🚀 go-pugleaf

In article <sZcrr1G00hMNI3EF5i@cs.cmu.edu> Daniel.Stodolsky@cs.cmu.edu writes:
>... one should be able to compute a 32 x 32 -> 64 bit multiply with four
>16x16 -> 32 multiplies, 4 32 bit adds and a few shifts.  So why not put some
>big memory killer micros to work and have a 16 by 16 multiply lookup table?
>It would consume 10 megs of core, but that's nothing for a KILLER MICRO.

10 meg?  A 16x16 lookup table is 2^32 entries of 32 bits each, which by
my arithmetic is 16 gigabytes of memory, a little rich for even a mainframe
these days.  And imagine testing the damn thing.  You have to test every 
word and verify it against an independently computed value; if each test
took 5us, a single pass through it would take six hours.  Perhaps this isn't
the right technology yet.

I do know there are medium sized combinatorial multipliers, perhaps a little
pushing on them would be more productive.
-- 
John R. Levine, Segue Software, POB 349, Cambridge MA 02238, +1 617 864 9650
johnl@esegue.segue.boston.ma.us, {ima|lotus|spdcc}!esegue!johnl
"Now, we are all jelly doughnuts."