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

npvtx-nvidia-cuda #9

Open
gnzlbg opened this issue Oct 5, 2018 · 2 comments
Open

npvtx-nvidia-cuda #9

gnzlbg opened this issue Oct 5, 2018 · 2 comments

Comments

@gnzlbg
Copy link
Contributor

gnzlbg commented Oct 5, 2018

I only see nvptx64-nvidia-cuda as a supported target, is it also possible to use rust-ptx-builder from a 32-bit host ? (e.g. i686-unknown-linux-gnu or i686-apple-darwin ?)

@denzp
Copy link
Owner

denzp commented Oct 5, 2018

There is no technical limitation for that, simply I didn't find enough energy to support them both.
Choosing a main supported target, I considered a fact that CUDA and HPC systems usually operate with big amounts of data, so there is no serious chance of running them on a 32-bit host OS.

I'm not sure how can we automatically distinguish between 32-bit and 64-bit target from build.rs script. I think it only can get info about host target, which can differ from actual target in case of cross-compilation.

So if we decide to support both targets, I think we will have to go with manual specification the expected target.

@gnzlbg
Copy link
Contributor Author

gnzlbg commented Oct 8, 2018

I think it only can get info about host target, which can differ from actual target in case of cross-compilation.

Inside a build script, HOST is the triple of the system in which compilation is happening, and TARGET is the triple of the system being actually target.

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

2 participants