I have a GT710 card on my "other" computer. I am running a stock Seti system.

I understand it won't process as fast as my GTX750Ti cards :) But, I got to looking at the TechPowerup GPU-Z graph and it is pretty saw tooth like (69%-99%). This while processing SOG type data.

I have played with increasing the available CPU to 1 (app_config.xml). I have played with adding -hp to the command line (mb*sog.txt). I have tried using the "middle grade" and "top end" NV parameters listed.

Nothing seems to smooth out the gpu load so that it is crunching patiently at 98-99%. What am I missing?

Thank you,
Tom

---

A proud member of the OFA (Old Farts Association).

Being a lower end GPU, the display itself might be a factor (if being used), though most likely IMO the substantial driver bloat could have some impact, in particular the hidden network streaming and telemetry components that have been introduced relatively recently. These can be disabled via services, and the program 'autoruns' (Google nvidia autoruns telemetry for a guide). The system looks to be capable otherwise, so not sure I can think of other factors, though I'm sure others will chip in with more parameters if they can help with loading.

---

"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.

Nothing seems to smooth out the gpu load so that it is crunching patiently at 98-99%. What am I missing?

Nothing, it's not unusual for the load to vary depending on how far through the WU it is, and the type of WU (Shortie, VLAR, mid range, and Arecibo or GBT) all affect just how much the GPU is loaded up and how constant that load is.

EDIT- running more than 1 WU at a time will increase the load to close to 100%, and make it close to constant, however with that hardware it will result in significantly less work done per hour than just running 1 WU at a time, particularly with the GBT work.

---

Grant
Darwin NT