Who are the Computer Architects?

last updated: February 2017

  1. Considerations about the list
  2. Supercomputer processors
  3. VLIW processors
  4. Independence architecture processors (Intel IA-64)
  5. Mainframe processors
  6. Minisupercomputer processors
  7. Minicomputer and Superminicomputer processors (16 and 32-bit)
  8. Microcomputer processors
  9. Workstation processors (32 and 64-bit)
  10. Selected early workstations
  11. Wintel processors (16 and 32-bit)
  12. Multimedia processors
  13. LISP processors
  14. Java processors
  15. Other language-directed processors
  16. Stack processors
  17. Embedded processors
  18. DSP processors
  19. Selected game processors
  20. Acknowledgements
  21. Revision history


Considerations about the list

The success and failure of high risk computer developments can quite often be traced to a single individual. It is not accidental that unique persons such as Gene Amdahl, Seymour Cray, Fred Brooks, and Bob Barton have become recognized leaders in the computer architecture and design field. Their reputations did not arise from a happy coincidence of being associated with a successful project; rather, they stand out because of their ability to generate a system wide concept, determine a course of action to get it implemented, make the necessary tradeoffs and finally drive through all obstacles to ensure completion of their vision.

Neil Lincoln, CDC (from "It's really not as much fun building a supercomputer as it is simply inventing one," 1977)

There is no doubt that Lincoln named four of the most influential computer architects of the 1950s and 1960s. However, as a more recent architect told me, people outside the design circles (sometimes even meaning company executives) have bought into a myth: "in the '60s, Computer Architecture Giants Walked The Earth, and we pathetic lame-o descendants aren't fit to carry their slide rules." I agree that it is a myth. It shouldn't be the case that just Amdahl, Cray, Brooks, and Barton are recognized as giants in computer architecture and everyone else today is a midget. There are many tremendously gifted people at work in instruction set design and especially microarchitecture; so, I am publishing this list to identify them and recognize their work.

The current format is a listing of an instruction set architecture (ISA) and its architect(s), followed by implementations of that ISA and the associated microarchitect(s)/designer(s). The processors I am listing have been available for sale commercially, and in most instances, I have categorized the processors by company. Although I may extend the list back into and before the 1970s, the current list mainly includes late 1980s and 1990s ISAs and microprocessor implementations. I especially want to highlight the high-performance (i.e., high-risk) implementations.

However, I approach this task recognizing several limitations of the list:

I would appreciate help in the form of your corrections, additions, and other suggestions. I am especially interested in published articles of these kinds:

I am also interested in URLs of web-published information.

I know of three books that help describe the environment and decision-making constraints (e.g., politics) facing an architect:

Harwood Kolsky wrote an excellent analysis of the problems in the IBM Stretch project. His observations, written in 1961, about problems such as a committee compromising and including competing proposals in a single design and such as making design decisions without proper cost and performance evaluation, remain relevant 50 years later!

Robert Yung's PhD dissertation, "Evaluation of a Commercial Microprocessor," UC Berkeley, SMLI TR-98-65, June 1998, describes the design decisions for the UltraSPARC microprocessor. Chapter 3 of his dissertation discusses design principles and pitfalls, and Chapter 6 discusses lessons learned with respect to design methodologies, business decisions, and technology considerations.

More recently, Bob Colwell has discussed some of his experiences at Intel in the 1990s while working on the Intel P6 and early phases of the Pentium 4 in Things CPU Architects Need To Think About (abstract), Stanford University Computer Systems Laboratory, EE380 Colloquium Series, Feb. 18, 2004. [available on the web, Windows Media, 80+ mins.] Bob has also written a book describing his experiences, mainly from a project manager perspective, called The Pentium Chronicles, IEEE-CS/Wiley-Interscience, 2006, and in 2009 was interviewed by Paul Edwards for an oral history (164 pp pdf).

Also, some articles that describe the design and verification process include:

Mark Smotherman


See also the list of machine designs admired by computer architects.


Supercomputer processors

... much more to do!


Astronautics


Control Data Corporation (CDC)


Cray Research (CRI)

[Seymour Cray left CDC in 1972 to found CRI. He left CRI in 1989 to found CCC. CRI merged with SGI in 1996. A separate Cray Research business unit was later created by SGI in 1999 and sold to Tera in 2000. Tera renamed itself as Cray, Inc.]


Cray Computer (CCC)

[CCC started in 1989 and closed in 1995. Seymour Cray founded SRC in 1996.]


Fuji Film


Fujitsu


Hitachi


NEC


Supercomputer Systems, Inc. (SSI)


SiCortex


Tera


Texas Instruments


Thinking Machines, Inc. (TMI)


VLIW processors

... more to do!

See multimedia processor section.


Apollo (see Apollo entry in workstation processor section)


Culler Scientific Systems


Cydrome


FPS (Floating Point Systems)


Fujitsu


Intel


Multiflow


Tera (see supercomputer processor section)


Texas Instruments


Independence architecture processors

Name due to Josh Fisher and Bob Rau. Explicitly encoded information on instruction independence is placed in the instruction format by the compiler. Difference from VLIW is that hardware does the scheduling. Example prototype is Burton Smith's Horizon processor. ... more to do!


Intel