It seems the chip registers are different on a Mobility X1600.

rovclock -i should show the correct GPU and memory clock frequency (more or less closely, depending if it found the reference clock in the video BIOS) and
I think <code>Core: 0.19 MHz, Mem: 0.0 MHz </code>is far away from the correct ...

The program doesn't even start in your case. Otherwise at least the banner would be printed. Maybe the partition where rovclock resides is mounted with the "noexec" option?

Seems very nice app, and quite useful for people owning laptops...just for undervoltage....

But the problem is that i cannot even run it...when i try it (as root) it keeps saying:
titan rovclock-0.6c # ./rovclock -i
bash: ./rovclock: Permission denied


Is the rovclock binary executable? Run ls ...

First, I've to say I'm far away from beeing a GPU specialist. This program was born because I wanted one and there was none :)
I got all information from some .h header files and code pieces, so it isn't perfekt. Especially the Mobile versions are sometimes a problem.

To Powerplay: It is far ...

8rdavcore 0.5.5 was a userspace ATXP1 driver. Since there's now a ATXP1 module for the kernel the old cold isn't required any more. Maybe when I get the time I'll finish the successor of 8rdavcore, which will run on linux.

@Jinidog: What's your Boot-FSB and your lowest value?

@Jase: cpufreq should update /proc/cpuinfo...hm. The "Detected on..." message was removed. Also they changed somewhere between 2.6.11 and 2.6.12-13 the sysfs-interface ("warning: initialization from incompatible pointer type"...not good), so it ...

The BIOS doesn't matter. Can you please post and enable cpufreq debugging in kernel to check messages?

Are you sure it isn't a PS/2-Serial adapter for a mouse? If yes, it is not a real 'adapter' which translates PS/2 to serial, this is done by the mouse, which detects if it is connected to a serial port or a PS/2 port.

You can connect a terminal/console to the serial port, just add something like ...

ravloony wrote:ok, really stupid question, but where should i put the ebuild in my overlay folder? media-gfx maybe? Does it even matter?

I put it in sys-apps, but I think it doesn't matter on your local overlay. It seems there are now enough reports that it works, so I can submit the ebuild

Some mobility revisions seems to have a different register access method, I'll work on a update for rovclock.

IIRC the "Intel Pentium 4 clock modulation" does not adjust the core voltage, so it can't be compared with Speedstep, with reduces the multiplier and voltage to save power.
The clock ...

WareKala wrote:Only one complaint: rovclock still says it's version 0.6b

Ups, should release a new version to fix this?

Yes, already did it The detection routines are only a quick hack until I have more time to write something better.

http://www.hasw.net/linux/rovclock-0.6c.ebuild
http://www.hasw.net/linux/rovclock-0.6c.tar.bz2

Can you please send me the output of 'lspci -vv' (PM or hasw@hasw.net)?

Which version of the ATXP1 module are you using? Are you using the kernel patch? It should be fixed, otherwise it
doesn't cleanly work with 2.6.12. Also the i2c-vid-vrm90.patch needs to be applied.

Can you please PM or mail me:


grep I2C kernelsource/.config
grep SENSORS kernelsource/.config ...

Now added more memory timings: http://www.hasw.net/linux/rovclock-0.6b.ebuild .


hasw@hasw ~ $ sudo /usr/sbin/rovclock -i
Radeon overclock 0.6b by Hasw (hasw@hasw.net)

Found ATI card on 01:00, device id: 0x4e44
I/O base address: 0x9000
Video BIOS shadow found @ 0xc0000
Reference clock from BIOS ...

I can change tWR and tCAS one unit down, other changes doesn't work. There are many other timings which maybe working better to change.
I'll add them if I've found out where they are stored.

I've now added some memory timings in version 0.6a. Use with care, better login via ssh to make changes because it's possible that it corrupts your screen.

http://www.hasw.net/linux/rovclock-0.6a.ebuild
http://www.hasw.net/linux/rovclock-0.6a.tar.bz2

Update: There's now an ebuild available: http://www.hasw.net/linux/rovclock-0.5b.ebuild

Using version 0.5a works, but it only detects the card. When calculating the clocks it throws out a "Gleitkomma-Ausnahme"
Here is my output:

Radeon overclock 0.5a by Hasw (hasw@hasw.net)

Found ATI card on 01:28, device id: 0x4e44
I/O base address: 0xfffffffc



It doesn't detect the right PCI ...

@TheRealElch: I know why, because it's the 6th device (currently it only checks the usual first device on the AGP bus). What board/card do you have?

EDIT: I updated to version 0.5a, which uses the information from /proc/bus/pci/devices. This should work better.

Nah, AGP voltage does 2 things:
1 ...

After hardware-modding the card. I don't think that increasing the AGP bus voltage helps a bit in this case. Maybe if you overclock the AGP bus, but not when overclocking the GPU core.

racoontje wrote:/me kindly asks for an ebuild

Have never written one before. I'll try it this afternoon, have to read the howtos first

Mostly RAM on this cards are more limitated than the GPU. On my card the RAM goes from 280 up to 310, the GPU up to 380. When I increase the voltage, it reaches 440/350

Sorry, found the bug. Has only searched bus 1...

Version 0.4b available: http://www.hasw.net/linux/rovclock-0.4b.tar.bz2

Ok, it's on bus 3. I updated the program (0.4a) to search from bus 1 to 9, should work now.