hes@ecsvax.UUCP (Henry Schaffer) (02/14/86)
IBM's Research Highlights publication (No. 1, 1986) has the above title. The footnote on "RISC" says "RISC is a term coined outside IBM. While the IBM scientists who originated the technology never attributed its efficiency solely or principally to reducing the number of instructions, the term-- which suggests an underlying simplicity-- is widely used in the computer industry." This 4-page issue is devoted to the concepts and their history. The original idea is credited to Dr. John Cocke, IBM Fellow in 1975. (He was born in NC and joined IBM from Duke Univ., so I guess we in the Research Triangle area should be proud of him!) IBM gets a lot of static for using developments of others rather than innovating. (I think that there is some truth to this.) However this may be, is the RISC architecture an example of IBM leading the way in an architectural innovation? You can probably get a copy from Research Commhnications Dept. IBM T. J. Watson Research Center, P.O. Box 218, Yorktown Heights NY 10598 (914)945-3036. --henry schaffer
cak@purdue.UUCP (Christopher A. Kent) (02/16/86)
In article <1194@ecsvax.UUCP>, hes@ecsvax.UUCP (Henry Schaffer) writes: > The original idea [of RISC] is credited to Dr. John Cocke, IBM Fellow in > 1975. > > However this may be, is the RISC architecture an example of IBM > leading the way in an architectural innovation? I dunno. I think an argument can be made that Seymour Cray was designing RISC machines more than 10 years earlier. Look at the CDC 6000 series, started in 1960, first delivered in OCtober 1964 (a 6600). It has a small number of simple instructions, efficiently implemented, and simple addressing modes (the processor is a three address machine, but the addressing modes correspond to register, direct, and register-index). Those seem to be the salient features of the RISC architecture idea. It's just my opinion, chris