Browse Prior Art Database

Supercomputers = Colossal Computations + Enormous Expectations + Renownec' Risk

IP.com Disclosure Number: IPCOM000131601D
Original Publication Date: 1983-May-01
Included in the Prior Art Database: 2005-Nov-11
Document File: 15 page(s) / 55K

Publishing Venue

Software Patent Institute

Related People

Neil R. Lincoln: AUTHOR [+3]

Abstract

Are supercomputer developers following the same old refrain or creating a new tune? The Cyber 205 project serves as a basis for this look at current and next-generation requirements. A supercomputer is o system that is only one generation behind the computing requirements of leading edge efforts in science and engineering -- Neil Lincoln Translating the needs and desires of those who practice large-scale computation into appropriate hardware and software systems requires continual compromise, negotiation, and grinding labor -- with a pinch of inventiveness thrown in. To acknowledged supercomputer developers, and scientific users from the last two decades, that statement is an often sung but seldom heeded refrain. Now we face a new generation of problems, and new technological opportunities entice us into a rephrasing and replaying of the same old tunes -- tunes that began long ago with the supercomputer architect. A natural focus for any new discussion of supercomputer development -- and the central concern of this article -- then, is the superprocessor architecture function.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 7% of the total text.

Page 1 of 15

THIS DOCUMENT IS AN APPROXIMATE REPRESENTATION OF THE ORIGINAL.

This record contains textual material that is copyright ©; 1983 by the Institute of Electrical and Electronics Engineers, Inc. All rights reserved. Contact the IEEE Computer Society http://www.computer.org/ (714-821-8380) for copies of the complete work that was the source of this textual material and for all use beyond that as a record from the SPI Database.

Supercomputers = Colossal Computations + Enormous Expectations + Renownec' Risk

Neil R. Lincoln

Control Data Corporation

Are supercomputer developers following the same old refrain or creating a new tune? The Cyber 205 project serves as a basis for this look at current and next-generation requirements.

A supercomputer is o system that is only one generation behind the computing requirements of leading edge efforts in science and engineering -- Neil Lincoln

Translating the needs and desires of those who practice large-scale computation into appropriate hardware and software systems requires continual compromise, negotiation, and grinding labor -- with a pinch of inventiveness thrown in. To acknowledged supercomputer developers, and scientific users from the last two decades, that statement is an often sung but seldom heeded refrain. Now we face a new generation of problems, and new technological opportunities entice us into a rephrasing and replaying of the same old tunes -- tunes that began long ago with the supercomputer architect. A natural focus for any new discussion of supercomputer development -- and the central concern of this article -- then, is the superprocessor architecture function.

"Camelot" the architecture function ~

The legendary knight-errant riding into the dark forest to confront a fire-breathing dragon is not unlike the supercomputer developer who sets out to slay a new set of mammoth computations. Both are sent off with great cheers of encouragement -- by spectators. Both are blissfully ignorant of the nature of the beast, despite an incredibly detailed analysis of its size and fury -- also by spectators. Both are somewhat awed by the mythology and mystery surrounding their goal (thanks in part, to reports from spectators living in the deep forest). Both, in their naivete, aspire to deeds of heroism and hope for tremendous rewards from the king (and his taxpaying spectators). Finally, both are most certainly "pure-ofheart" - - as are all the spectators, of course.

When we develop new machinery to keep up with demands for scientific computation, we have to consider all previous efforts;ivhich began long ago with the knightly deeds of the computer architect. Cyber 200 developers established the following list of what the computer architecting function requires:

(1) review of the premises and successes of previous computer developments,

(2) intimate knowledge of the computational environment in which the new machine is to be employed,

(3) reasonable projections for the direction of computations...