Jump to content

Need Nvidia GPU for CUDA programming / Machine Learning

I have an app that I'm developing that I want to accelerate the machine learning aspect of. I've done CUDA programming before, but that was on my personal desktop and I'm trying to migrate the app to a different system entirely.

I already have the machine for the app set up, all except for the GPU. Currently it's using it's iGPU for display, but I still want an Nvidia card for acceleration.

 

I was looking at the wiki page for comparing GPU gFLOPS, but this is really the only metric I can see that's comparable for ML applications.

Anyone know what I should try going for? Should I be trying to get some RTX card to get Tensor Cores? Do Tensor Cores truly make a difference for ML apps?

Link to comment
Share on other sites

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

×