11 Aug
2015
11 Aug
'15
4:20 p.m.
On 08/11/2015 08:37 AM, Paul Koning wrote:
No, it was a CDC product, but developed by CDC Holland
(at their
Rijswijk office). Apparently it was created at the insistence of a
number of CDC?s academic customers in Europe.
Which explains why I never saw it at CPD SVLOPS. CDC in those days was
fond of "bootleg" products. MACE/KRONOS/NOS being the chiefest of them.
At least one program that I wrote (in a week) was turned into an
official product, complete with reference manual. It was never intended
as anything more than a way fro me to get my own work done. "Ports" of
it were downright silly.
Which makes sense; it demonstrates what nearly
everyone now knows,
which is that RISC architecture is a very good way to design a
computer.
What it told me was that byte.character addressability wasn't all that
it was cracked up to be. Even after the CYBER 70 introduced the CMU (on
the 72/73 only; not on the 74), use of it didn't contribute massively to
the speed of COBOL.
I suspect part of the reason is that Algol wasn?t all
that popular in
the USA even if its heyday. Add to that the fact that most computer
designers weren?t all that skilled in software. And finally, as the
RISC experience has shown, it isn?t really worth it.
...which is why we're all working in x86 today. :)
What RISC does demand is a fast memory system. The 6600 had 1 usec
memory interleaved 10 ways, so it could issue a read or write every
machine cycle (100 nsec). Without that, the 6600 could well have been a
real dog.
--Chuck