems now available, is presented.

Original languageEnglish (US)
Pages (from-to)70-83
Number of pages14
JournalIEEE International Symposium on High Performance Distributed Computing, Proceedings
StatePublished - Dec 1 1999
EventProceedings of the 1999 8th IEEE International Symposium on High Performance Distributed Computing - HPDC-8 - Redondo Beach, CA, USA
Duration: Aug 3 1999Aug 6 1999

Fingerprint

Dive into the research topics of 'Portable petaflop/s programming: Applying distributed computing methodology to the grid within a single machine room'. Together they form a unique fingerprint.

Cite this