Hi all,

I have 2 GPUs in my pc, a 3070 which also drives the display, and a 3080.
Whenever rosetta is not running, all is fine, but whenever rosetta runs, only the 3080 is being used
by other GPU boinc projects.

Any ideas what how this is caused and how to fix it?


Thanks!

With your systems hidden only a Wild Arse Guess is possible.

Most likely you need to make use of app_config files for each of your GPU projects to reserve a CPU core/thread to support each running GPU application, or just limit the number of Cores/Threads Rosetta can use so there are spare threads to support all running GPU applications.

---

Grant
Darwin NT

Never mind. I fixed it.

I set the rosetta app_config.xml to run less instances than the available cpus.

Curious that this only happens with rosetta though.

It probable due to combination of large work cache in your BOINC setting + short deadlines for R@H WUs (R@H server side settings).
It can drive BOINC into "panic" (high priority mode) - it allocate all CPU resources to a single project in try to avoid missing deadline.
Including CPU core(s) allocated for GPU support.

Its a stupid design decision(because it greatly decrease total performance by cut down of all GPU computations) but it have been this way in BOINC scheduler for years.

Possible workarounds for this
1 - reduce cache size setting or/and abort excessive WUs from a "hoarding" project in BOINC WUs queue.
2 - use of app_config.xml to limit max number of running instances for one project