Finding the Compute Compatibility Score for your GPU #451
Unanswered
tgraupmann
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
I'm on
07 Milestone Project 1: 🍔👁 Food Vision Big™
https://github.com/mrdbourke/tensorflow-deep-learning/blob/main/07_food_vision_milestone_project_1.ipynb
and watching the content on compute compatibility scores.
https://developer.nvidia.com/cuda-gpus#compute
Eventually I plan on training/predicting on models outside of Google Collab and try to run it locally on my desktop.
I have the
Nvidia Geforce RTX 2070 Super
.https://www.nvidia.com/en-me/geforce/graphics-cards/rtx-2070-super/
Looking at the data here, it seems like the 2070 is in the same group
Turing (CUDA 10 and later)
as the Tesla T4 with a compute compatibility score of7.5
.https://arnon.dk/matching-sm-architectures-arch-and-gencode-for-various-nvidia-cards/
Is that the correct score?
There's a nice table here but it doesn't list all the cards.
https://gist.github.com/standaloneSA/99788f30466516dbcc00338b36ad5acf
Beta Was this translation helpful? Give feedback.
All reactions