lkml.org 
[lkml]   [1997]   [Jul]   [19]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: OFF-TOPIC Intel CPU dies...
Date
From
Geert Uytterhoeven wrote:
>
> On Fri, 18 Jul 1997, Rogier Wolff wrote:
> > Someone who was quoted wrote:
> >
> > > You didn't do the experiment I suggested:
> > >
> > > Run a 200MHz-rated CPU at 75/100MHz, and a 75/100MHz-rated CPU at 200MHz.
> >
> > I think Intel chips are speced for 50-100% of their rated speed.
> > i.e. you're allowed to run a 200MHz CPU at 100MHz if you want too.
> >
> > On the other hand, they will NOT blow up at lower speeds. Clock
> > multiplying may become unreliable at lower speeds, but at a multiplier
> > of 1, that too should be OK.

> But most CPUs are not `static designs'. This means that the internal
> registers and memory need a sufficiently high clock to refresh their
> contents, cfr. refresh cycles on DRAM.

Correct. That is probably why Intel specifies a minimum clock rate for
their chips.

I just looked up the spec for the Pentium/mmx processors:

Max Bus/Core Min Bus/Core
Frequency (MHz) Frequency (MHz)
66/200 33/100
66/166 33/83
66/233 33/117

The "divide by 32 on power-save" is not allowed according to Intel
specs.

The above table is almost literally from the Intel documentation.
(I skipped the third line which says that no mmx chips run at
twice the bus speed, the (get this!) -=default=- ...)

Roger.


\
 
 \ /
  Last update: 2005-03-22 13:39    [W:0.043 / U:1.792 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site