mark@mips.COM (Mark G. Johnson) (11/13/88)
In article <19070@uflorida.cis.ufl.EDU>, cl0@beach.cis.ufl.edu writes >According to the recent Communication ACM (Vol. 31, No. 10, Oct. 1988, >p.1173), the world fastest microprocessor is now in existence and clocks >in at over 60 Megahertz. Any one have more information of it? Thanks. Um, since the i4004 there's always been a world's fastest microprocessor (its name just changes with time ;-). But seriously, the title at present -- November 1988 -- belongs to Rockwell International. They have a Galliun Arsenide MESFET implementation of the Defense Dept's "core MIPS" (a derivative of the Stanford Univ. risc research) instruction set. In February 1988 it ran at 150 million native instructions per second. Some may quibble with this since it was a multi- chip implementation.... so the runner-up might be considered: Texas Instruments implemented the DARPA "core MIPS" instruction set in Gallium Arsenide *bipolar* technology. They claim 200 MHz and 200 million native instructions per second, when their die shrink pops out of fab. That too was in February; maybe their shrink is out and running. (With DARPA contracts they officially publish their results only occasionally). In February the non-shrunk die was running at 120 MHz. In the commercial realm, one might want to consider the ECL implementation of Sun's SPARC architecture (built by B.I.T. and rumored to operate at >79 MHz), the GaAs processors available from Vitesse and Honeywell, (both >100 MHz), and so forth. Prediction: Whatever uP you choose to brand "worlds fastest", there will be lots of disagreement. LOTS of disagreement. Rockwell device: "A 150 MOPS GaAs 8b Slice Processor", R. V. Gauthier et al, 1988 IEEE ISSCC, pp. 32-33. TI device: "A 32b GaAs RISC Microprocessor", D. A. Whitmire et al, 1988 IEEE ISSCC, pp. 34-35. -- -- Mark Johnson MIPS Computer Systems, 930 E. Arques, Sunnyvale, CA 94086 ...!decwrl!mips!mark (408) 991-0208
oconnor@disney.steinmetz (Dennis M. O'Connor) (11/15/88)
An article by mark@mips.COM (Mark G. Johnson) says:
] In article <19070@uflorida.cis.ufl.EDU>, cl0@beach.cis.ufl.edu writes
] >According to the recent Communication ACM (Vol. 31, No. 10, Oct. 1988,
] >p.1173), the world fastest microprocessor is now in existence and clocks
] >in at over 60 Megahertz. Any one have more information of it? Thanks.
]
] [...] the title [...] November 1988 -- belongs to Rockwell
] International [...] Galliun Arsenide MESFET implementation [...]
] at 150 million native instructions per second. [...]
]
] Texas Instruments [...] Gallium Arsenide *bipolar* technology.
] [...] 200 MHz and 200 million native [IPS]
] when their die shrink pops out of fab ... in February [...]
] In February the non-shrunk die was running at 120 MHz.
] [...]
] Prediction: Whatever uP you choose to brand "worlds fastest", there will
] be lots of disagreement. LOTS of disagreement.
This is very true. For instance, the the IEEE FP uniots for the
GaAs chips mentioned use bit-serial techniques to do multiplies.
For the TI chip, for example :
Integer multiply : 39 cycles, 195ns
Integer divide : 47 cycles, 235ns
FADD single : 6 cycles, 30ns
FMUL single : 19 cycles, 95ns
FDIV single : 38 cycles, 190ns
Double precision floating point is even slower.
This isn't slow, but on-the-market CMOS chips can and have done better,
simply by throwing more transistors at the problem. Although I haven't
seen any CMOS 30ns IEEE adders, I've seen much faster CMOS multipliers.
So what's your measure of speed : Integer adds or floating multiplies ?
Remember that speed isn't GaAs's only interesting property to the
military. They are VERY Rad-hard, which is sometimes more important.
The best bulk CMOS process I've seen is only good to a megarad.
--
Dennis O'Connor oconnor%sungod@steinmetz.UUCP ARPA: OCONNORDM@ge-crd.arpa
"Never confuse the USENET with something that matters, like CAFFEINE."