-
Notifications
You must be signed in to change notification settings - Fork 132
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
an illegal memory access was encountered when I run delaunayrefinement_gpu #378
Comments
The error messages are:
|
It's not immediately clear to me what would cause this. @yishanlu is probably the most familiar with that code, so hopefully he has some insight. |
Unfortunately I am not familiar with the GPU implementation, so I do not have immediate answer for your question. Did you try with the test inputs? Maybe it is caused by your inputs... |
The url link of the test inputs is wrong and returned 404 error. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi Galois Team,
I am trying to run your gpu delaunayrefinement in the master branch but I got "an illegal memory access was encountered".
The command I run:
I use a 500000 nodes list file with the format:
to feed into the delaunaytriangulation in the release-0.5 branch to generate nodes0.5M.ele, nodes0.5M.node, and nodes0.5M.poly files.
Then I use those files to feed into the delaunayrefinement_gpu in the master branch but unfortunately got an illegal memory access bug.
CUDA version: 11.2
NVIDIA GPU: Tesla v100
Compiled with capability 7.0
Could you help with the memory access bug?
Thanks!
Yuxin
The text was updated successfully, but these errors were encountered: