7 Aug
2006
7 Aug
'06
11:03 a.m.
On Monday 07 August 2006 12:15 am, Chuck Guzis wrote:
On 8/6/2006 at 10:41 PM Ray Arachelian wrote:
Wasn't the 68010 supposed to fix this? I have one of those, too...
--
Member of the toughest, meanest, deadliest, most unrelenting -- and
ablest -- form of life in this section of space, a critter that can
be killed but can't be tamed. --Robert A. Heinlein, "The Puppet Masters"
-
Information is more dangerous than cannon to a society ruled by lies. --James
M Dakin
It's worth a read to get a feel of the
excitement the 68K caused back in
the day when it was introduced. Some of it is very funny, there's one
issue where the author compares an Intel FPU to the 68000 running
software floating point routines, and guess what, the 68000 actually ran
FASTER! :-)
I never did benchmark the 68881. IIRC, the 68K was a big deal in the fab
business. I think it used the then-very-new 3 micron technology. My
biggest disappointment was that the CPU instructions weren't resumable
after a fault--i.e. with those 24 bits of address, there was no possibility
of virtual memory implementation. I did hear of a scheme for using two
68Ks, one running a half-clock ahead of the other to get around this, but
that was prohibitively expensive. 16 MB sounded like a huge amount of
memory back then.