Skip to content
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

[GPU Acceleration] Validate AMD GPU usage and evaluate acceleration #2836

Open
dpascualhe opened this issue Nov 5, 2024 · 0 comments
Open
Assignees

Comments

@dpascualhe
Copy link
Collaborator

The initial task is to validate whether an AMD GPU can function similarly to Intel cards by using the appropriate DRI path. To test this:

  • GPU acceleration:
docker run --rm -it --device /dev/dri -e DRI_NAME=<AMD card ID> -p 7164:7164 -p 6080:6080 -p 1108:1108 -p 7163:7163 jderobot/robotics-backend
  • CPU only:
docker run --rm -it -p 7164:7164 -p 6080:6080 -p 1108:1108 -p 7163:7163 jderobot/robotics-backend

We aim to capture RTF (Real-Time Factor) and CPU/GPU usage metrics. (@dduro2020)

Next, we can explore using ROCm to determine if it provides further improvements in GPU acceleration. For more details, refer to the ROCm Docker Containers Guide.

@dpascualhe dpascualhe self-assigned this Nov 5, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant