26 Oct
1999
26 Oct
'99
4:21 a.m.
Mike Cheponis wrote:
[stuff deleted]
Now, I have proven to the satisfaction of everybody
that, ASSUMING
synchronous buses that are identical in every way except speed
(one being twice as fast as the two half-speed busses) that in two
real-life situations, one faster bus is BETTER than two separate busses.
*sighs* And it's just as easy to demonstrate cases where multiple
buses are superior to a single, faster bus. What does this have to do
with old iron?
I'm waiting for somebody who knows what he/she is
talking about on this
issue and provides data, assumptions, references, and, if necessary,
simulation software, etc.
I'd suggest any early 80's or later text on system or CPU architecture.
Patterson does a reasonable treatment of the subject, despite it
not being his principle focus. You could go earlier, I suppose, and
look at some of Cray's earlier work, and you could do a literature
search of "Harvard Architecture". That would make for a good start.
Opinions and vague handwaving won't do for me
anymore, sorry.
Could you please take this to one of the architecture groups? It
really doesn't seem to belong here.
Best,
Chris
--
Chris Kennedy
chris(a)mainecoon.com
http://www.mainecoon.com
PGP fingerprint: 4E99 10B6 7253 B048 6685 6CBC 55E1 20A3 108D AB97