Ok searching the web i finally came to this conclusion :
Under linux a cool'n'quiet capable cpu will always have the fid and vid flags present when doing a "cat /proc/cpuinfo", either in the flags or "power management" line. So that's a pretty easy way to tell that one cpu does not support it.
On the other hand this test isn't sufficient to tell that one cpu does have the cool'n'quiet feature, only that it has some power management capabilities.
So my sempron 2800+ manila does not indeed support cool'n'quiet, since it doesn't have those fid and vid flags.
Trying to set power management i also get this message :
Nov 13 22:34:58 sarge kernel: powernow-k8: Power state transitions not supported
The good thing is i came accross a very interesting gentoo topic about undervolting, here are some quotes :
http://forums.gentoo.org/viewtopic-p-31 ... 27[quote]I don't really want to go to very low voltages with a rev E CPU (Manchester core is rev E, as is Venice and other recent cores)... There are issues with those about damaged memory controllers (
http://www.xtremesystems.org/forums/sho ... ge=1&pp=25) when there is too much a difference between Vtt (half Vddr) and Vcore. Normally it happens when you use too high a voltage for the RAM (3V or more, which is used to get better o/c with some kinds of RAM), but I guess it could happen with too low Vcore too.
It's supposed to be safe when abs(Vtt - Vcore) < 0.35 V, so with default 2.5 V Vddr (so 1.25 V Vtt), it is safe for Vcore as low as 0.9 V, but given the price of the CPU, I prefer to leave a little more margin... This might be the reason of the limited vid range btw.[/quote]
http://forums.gentoo.org/viewtopic-p-31 ... [quote]Not necessarily. If you look at my post above with the X2, you will see it has a limited range of valid VIDs (1100 to 1400 mV). Your Opteron probably has the same limits, and if it's the case, the CPU will refuse the "forbidden" voltage, and either do nothing, or switch to the maximum allowed (ie 1400 mV).
Some motherboards may be able to go higher by forcing the values of VID pins on the VRM controller chip (overriding what the CPU indicates), or by inserting an offset (like +100 mV or +5% or whatever) in the voltage regulation, but both of those need specific hardware. If your motherboard can't do it, there's no way to do it in software.[/quote]
So i tried this program (from the gentoo topic) :
http://www.net-42.eu.org/vid-changer/a64-vid.c
[src 0]# grep -i </usr/src/linux-2.6.18.2/.config msr
CONFIG_X86_MSR=m
[src 0]# modprobe msr
Nov 13 22:43:39 sarge udev[17572]: creating device node '/dev/cpu/0/msr'
[src 1]# /usr/src/a64-vid 1400
Maximum freq. : 0x00 (800 MHz)
Startup freq. : 0x00 (800 MHz)
Current freq. : 0x00 (800 MHz)
Voltage range : 0x1e (800 mV) [No low limit] -> 0x00 (1550 mV) [No high limit]
Startup voltage : 0x00 (1550 mV)
Current voltage : 0x00 (1550 mV)
Target voltage : 0x06 (1400 mV)
New control MSR : 0x0000000000010600
New voltage : 0x20 (750 mV) [FAILURE]
So setting the volting on the sempron 2800+ via a64-vid doesn't work eather (can't wait to try this on another cpu). Of course since basicly the program "asks" the cpu for a voltage change via the msr registers that's not a big surprise.
That's probably for the same reason that the AMSNF3-VSTA BIOS doesn't present an option to change the voltage, because the cpu states it would not allow it.
As explained in the gentoo topic some other MB with more advanced overclocking would certainly have been able to undervolt this sempron ( without asking permission ).
Good to know also ( not clearly specified in the documentation ), the secondary IDE port seems pretty limited. I have to test it but i can already tell it doesn't support the 80 wide cable for the most recent UDMA transfers.
EDIT on Tue, 14 Nov 2006 19:31:47 +0100 : Ok i tested it more thoroughly, i was wrong, everything is fine, both ide ports.
P.S some notes for the linux support : ( net : module forcedeth, no Realtek chip contrary to the asrock description; sata : sata_nv; ide : amd74xx; audio : its an usb device! i have some sound with snd-usb-audio but it's bad )
EDIT on Tue, 14 Nov 2006 19:31:47 +0100 :
CONFIG_SENSORS_W83627EHF=m; from the doc : "Only fan and temperature inputs are supported at the moment, while the chip does much more than that."
so far the first MB i have that seems to work without needing to pass any noapic, nolapic or nodma and such in the boot command line. Very well supported except for the sound but it's a new chip so let's see in a couple of months
Is the fan to the sempron fairly quiet?
