-
Notifications
You must be signed in to change notification settings - Fork 191
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
Some backprjections/FDK result in an unexpected CUDA error #492
Comments
Could this have something to do with e7ad230 ? |
@tsadakane possibly, that is what I thought, but my preliminary test don't seem to show any mayor change. I just need some time to sit down and print the right things. |
Hi @tsadakane I wonder if this has to do with the particulars of the computer I am running this at, a 4 GPU station. |
I have more or less found the issue, and it resides in the difference between these two enviroments. I need to check what exactly is the breaking one (for tomorrow....) Working:
Not working:
|
Yes, we do.
Yes, we can.
|
In nay case, its still nor clear to me what causes the error. I upgraded the non-working env to cython 3 and that still causes errors. |
Still unsure which geos cause this, but I get "main loop fail" for some geos. If it is a prooblem of the geo being wrong, this should be caugth earlier, otherwise there is a mayor bug somewhere. I wonder in the sizes/ints are being properly passed since the latest changes
The text was updated successfully, but these errors were encountered: