FROM THE EDITORS
THE SPREAD SPECTRUM IN COMPUTING By Norman Chonacky
F
ROM TIME TO TIME, I FIND IT NECESSARY TO REMIND MYSELF OF HOW BROADLY COMPUTING APPLICATIONS ARE SPREAD ACROSS THE SCIENCES
AND ENGINEERING. THIS BREADTH EXTENDS NOT ONLY ALONG THE AXES OF COMPUTING COMPLEXITY AND DISCIPLINARY DIVERSITY, BUT ALSO ALONG the axes of task and sophistication. Over the years, this magazine has certainly explored the former two, but here I’d like to probe the latter two. This issue’s theme is dedicated to special-purpose computing; in current conventional parlance, this often means using field-programmable gate arrays (FPGAs) instead of software to configure a computer to perform a specific calculation. A central principle of this approach to computation is to use FPGAs to “write” critical parts of the computational program into the hardware, thereby increasing computational speed by replacing cycle speed with gate speed as the scaling factor determining a program’s execution time. The FPGA implements algorithms optimized to a specific calculation, hence the term “special.” Researchers have applied this concept to playing master chess, simulating the environment, and solving other so-called heroic problems.
OUR NEW LOOK
Y
ou might notice something slightly different as you flip through this issue of CiSE. We’ve changed our color scheme—inside and out—as the first step in an eventual far-reaching overhaul of the magazine’s layout design. Our logo, for example, now puts a greater emphasis on science and engineering, instead of just computing, and the color we’re using on internal pages is much brighter than in issues past. As always, we’re interested in what you think about our new look, and we welcome any feedback on what you’re excited to see change and what you’d hate to see go. Send any and all aesthetic opinions to me at
[email protected].
2
Copublished by the IEEE CS and the AIP
1521-9615/06/$20.00 © 2006 IEEE
As the manuscripts submitted to this theme issue started to roll in, I was struck by how many focused on heroic applications. They represent an important yet narrow sector of what we might construe as special-purpose computing, so I was heartened when one arrived that described using an ordinary computer graphics board to compute holograms. I suddenly thought of several other examples of special-purpose computers that have become so commonplace we don’t think of them as special any more, even though they embody that concept. My mind turned to floating-point and array coprocessors, both of which were pioneered long ago to perform computing tasks no longer considered sophisticated. We tried but failed to obtain an appropriate paper that exposes these simpler, easier to understand historic examples. Finding a historical article might have helped make this theme issue more inclusive, illustrated easier-to-apply principles, and hence addressed our very difficult mission to foster computing by maintaining a platform that embraces the widest possible span of people using computing in their science and engineering work. That said, this issue does pull together a fine array of articles that illustrate state-of-theart special-purpose computing efforts. Thinking along these lines reminded me of another case in point about the breadth of task and sophistication among our readers. Earlier this year, I contributed to a Technology Reviews article about the use of computational productivity software packages. We chose to deal with exemplars of packages that we felt compromised the lowest common denominator of those that scientists and engineers might use. In this case, we chose Matlab, Maple, and Mathematica. Yet at a subsequent engineering conference, I spoke to a computational consultant to the engineering industry. When I asked him which of these packages, in his experience, engineers were using for their work, he surprised me by point-
COMPUTING IN SCIENCE & ENGINEERING
ing out that many of them use spreadsheets as their basic computational tool! What struck me most about his answer was how unprepared I was for it. Because he was talking about professionals who are well within the scope of the CiSE mission to serve, I had completely misread our audience. In part, my failure may be due to differences between academe and industry. Whereas universities have a complement of students who are willing to tinker with or seriously dedicate themselves to mastering the more sophisticated packages, businesses do not. Nor do professionals in business have the luxury to take time out to learn these packages. Thus, with the notable exception of those for whom computation, especially intensive or sophisticated computation, is the basis for their work, they go with what is easiest for the task at hand.
T
here is an editorial lesson here. Clearly, in order to think broadly enough to serve the magazine’s mission, we must cast a very wide net. If we want to enable engineers and scientists of all stripes to improve their work by assimilating computational innovations that, although potentially useful, lie far from their bench work, then our articles need to be understandable at a very wide range of levels. Conversely, the computer scientists and engineers who conceive those innovations and develop the products that these engineers will eventually use should be aware of the problems to which their products will be applied. Both groups are our clients, and this is our task. If not CiSE, then who? If not now, then when?
Circulation: Computing in Science & Engineering (ISSN 1521-9615) is published bimonthly by the AIP and the IEEE Computer Society. IEEE Headquarters, Three Park Ave., 17th Floor, New York, NY 10016-5997; IEEE Computer Society Publications Office, 10662 Los Vaqueros Circle, PO Box 3014, Los Alamitos, CA 90720-1314, phone +1 714 821 8380; IEEE Computer Society Headquarters, 1730 Massachusetts Ave. NW, Washington, DC 20036-1903; AIP Circulation and Fulfillment Department, 1NO1, 2 Huntington Quadrangle, Melville, NY 11747-4502. 2006 annual subscription rates: $43 for Computer Society members (print plus online), $73 (sister society), and $74 (individual nonmember). For AIP society members, 2006 annual subscription rates are $42 (print plus online). For more information on other subscription prices, see www.computer.org/subscribe/ or https://www.aip.org/forms/journal_catalog/order_form_fs.html. Computer Society back issues cost $20 for members, $96 for nonmembers; AIP back issues cost $22 for members. Postmaster: Send undelivered copies and address changes to Computing in Science & Engineering, 445 Hoes Ln., Piscataway, NJ 08855. Periodicals postage paid at New York, NY, and at additional mailing offices. Canadian GST #125634188. Canada Post Corporation (Canadian distribution) publications mail agreement number 40013885. Return undeliverable Canadian addresses to PO Box 122, Niagara Falls, ON L2E 6S8 Canada. Printed in the USA. Copyright & reprint permission: Abstracting is permitted with credit to the source. Libraries are permitted to photocopy beyond the limits of US copyright law for private use of patrons those articles that carry a code at the bottom of the first page, provided the per-copy fee indicated in the code is paid through the Copyright Clearance Center, 222 Rosewood Dr., Danvers, MA 01923. For other copying, reprint, or republication permission, write to Copyright and Permissions Dept., IEEE Publications Administration, 445 Hoes Ln., PO Box 1331, Piscataway, NJ 08855-1331. Copyright © 2006 by the Institute of Electrical and Electronics Engineers Inc. All rights reserved.
JANUARY/FEBRUARY 2006
The American Institute of Physics is a not-for-profit membership corporation chartered in New York State in 1931 for the purpose of promoting the advancement and diffusion of the knowledge of physics and its application to human welfare. Leading societies in the fields of physics, astronomy, and related sciences are its members. In order to achieve its purpose, AIP serves physics and related fields of science and technology by serving its member societies, individual scientists, educators, students, R&D leaders, and the general public with programs, services, and publications—information that matters. The Institute publishes its own scientific journals as well as those of its member societies; provides abstracting and indexing services; provides online database services; disseminates reliable information on physics to the public; collects and analyzes statistics on the profession and on physics education; encourages and assists in the documentation and study of the history and philosophy of physics; cooperates with other organizations on educational projects at all levels; and collects and analyzes information on federal programs and budgets. The Institute represents approximately 120,000 scientists through its member societies. In addition, approximately 6,000 students in more than 700 colleges and universities are members of the Institute’s Society of Physics Students, which includes the honor society Sigma Pi Sigma. Industry is represented through the membership of 36 Corporate Associates. Governing Board:* Mildred S. Dresselhaus (chair), Martin Blume, Marc H. Brodsky (ex officio), Slade Cargill, Charles W. Carter Jr., Hilda A. Cerdeira, Marvin L. Cohen, Timothy A. Cohn, Lawrence A. Crum, Robert E. Dickinson, Michael D. Duncan, H. Frederick Dylla, Judy R. Franz, Brian J. Fraser, John A. Graham, Joseph H. Hamilton, Ken Heller, James N. Hollenhorst, Judy C. Holoviak, Anthony M. Johnson, Angela R. Keyser, Bernard V. Khoury, Leonard V. Kuhi, Louis J. Lanzerotti, Rudolf Ludeke, Christopher H. Marshall, Thomas J. McIlrath, Arthur B. Metzner, Robert W. Milkey, James Nelson, John A. Orcutt, Richard W. Peterson, Helen R. Quinn, S. Narasinga Rao, Elizabeth A. Rogan, Bahaa A.E. Saleh, Charles E. Schmid, James B. Smathers, Benjamin B. Snavely (ex officio), A.F. Spilhaus Jr, Richard Stern, and John H. Weaver. *Board members listed in italics are members of the Executive Committee.
Management Committee: Marc H. Brodsky, Executive Director and CEO; Richard Baccante, Treasurer and CFO; Theresa C. Braun, Vice President, Human Resources; James H. Stith, Vice President, Physics Resources; Darlene A. Walters, Senior Vice President, Publishing; and Benjamin B. Snavely, Secretary.
w w w. a i p . o r g 3
