Selected Historical Computer Designs

Welcome to a gallery of fascinating machine designs!

I want to collect here information on historical firsts and on important machines that are relatively unknown and/or are underappreciated. I am indebted to Dr. Fred Brooks, whose love of computer architecture inspired me in class at UNC, Chapel Hill. It was a privilege to also work as a graduate student assistant for him on early drafts of his architecture text, Computer Architecture: Concepts and Evolution. See his text for a complete history of computer designs.

Please email me if you have comments, additional references on items in the collection, or suggestions for additional items.

The architects behind the machines

List of computer architects

The machines admired by computer architects

List of admired designs

Historical essays

Architecture

• Condition codes (under construction)

• EPIC (explicitly parallel instruction computing)

• ILP (instruction-level parallelism)

• Input/output systems

• Interrupts (under construction)

• Multithreading (under construction)

• Subroutine calls (under construction)

• Subword parallelism and graphics/multimedia support (under construction)

• Synchronization instructions (under construction)

• System calls and protection mechanisms (under construction)

Implementation

• Cooling techniques (under construction)

• Decoded instruction caches (under construction)

• Eager execution (under construction)

• Prediction buffers (under construction)

• see also ILP above

• Microprogramming

On-line historical resources

Stored Program Concept Attributed to Eckert

• Letter from John W. Mauchly to Don Knuth, June 22, 1978, with copy of "Disclosure of Magnetic Calculating Machine" (pdf), written by J. Presper Eckert, Jr., and witnessed by John W. Mauchly, January 29, 1944.

• See also: Nick Metropolis and Jack Worlton, "A Trilogy on Errors in the History of Computing," IEEE Annals of the History of Computing, vol. 2, no. 1, January-March 1980, pp. 49-59. IEEE Xplore link

Stored Program Concept vs. Modern Code Paradigm

• Thomas Haigh, Mark Priestley, and Crispin Rope, "Reconsidering the Stored Program Concept," IEEE Annals of the History of Computing, vol. 36, no. 1, January-March 2014, pp. 4-17.

• Thomas Haigh and Mark Priestley, "Where Code Comes From: Architectures of Automatic Control from Babbage to Algol," Communications of the ACM, vol. 59, no. 1, January 2016, pp. 39-44.

EINAC Evolution

• Thomas Haigh, Mark Priestley, and Crispin Rope, "Engineering 'The Miracle of the ENIAC': Implementing the Modern Code Paradigm," IEEE Annals of the History of Computing, vol. 36, no. 2, April-June 2014, pp. 41-59.

• Thomas Haigh, Mark Priestley, and Crispin Rope, "Los Alamos Bets on ENIAC: Nuclear Monte Carlo Simulations, 1947-48," IEEE Annals of the History of Computing, vol. 36, no. 3, July-September 2014, pp. 42-63.

EDVAC Evolution

• John von Neumann, "First Draft of a Report on the EDVAC" (pdf), Contract No. W-670-ORD-4926, Between the United States Army Ordnance Department and the University of Pennsylvania Moore School of Electrical Engineering University of Pennsylvania, June 30, 1945.

  reformatted version by Michael Godfrey (pdf)

• J. Presper Eckert, Jr., and John W. Mauchly, "Automatic High Speed Computing: A Progress Report on the EDVAC" (pdf), Moore School of Electrical Engineering, Univ. of Pennsylvania, Pennsylvania, Philadelphia, Pa., Sept. 30, 1945.

• Michael Godfrey and David Hendry, "The computer as von Neumann planned it," IEEE Annals of the History of Computing, vol. 15, no. 1, 1993, pp. 11-21. IEEE Xplore link

  The initial EDVAC architecture proposed by von Neumann is similar in some ways to the later Burroughs B5000.

  vN-EDVAC was a serial, synchronous, 32-bit word, zero-address, binary machine with a hierarchical operation-code structure of eight basic codes, 10 subcodes, and one modifier. It had three nonaddressable registers, organized as a stack mechanism. Tagged memory was used to distinguish instructions from data.

  [p. 14, emphasis in original]

• Michael Williams, "The origins, uses, and fate of the EDVAC," IEEE Annals of the History of Computing, vol. 15, no. 1, 1993, pp. 22-38. IEEE Xplore link

• Don Knuth, "Von Neumann's First Computer Program," ACM Computing Surveys, vol. 2, no. 4, December 1970, pp. 247-260. ACM portal link

IAS instruction set

• Arthur W. Burks, Herman H. Goldstine, and John von Neumann, "Preliminary discussion of the logical design of an electronic computing instrument," from report to U. S. Army Ordnance Department, 1946, reprinted in Bell and Newell

• Leif Harcke of the EE Dept. at Stanford University tracked down the 1954 Final Project Report (pdf) for the IAS Electronic Computer Project, which contains the instruction set that was actually implemented

• see also Harcke's notes and links to the instruction sets of other IAS-inspired computers

Surveys and Descriptions of Historical Computers

• List of computers (1946-2002)

• Computer Conservation Society's web site on Our Computer Heritage, a project to document 80 computers that were designed and built in the UK between 1945 and 1970

  (see also the online issues of Resurrection: The Bulletin of the Computer Conservation Society)

• Manchester Mark I and II (pdf)

• Ed Thelen's OCR'ed copy of BRL Report No. 971, Martin Weik, A Survey of Domestic Electronic Digital Computing Systems, December 1955

• BRL Report, 1961 version

• Saul Rosen, "Electronic Computers: A Historical Survey," ACM Computing Surveys, vol. 1, no. 1, March 1969, pp. 7-36. ACM portal link

• The History of the Microcomputer - Invention and Evolution, Stanley Mazor

• Great Microprocessors of the Past and Present (V 13.4.0), John Bayko

• History of Bull, GE, and Honeywell computers maintained by J. Bellec and J. Faure

• Information Processing Society of Japan (IPSJ) Computer Museum

• Articles on the history of calculators maintained by James Redin

• Derek Smith, A Brief History of Computing Technology
  • to 1925
  • 1925 to 1942
  • 1943 to 1950
  • 1951 to 1958

• information on early CDC supercomputers
  • CDC 6600
  • CDC 7600
  • CDC 8600

On-line Books

• Simon H. Lavington, Early British Computers

• Werner Buchholz, Planning A Computer System - Project Stretch (10.4 MB pdf)

• James Thornton, Design Of A Computer - The Control Data 6600 (18 MB pdf)

• Gordon Bell's on-line copy of Bell and Newell, Computer Structures: Readings and Examples

• Gordon Bell's on-line copy of Siewiorek, Bell, and Newell, Computer Structures: Principles and Examples

• Gordon Bell's on-line copy of Bell, Mudge, and McNamara, Computer Engineering: A DEC View of Hardware Systems Design

Manuals

• Al Kossow's collection of old computer manuals at bitsavers mirror

• IBM 704 Manual of Operation, 1956 (jpegs)

• The Descriptor - A Definition of the B 5000 Information Processing System, Feb. 1961 (jpegs) (also, other Burroughs 5000 and 205 manuals are available from UVa)

• Gordon Bell's collection of on-line Digital Equipment Corp (DEC) manuals (PDP-1, -4, -5, -6, and -11) and articles on PDP-11/VAX history

• Sandpile.org collection of on-line documents on various x86 processors

• chipdb.org datasheet archive

Document Collections

• Project Whirlwind reports (MIT)

• IAS project reports

• Digital Tech Journal, 1985-1998

Some interesting patents (under construction)

Selected National Lab computer design projects

• S-1 - spawned CAD logic design

Selected university computer design projects

• Berkeley - RISC

• Cal Tech - Cosmic Cube

• CMU
  • C.mmp (Hydra OS)
  • Cm* (Medusa and StarOS)

• Hertfordshire - HARP

• Illinois - CEDAR

• Stanford
  • SUN workstation
  • MIPS
  • DASH / FLASH

Some notable commercial "failures" that advanced the state-of-the-art

• IBM Stretch, late-1950s, early supercomputer

• IBM Advanced Computing System (ACS), 1965-1969, ECL-based superscalar

• IBM Future System (FS), 1971-1975, single-level store

• DG Fountainhead Project (FHP), 1976-1981, paged microcode for various language-based virtual machines and single-level store across a network of computers

• Intel 432, 1975-1985, object-oriented processor (also known as SSO, 8816, 8800)

• IBM Fort Knox, mid-1980s, adopt the 801 company wide

• Multiflow and Cydrome, 1980s, VLIW

• DEC PRISM, 1985-1988, forerunner of Alpha

• Cray-3 / Cray-4, 1985-1995, high-density galium arsenide design

• Supercomputer Systems, 1988-1993, high-density ECL design (Steve Chen, see US 5,197,130 and 5,251,097)

• Intel Itanium 1 (Merced), a project management nightmare on an EPIC scale
  • Stephen Shankland, "Itanium: A cautionary tale," CNET News.com, December 7, 2005
  • David Hamilton, "Intel gambles with Itanium," The Wall Street Journal Online, May 28, 2001 (alternate link)
  • Linley Gwennap, "What's wrong with Merced?" MPR Editorial, August 3, 1998

[Mark's homepage] [CPSC homepage] [Clemson Univ. homepage]

mark@cs.clemson.edu