Original Publication Date: 1978-Sep-01
Included in the Prior Art Database: 2005-Nov-10
Software Patent Institute
Hollis L. Caswell: AUTHOR [+13]
Honeywell Information Systems
THIS DOCUMENT IS AN APPROXIMATE REPRESENTATION OF THE ORIGINAL.
This record contains textual material that is copyright ©; 1978 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.
Hollis L. Caswell IBM
Thomas J. Watson Research Center
George A. Brown Texas Instruments
Daniel H. Carter Texas Instruments
Edward B. Eichelberger
William C. Holton
Paul Losleben Department of Defense
Richard J. Petschauer
Robert M. Sullivan
Computer technology will continue to advance, and the capabilities we need will exist in VLSI. But capitalizing on them will require innovative design tools and architectures.
In a world of generally rising costs, the cost of data processing has fallen steadily during the past 25 years. In 1954, when vacuum tubes and magnetic cores were the switching and memory components used in computers, the cost of performing 100,000 multiplications was $1.26. In 1978, as a result of the advances in LSI technology, it is less than S.01. Today, for a few hundred dollars, we can duplicate the capability of hardware costing tens of thousands of dollars in the early 60's.
There is no fundamental reason why this progress should not continue well into the 80's. However, technologists must meet certain challenges if the rapid rate of progress is to continue. These are the challenges we outline in this blueprint article and have explored from our own separate perspectives in the papers on which it is based.'
IEEE Computer Society, Sep 01, 1978 Page 1 IEEE Computer Volume 11 Number 9, Pages 10-19
We emphasize silicon LSI technology and terminals. We hayed omitted other important areas, not because significant progress has been lacking or will not occur in those areas in the future, but rather because they are likely to pose less serious problems as we move into the 80's. An example where we can expect continued progress is magnetic storage. As Figure 1 shows, the rental costs of magnetic storage have decreased rapidly during the past 15 years. Moreover, new developments such as floppy disks and magnetic bubbles will alter the strateD used in organizing magnetic stores. As the technology advances, each dollar spent on magnetic storage will buy more effective storage, and we see no major problems that must be solved to allow this advance to continue.
This article represents a consensus of the authors views. but does not necessarily reflect their individual opinions or those of the organizations they represent.
VLSI fabrication technology
Providing users with ma...