Architecture, algorithms and applications for future generation supercomputers

V. Kumar, A. Sameh, A. Grama, G. Karypis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations


In this paper, we outline a hierarchical architecture for machines capable of over 100 teraOps in a 10 year time-frame. The motivating factors for the design are technological feasibility and economic viability. The envisioned architecture can be built largely from commodity components. The development costs of the machine will therefore be shared by the market. To obtain sustained performance from the machine, we propose a heterogeneous programming environment for the machine. The programming environment optimally uses the power of the hierarchy. Programming models for the stronger machine models existing at the lower levels are tuned for ease of programming. Higher levels of the hierarchy place progressively greater emphasis on locality of data reference. The envisioned machine architecture requires new algorithm design methodologies. We propose to develop hierarchical parallel algorithms and scalability metrics for evaluating such algorithms. We identify three important application areas: large scale numerical simulations, problems in particle dynamics and boundary element methods, and emerging large-scale applications such as data-mining. We briefly outline the process of hierarchical algorithm design for each of these application areas.

Original languageEnglish (US)
Title of host publicationFrontiers of Massively Parallel Computation - Conference Proceedings
Editors Anon
Number of pages9
StatePublished - Dec 1 1996
EventProceedings of the 1996 6th Symposium on the Frontiers of Massively Parallel Computing, Frontiers'96 - Annapolis, MD, USA
Duration: Oct 27 1996Oct 31 1996


OtherProceedings of the 1996 6th Symposium on the Frontiers of Massively Parallel Computing, Frontiers'96
CityAnnapolis, MD, USA


Dive into the research topics of 'Architecture, algorithms and applications for future generation supercomputers'. Together they form a unique fingerprint.

Cite this