Lance Cummings wrote:

> On Sun, 01 Mar 1998 07:51:00 -0500, Bill Cohane <[log in to unmask]> wrote:
>
> > At 13:43 01-03-98 +0900, Lance Cummings <[log in to unmask]> wrote:
> > >Perhaps you can tell me if the ability of ultra to double the clock
> > >rate means that ultra would probably support higher bus speeds...
> > >such as 75 mhz or 83 mhz.
> >...............CUT..................



> Finally, I think that any speed increase from overclocking would be

> > useless if it came with corrupted data or system instability. Better
> > to wait 6 months (or whatever) for the upcomming 100 mhz bus
> > motherboards where the PCI bus should be run asynchronously from the
> > system bus, i.e. at the normal 33 mhz. That would make this whole
> > speculation mute.

I don't know exactly how is going to work but why would you have the bus
running at 100MHz and the PCI bus at 33MHz? It defeats the purpose of the
whole exercise. The PCI bus will have to run at 50MHz to see an improvement
otherwise what are you actually improving the bus speed for? To access RAM
only? Don't think so. As far as the drives, they wont run any faster, what
will be faster is the PCI bus. When the CPU asks for a read, the request will
go across the PCI bus (from the CPU to the PCI card) at 41.5MHz on a 83MHZ
bus. The card will then do it's thing and ask the drive for the info,once the
request reaches the drive the speed is at the drives mercy. When the drive
puts the data back on the bus it picks up speed again on it's way to the card
which will then send the data across the bus at 41.5 to the CPU. This may not
be exactly like this but the principal is there. Corrections are welcome.

> True enough about the corrupted data or instability.  I couldn't agree
> more.  But waiting for the 100 mhz bus mobo's may involve both quite
> a wait and quite a bit of additional cost, yes?

I have clients that are waiting for the final whatever, they still have 386s.
<G>

HTH

Jose