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

Support for CUDA-capable GPU with compute capability 4.0 like GTX 1080 #587

Closed
trollichon opened this issue Dec 4, 2020 · 1 comment
Closed
Labels
enhancement New feature or request

Comments

@trollichon
Copy link

Consider support for GTX 1080 and other GPU with compute capability 4.0

The current README.md states that only "GPU with compute capability 5.0" are currently supported. Would it be technically possible to support older GPUs with compute capability 4.0 in future ? If not, could someone give some technical information why this is not possible ?

Thanks all for the great job on cuda and julia.

@trollichon trollichon added the enhancement New feature or request label Dec 4, 2020
@maleadt
Copy link
Member

maleadt commented Dec 4, 2020

A GTX 1080 has compute capability 6.1, so is fully supported. sm_40 is really old, so doesn't seem like a problematic requirement nowadays. And older versions of CUDA.jl do support devices below it.

The reason is that certain CUDA APIs (gemmex) and kernel features (shuffle, certain atomics) are only available on recent hardware, so it simplifies our implementation here.

@maleadt maleadt closed this as completed Dec 4, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants