Re: IO-APIC on nforce2 [PATCH] + [PATCH] for nmi_debug=1 + [PATCH]for idle=C1halt, 2.6.5

[Craig Bradney]

On Mon, 2004-05-17 at 21:37, Prakash K. Cheemplavam wrote:
> Craig Bradney wrote:
> > On Mon, 2004-05-17 at 17:26, Prakash K. Cheemplavam wrote:
> > 
> >>Hi all,
> >>
> >>I just made an interesting finding and would like to have comments from 
> >>NVidia:
> >>
> >>Chip   Current Value   New Value
> >>C17       1F0FFF01     1F01FF01
> >>C18D      9F0FFF01     9F01FF01
> >>
> >>In fact I have the newer chip revision (lspci says c1), but due to a 
> >>post at Abit Forums I tried to use the value for the older revision on 
> >>my board, and guess what: I never had such low idle temps! I am 
> >>currently even using nvidia binary graphics driver and usually I would 
> >>be having around 49-51°C idle temp, but now it is around 45°C, and it 
> >>was not the first boot (then the mobo usually shows 5°C less). Instead 
> >>the temp steadily fell from >50°C to 45°C.
> >>
> >>(esp @nvidia:) Is there anything evil using the old chip's value for the 
> >>new chip? So far I haven't noticed any bad thing about it. Perhaps some 
> >>daring nforce2 user with the new revision should try as well.
> >>
> > 
> > 
> > Isnt it the case that that change is the one that brings about
> > stability? Was indicated before to be the main causing c1halt crashes.
> 
> Nope, I am changing the 9F to 1F. The "stability byte" was changing the 
> 0F to 01. I am no using 1F01FF01 instead of 9F01FF01. I guess I wasn't 
> clear enough.

And I wasnt looking hard enough at those characters. :) Interesting
find.. Allen.. any comments?

Craig

Attachment: signature.asc
Description: This is a digitally signed message part