Gene Amdahl - a Computer Pioneer Carl-Johan Ivarsson
Total Page:16
File Type:pdf, Size:1020Kb
Load more
Recommended publications
-
The State of Digital Computer Technology in Europe, 1961
This report indicates the level of computer development and application in each of the thirty countries of Europe, most of which were recently visited by the author The State Of Digital Computer Technology In Europe By NELSON M. BLACHMAN Digital computers are now in use in practically every Communist Countries country in Europe, though in some there are still very few U. S. S.R. A very thorough account of Soviet com- and these are of foreign manufacture. Such machines have puter work is given in the report edited by Willis Ware [3]. been built in sixteen European countries, of which seven To Ware's collection of Russian machines can be added a are producing them commercially. The map above shows computer at the Moscow Power Institute, a school for the the computer geography of Europe and the Near East. It is training of heavy-current electrical engineers (Figure 1). somewhat difficult to rank the countries on a one-dimen- It is described as having a speed of 25,000 fixed-point sional scale both because of the many-faceted nature of the operations or five to seven thousand floating-point oper- computer field and because their populations differ widely ations per second, a word length of 20 or 40 bits, and a in size. Nevertheh~ss, Great Britain clearly comes first 4096-word ferrite-core memory, supplemented by a fixed (after the U. S.). She is followed by (West) Germany, the 256-word store on paper printed with condensers plus a U. S. S. R., France, and Japan. Much useful information on 50,000-word magnetic-tape store. -
Lynn Conway Professor of Electrical Engineering and Computer Science, Emerita University of Michigan, Ann Arbor, MI 48109-2110 [email protected]
IBM-ACS: Reminiscences and Lessons Learned From a 1960’s Supercomputer Project * Lynn Conway Professor of Electrical Engineering and Computer Science, Emerita University of Michigan, Ann Arbor, MI 48109-2110 [email protected] Abstract. This paper contains reminiscences of my work as a young engineer at IBM- Advanced Computing Systems. I met my colleague Brian Randell during a particularly exciting time there – a time that shaped our later careers in very interesting ways. This paper reflects on those long-ago experiences and the many lessons learned back then. I’m hoping that other ACS veterans will share their memories with us too, and that together we can build ever-clearer images of those heady days. Keywords: IBM, Advanced Computing Systems, supercomputer, computer architecture, system design, project dynamics, design process design, multi-level simulation, superscalar, instruction level parallelism, multiple out-of-order dynamic instruction scheduling, Xerox Palo Alto Research Center, VLSI design. 1 Introduction I was hired by IBM Research right out of graduate school, and soon joined what would become the IBM Advanced Computing Systems project just as it was forming in 1965. In these reflections, I’d like to share glimpses of that amazing project from my perspective as a young impressionable engineer at the time. It was a golden era in computer research, a time when fundamental breakthroughs were being made across a wide front. The well-distilled and highly codified results of that and subsequent work, as contained in today’s modern textbooks, give no clue as to how they came to be. Lost in those texts is all the excitement, the challenge, the confusion, the camaraderie, the chaos and the fun – the feeling of what it was really like to be there – at that frontier, at that time. -
Open PDF in New Window
BEST AVAILABLE COPY i The pur'pose of this DIGITAL COMPUTER Itop*"°a""-'"""neesietter' YNEWSLETTER . W OFFICf OF NIVAM RUSEARCMI • MATNEMWTICAL SCIENCES DIVISION Vol. 9, No. 2 Editors: Gordon D. Goldstein April 1957 Albrecht J. Neumann TABLE OF CONTENTS It o Page No. W- COMPUTERS. U. S. A. "1.Air Force Armament Center, ARDC, Eglin AFB, Florida 1 2. Air Force Cambridge Research Center, Bedford, Mass. 1 3. Autonetics, RECOMP, Downey, Calif. 2 4. Corps of Engineers, U. S. Army 2 5. IBM 709. New York, New York 3 6. Lincoln Laboratory TX-2, M.I.T., Lexington, Mass. 4 7. Litton Industries 20 and 40 DDA, Beverly Hills, Calif. 5 8. Naval Air Test Centcr, Naval Air Station, Patuxent River, Maryland 5 9. National Cash Register Co. NC 304, Dayton, Ohio 6 10. Naval Air Missile Test Center, RAYDAC, Point Mugu, Calif. 7 11. New York Naval Shipyard, Brooklyn, New York 7 12. Philco, TRANSAC. Philadelphia, Penna. 7 13. Western Reserve Univ., Cleveland, Ohio 8 COMPUTING CENTERS I. Univ. of California, Radiation Lab., Livermore, Calif. 9 2. Univ. of California, SWAC, Los Angeles, Calif. 10 3. Electronic Associates, Inc., Princeton Computation Center, Princeton, New Jersey 10 4. Franklin Institute Laboratories, Computing Center, Philadelphia, Penna. 11 5. George Washington Univ., Logistics Research Project, Washington, D. C. 11 6. M.I.T., WHIRLWIND I, Cambridge, Mass. 12 7. National Bureau of Standards, Applied Mathematics Div., Washington, D.C. 12 8. Naval Proving Ground, Naval Ordnance Computation Center, Dahlgren, Virgin-.a 12 9. Ramo Wooldridge Corp., Digital Computing Center, Los Angeles, Calif. -
Niels Ivar Bech
Niels Ivar Bech Born 1920 Lemvig, Denmark; died 1975; originator of Danish computer development. Niels Ivar Bech was one of Europe's most creative leaders in the field of electronic digital computers.1 He originated Danish computer development under the auspices of the Danish Academy of Technical Sciences and was first managing director of its subsidiary, Regnecentralen, which was Denmark's (and one of Europe's) first independent designer and builder of electronic computers. Bech was born in 1920 in Lemvig, a small town in the northwestern corner of Jutland, Denmark; his schooling ended with his graduation from Gentofte High School (Statsskole) in 1940. Because he had no further formal education, he was not held in as high esteem as he deserved by some less gifted people who had degrees or were university professors. During the war years, Bech was a teacher. When Denmark was occupied by the Nazis, he became a runner for the distribution of illegal underground newspapers, and on occasion served on the crews of the small boats that perilously smuggled Danish Jews across the Kattegat to Sweden. After the war, from 1949 to 1957, he worked as a calculator in the Actuarial Department of the Copenhagen Telephone Company (Kobenhavns Telefon Aktieselskab, KTA). The Danish Academy of Technical Sciences established a committee on electronic computing in 1947, and in 1952 the academy obtained free access to the complete design of the computer BESK (Binar Electronisk Sekevens Kalkylator) being built in Stockholm by the Swedish Mathematical Center (Matematikmaskinnamndens Arbetsgrupp). In 1953 the Danish academy founded a nonprofit computer subsidiary, Regnecentralen. -
Oral History Interview with Gene M. Amdahl
An Interview with GENE M. AMDAHL OH 107 Conducted by Arthur L. Norberg on 16 April 1986 17 January 1989 5 April 1989 Cupertino, CA Charles Babbage Institute The Center for the History of Information Processing University of Minnesota, Minneapolis Copyright, Charles Babbage Institute 1 Gene M. Amdahl Interview 16 April 1986 17 January 1989 5 April 1989 Abstract Amdahl begins the first session with a description of his early life and education. He recalls his experiences teaching in the Advanced Specialized Training Program during and after World War II. Amdahl discusses his graduate work at the University of Wisconsin and his direction of the design and construction of WISC. He concludes the first session with a brief discussion of his work at International Business Machines (IBM). In the second and third sessions, Amdahl discusses his role in the design of several computers for IBM including the STRETCH, 701, 701A, and 704. He discusses his work with Nathaniel Rochester and IBM's management of the design process for computers. He also mentions his work with Ramo -Woolridge, Aeronutronic, and Computer Sciences Corporation. 2 GENE M. AMDAHL INTERVIEW DATE: 16 April 1986 INTERVIEWER: Arthur L. Norberg LOCATION: Cupertino, CA NORBERG: Dr. Amdahl, can you tell me something about your parents? I know you're from South Dakota originally. Were they a farming family in South Dakota? AMDAHL: Yes, my grandfather homesteaded in South Dakota prior to it becoming a state. So the homesteading would have occurred sometime in the early '70s. And on my mother's side, they homesteaded also on and about the same time, also in South Dakota. -
Norwegian Computer Tecnology Founding a New Industry
Norwegian Computer Tecnology Founding a new Industry Yngvar Lundh Research Engineer rered from NDRE Norwegian Defence Research Establisment Early history of development a personal account • 1950s: – Electronic brains ”Replacing so many matemacians” – A few isolated goups in Scandinavia BESK, DASK, NUSSE – Similar groups in the US and elsewhere Probably many military applicaons. • 1960s: – Group of young research engineers at NDRE – Spawning three major businesses Three growing businesses • Norsk Data grew fast to become ”The Flagship of Norwegian Industry” – unl the crisis in the late 1980s • Computer division of Kongsberg Våpenfabrikk specialised systems • Consulng company AS Informasjonskontroll Informasjonskontroll Professional knowledge,advice and assistance Study ”Siffer Frekvens‐ systemet” could In my thesis work I invesgated add, mulply, divide a special digital technique Vacuum tube digital logic Reliability • Vacuum tubes unreliable • Much litterature about that • Solid state? Transistors and magnec devices were studied and a few experimental transistorized machines were built in the late 1950s in USA Fellowship at MIT • In 1958 – 59 I was guest • I could use it all by at MIT and worked on myself the TX‐0 computer • Studied circuits • Transistors • Magnec core memory • CRT screen Paper tape, CRT, Flexowriter • Programming in binary Exploing Man machine • Some fellow researchers communicaons in the TX‐0 lab developed useful programming aids: • Tom Stockham: ”Insight” • Larry Roberts: ”Text on the screen” • Yngvar Lundh: Input via -
Något Om De Första Svenska Datamaskinerna
Något om de första svenska datamaskinerna Av Jörgen Lund De datamaskiner - eller som vi säger idag, datorer - som fanns tillgängliga i början av 1950-talet var samtliga laboratoriebyggda. De var till yttermera visso inte datorer i modern bemärkelse utan snarare automatiska beräkningsmaskiner. Det skulle dröja några år innan de första egentliga ”databehandlingsmaskinerna”, dvs vad tyskarna kal lade ”Datenverarbeitungsanlagen”, kom på marknaden; med andra ord, datorer avsedda för det område som kallas administrativ databe handling (ADB). I och med lanseringen av de första ADB-datorerna i slutet av 1950-talet i Sverige inleddes en ny epok med en mer allmän utbredning och användning av det relativt nya hjälpmedlet, datorn. I mitten av 50-talet stod det klart att datorn var ett hjälpmedel att räkna med i framtiden - i dubbel bemärkelse. Sverige skulle bli något av ett föregångsland i kraft av skickliga och begåvade tekniker och matematiker. Visserligen hade man innan dess varit i det stora landet i väst, USA, och lärt sig en hel del om den nya teknologin; visserligen hade amerikanska maskiner tjänat som förebild för de första svenska datorerna, men de konstruerades och byggdes icke förty av svenska tekniker och matematiker. ”Nattvandrare Varför inte inleda med ett citat ur Dagens Nyheter 1 februari 1953: kan konstatera ”Nattvandrare kan konstatera att det alltid lyser i nämndens fönster att.. ut mot Drottninggatan. Där arbetar BARK, Sveriges första matema tikmaskin, ambitiöst dygnet runt och tjänar in vackra slantar ät svenska staten. När den blev färdig 1950 hade den kostat 600000 kronor. Nu ger den en avkastning pä i runt tal 100000 om äret och kan alltsä sägas vara en ovanligt lyckad kapitalplacering. -
SHARE and Data Security
What Are You Going To Do With All That Sensitive Data? (do you even know where it all is?) Barry Schrager Xbridge Systems, Inc. [email protected] (650) 319-7345 DataSniff User Session David Wade, CIO of Primerica 12943: How to Identify Datasets Containing PCI, PII or Other Sensitive Information Tuesday, February 5, 2013: 11:00 AM-12:00 PM Golden Gate 6, Lobby Level (San Francisco Hilton) Visit Xbridge Systems at Booth #202 in the Expo © 2013 Xbridge Systems, Inc. 2 Barry Schrager Formed the SHARE Security Project in 1972 which created the requirements for today’s mainframe security systems http://www.share-sec.com/1972-2012.html In 1973, one of 20 customers invited to Poughkeepsie to review the new MVM (aka MVS) Operating System before it was announced Architect and primary author of ACF2 – developed after IBM told SHARE Security Project that protection by default and algorithmic definition of datasets and users were not achievable. SKK sold to UCCEL in 1986 – ACF2 had a 60% market share Member, Mainframe Hall of Fame Honored to be included with: Admiral Grace Hopper, T.J. Watson, Jr. and Dr. Gene Amdahl © 2013 Xbridge Systems, Inc. 3 Xbridge Systems Xbridge co-founded by Gene Amdahl and Ray Williams the co- founders of Amdahl Corporation Xbridge Systems redefines data discovery with DataSniff, the world's FIRST and ONLY automated Mainframe Data Discovery tool DataSniff Software is a powerful search engine for discovering sensitive data stored on IBM z/OS series mainframes © 2013 Xbridge Systems, Inc. 4 State of South Carolina Breach Announced in October 2012 3.6 million Social Security Numbers 387,000 Credit Card Numbers Only a portion of the data was encrypted “The cost is also going to be enormous” (SC Gov. -
The Genesis of the Mainframe Bob O. Evans
The Genesis of the Mainframe Bob O. Evans 1 Introduction by Wilhelm G. Spruth In 1927 the German author Stefan Zweig published a short book labeled “Sternstunden der Menschheit” (world hours of mankind). In it he descripes 14 historical events that changed history forever. I have always believed the appearance of System /360 in 1964 has been such an event, changing the direction of the computer industry in more ways than anything else in the last 50 years. The design of the S/360 architecture is rightfully credited to Gene Amdahl, Gerry Blaauw and Fred Brooks. Bob O. Evans has been the IBM executive who made it happen. It is impossible to have met Bob O. Evans and not been impressed. He was forceful, decisive, intelligent, an excellent engineer with a broad vision, an uncanny capability to understand the most complex issues, and an outstanding leader for the people working for him. He also had an overpowering personality. I will be forever grateful for his guidance. In 2002 I learned Bob O. Evans had written his memoirs, had considered to publish them as a book, and had been adviced by his friends not to do so, because the text contained too much sensitive material. I contacted Evans and asked him if I could read the manuscript. He gracefully consented and e-mailed me a copy. Bob O. Evans died in 2004. I believe Bob O. Evans personal account of such a monumental event as the S/360 announcement should be made available. Thus in 2007 I asked his son Douglas B. -
Copyright National Academy of Sciences. All Rights Reserved. Memorial Tributes: Volume 22
Memorial Tributes: Volume 22 Copyright National Academy of Sciences. All rights reserved. Memorial Tributes: Volume 22 GENE M. AMDAHL 1922–2015 Elected in 1967 “Development of large computer systems.” BY MARK D. HILL SUBMITTED BY THE NAE HOME SECRETARY GENE MYRON AMDAHL, known for seminal work on the design of mainframe computers, deft business and entrepre- neurial leadership, and the eponymous Amdahl’s law, died November 10, 2015, at the age of 92 in Palo Alto, California. He was born November 16, 1922, in Flandreau, South Dakota (about 50 miles from Sioux Falls), to a farm family with Norwegian and Swedish roots. His early educational roots were modest: as a child he attended a one-room school without electricity. Rural electrification reached him only in high school, he noted in a 1992 interview with Computerworld. He attempted to join the military after the attack on Pearl Harbor in 1941, but was turned down because his farming skills were considered more important at the time. A few years later, in 1944, he joined the Navy and taught radar at naval training centers around the United States. He earned his bachelor’s degree in engineering physics from South Dakota State University in 1948, and master’s and doctoral degrees in theoretical physics from the University of Wisconsin–Madison in 1949 and 1952. In 1979 the University of Wisconsin–Madison awarded him an honorary doctorate in science. It was during his graduate school years that his interest in digital computing bloomed. His doctoral dissertation, “The 9 Copyright National Academy of Sciences. All rights reserved. -
Downloading from Naur's Website: 19
1 2017.04.16 Accepted for publication in Nuncius Hamburgensis, Band 20. Preprint of invited paper for Gudrun Wolfschmidt's book: Vom Abakus zum Computer - Begleitbuch zur Ausstellung "Geschichte der Rechentechnik", 2015-2019 GIER: A Danish computer from 1961 with a role in the modern revolution of astronomy By Erik Høg, lektor emeritus, Niels Bohr Institute, Copenhagen Abstract: A Danish computer, GIER, from 1961 played a vital role in the development of a new method for astrometric measurement. This method, photon counting astrometry, ultimately led to two satellites with a significant role in the modern revolution of astronomy. A GIER was installed at the Hamburg Observatory in 1964 where it was used to implement the entirely new method for the meas- urement of stellar positions by means of a meridian circle, then the fundamental instrument of as- trometry. An expedition to Perth in Western Australia with the instrument and the computer was a suc- cess. This method was also implemented in space in the first ever astrometric satellite Hipparcos launched by ESA in 1989. The Hipparcos results published in 1997 revolutionized astrometry with an impact in all branches of astronomy from the solar system and stellar structure to cosmic distances and the dynamics of the Milky Way. In turn, the results paved the way for a successor, the one million times more powerful Gaia astrometry satellite launched by ESA in 2013. Preparations for a Gaia suc- cessor in twenty years are making progress. Zusammenfassung: Eine elektronische Rechenmaschine, GIER, von 1961 aus Dänischer Herkunft spielte eine vitale Rolle bei der Entwiklung einer neuen astrometrischen Messmethode. -
Early Nordic Compilers and Autocodes Peter Sestoft
Early Nordic Compilers and Autocodes Peter Sestoft To cite this version: Peter Sestoft. Early Nordic Compilers and Autocodes. 4th History of Nordic Computing (HiNC4), Aug 2014, Copenhagen, Denmark. pp.350-366, 10.1007/978-3-319-17145-6_36. hal-01301428 HAL Id: hal-01301428 https://hal.inria.fr/hal-01301428 Submitted on 12 Apr 2016 HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. Distributed under a Creative Commons Attribution| 4.0 International License Early Nordic Compilers and Autocodes Version 2.1.0 of 2014-11-17 Peter Sestoft IT University of Copenhagen Rued Langgaards Vej 7, DK-2300 Copenhagen S, Denmark [email protected] Abstract. The early development of compilers for high-level program- ming languages, and of so-called autocoding systems, is well documented at the international level but not as regards the Nordic countries. The goal of this paper is to provide a survey of compiler and autocode development in the Nordic countries in the early years, roughly 1953 to 1965, and to relate it to international developments. We also touch on some of the historical societal context. 1 Introduction A compiler translates a high-level, programmer-friendly programming language into the machine code that computer hardware can execute.