Hi guys,
so after recently I've fried 2 nVidia GPUs 'cause of the "heat-sink fail"...decided that on GPU powered machines I have to run Tthrottle not to go it again...sadly, GT8500 & GT220 are as dead as a rock now, but will have some extra coolers if someone needs them?!

So my desktops on Win also got their Tthrottle, like laptops did...put the Tjunc on 90% & let them crunch away! ;)
But more importantly, GPUs only get to go 100°C...even though their Tjunc is so much higher (around 130°C)!

On 2x linux machines I lack that program...& wouldn't want to fry another card by a simple heat-sink fail...so if anyone got some ideas & experiences with some program like Tthrottle which limits % of CPU on BOINC - especially on GPUs...I'd appreciate the input!

thanks,
;)

---

non-profit org. Play4Life in Zagreb, Croatia, EU

Fred's a pretty great guy to talk to, have you asked him about the possibility?

---

"Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions.

This could possibly be something to look into: https://en.wikipedia.org/wiki/Lm_sensors

It may take some experimentation to get it to poll the GPU for its temp so that when a certain temp is reached, a specified action takes place, but that's probably a pretty good starting point is being able to find out what the temps are in the first place.

---

Linux laptop:
record uptime: 1511d 20h 19m (ended due to the power brick giving-up)

Fred's a pretty great guy to talk to, have you asked him about the possibility?

He said NO, for now:
http://efmer.com/forum/index.php?topic=1261.0
:/

---

non-profit org. Play4Life in Zagreb, Croatia, EU

nvidia-settings can set clock up/down for GPU and its memory.
You have to enable cool-bits.

Open a Terminal and type,

cd /etc/X11
sudo nvidia-xconfig --cool-bits=28


This will take effect after a restart.

Then launch nvidia-settings and you have an option to tune up/down all youg nvidia gpu's.

The bit values are explained in many places. I copied this one from somewhere.

The Coolbits value is the sum of its component bits in the binary numeral system. The component bits are:
1 (bit 0) - Enables overclocking of older (pre-Fermi) cores on the Clock Frequencies page in nvidia-settings.
2 (bit 1) - When this bit is set, the driver will "attempt to initialize SLI when using GPUs with different amounts of video memory".
4 (bit 2) - Enables manual configuration of GPU fan speed on the Thermal Monitor page in nvidia-settings.
8 (bit 3) - Enables overclocking of Fermi and newer cores on the PowerMizer page in nvidia-settings. Available since version 337.12.[1]
16 (bit 4) - Enables overvoltage of Fermi and newer cores using nvidia-settings CLI options. Available since version 346.16.[2]
To enable multiple features, add the Coolbits values together. For example, to enable overclocking and overvoltage of Fermi cores, set Option "Coolbits" "24".

---

To overcome Heisenbergs:
"You can't always get what you want / but if you try sometimes you just might find / you get what you need." -- Rolling Stones

thx, but can it be configured to automatically under-clock nVIDIA chip if the temp goes too high?!

---

non-profit org. Play4Life in Zagreb, Croatia, EU

thx, but can it be configured to automatically under-clock nVIDIA chip if the temp goes too high?!

You could probably put a simple script together that uses a combination of lm_sensors to poll for temps and then uses nvidia-config to downclock.. or tell BOINC to suspend for 30-60 seconds.

Personally, I would set it up to be a cron job that runs every 1 minute, polls for temps, then acts accordingly. It will take some trial-and-error, and a bit of duct tape and bubblegum, but it shouldn't be too difficult to do with a few .sh scripts and a cronjob.

---

Linux laptop:
record uptime: 1511d 20h 19m (ended due to the power brick giving-up)

thx, but can it be configured to automatically under-clock nVIDIA chip if the temp goes too high?!

You could probably put a simple script together that uses a combination of lm_sensors to poll for temps and then uses nvidia-config to downclock.. or tell BOINC to suspend for 30-60 seconds.

Personally, I would set it up to be a cron job that runs every 1 minute, polls for temps, then acts accordingly. It will take some trial-and-error, and a bit of duct tape and bubblegum, but it shouldn't be too difficult to do with a few .sh scripts and a cronjob.

Haven't done some scripts like that from high-school, some 20y ago... :/

---

non-profit org. Play4Life in Zagreb, Croatia, EU