-
Notifications
You must be signed in to change notification settings - Fork 7
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
cuda_plot keeps GPU x open when only GPU y is selected #29
Comments
More info: a |
Yeah I've seen this with many CUDA applications before, the driver likes to use GPU 0 always for no apparent reason... |
I'm not using device 0 on purpose... it's the driver doing it internally. |
The first thing I do in the code is |
Maybe it's harmless? I was having trouble pinning down a solid benchmark result that showed any penalty from having that open, unused handle to the other GPU. I wonder if you can do cudaSetValidDevices before anything else to exclude the non-selected GPU(s)? |
I think that function just remaps the integers, which I can use to simplify the code but that's it. |
I was able to "solve" this "issue" by setting CUDA_VISIBLE_DEVICES in the environment before launching cuda_plot. I don't even need to use the -g flag anymore. |
good to know, thx |
When I select e.g. CUDA device 1 with e.g.
-g 1
, I can see innvtop
thatcuda_plot
keeps a process open on CUDA device 0. I'm not sure what impact this has, if any, but I can see some undesirable RMA innumatop
and this is the most likely explanation in my case. I think it would be better ifcuda_plot
completely disengaged the CUDA device(s) not selected with-g
.The text was updated successfully, but these errors were encountered: