At 07:36 AM 1999/03/02 -0800, Paul Leyland <[EMAIL PROTECTED]> wrote:
>> >When I was working with some of the first digital designs in the
>> >100-600 MHz range over 25 years ago...
I suspect the original comment above relates to working with the simpler
digital logic components of the day, not whole processors' clock rate.
As a reference point, a 1985 Fairchild F100K ECL Data book mentions
counters, registers, and flip-flops useful in the 400-500Mhz range.
Schottky TTL
of the same period was capable of about 100-125Mhz in flipflops.
Special purpose devices such as frequency counter prescalers were available
in the gigahertz range. (In July 1981 a 1250. Mhz prescaler chip could be had
for $35.00.) The 1972 Radio Amateur's Handbook mentions both analog IC's
(differential amplifiers) operating up to 100Mhz, and a prescaler operating
up to 320Mhz. (A prescaler is a circuit that divides a clock pulse train
down to a slower frequency by a fixed factor, such as by 10.)
>> Oops. I don't know if this is an extra-zeroes issue or a "M"
>> instead of a
>> "K" or what, but just 10 years ago 1 MHz was good and 7 MHz
>> was high end.
>> 25 years ago, I very much doubt they were bandying about
>> 600MHz anything,
>> since we're only just reaching the 600MHz level now at the
>> end of the 1990s!
>>
>> [Excessive quoted material snipped]
>
>[Excessive signature snipped 8-]
>
>Eh? My first job after finishing my DPhil was microcoding a AMD-2900 series
>bit slice machine which had a 25ns (40MHz) clock. That was in 1983 and it
>was far from rocket science then. Actually, I started (unpaid) work on it a
>couple of years earlier, so we're actually talking about 18 years ago.
>
>The good old 1970's Cray-1 had a 9ns (110MHz) clock if I remember correctly.
>
>*Twenty* years ago, a 4MHz Z80A was a commodity chip. I still have a 1979
>model 380Z from Research Machines with that very cpu. (Incidentally, RM is
>one of the few companies of that era still making PCs.)
>
>I can't remember when I bought my 25MHz 386, but it must be approaching 10
>years ago.
>
>
>Paul
1977: 1Mhz 6502 or 4Mhz Z80 (also the Vax 11/780; Mhz?)
1981: 4.77Mhz 8088 in the IBM PC
1984: 6Mhz 80286 in the IBM AT
1986: 16Mhz 80386 in a Compaq
1990: 33Mhz 80386 (mine just turned 9 & still runs, with its third hard drive;
the first drive cost about $10/MB)
Mhz alone is not a direct measure of performance, even with equal word size.
In 1983 I programmed a single-board PDP-11 clocked around 21Mhz in assembler,
and since it had no multiply or divide instruction, it took
about 480 microseconds to do a 16x16 unsigned integer multiply, which is
far longer than the 30 microseconds or so that a 4.77Mhz 8088 would take.
Ken
________________________________________________________________
Unsubscribe & list info -- http://www.scruz.net/~luke/signup.htm
