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

Compute Capability of Halide #21

Closed
aditya4d1 opened this issue Aug 21, 2012 · 2 comments
Closed

Compute Capability of Halide #21

aditya4d1 opened this issue Aug 21, 2012 · 2 comments

Comments

@aditya4d1
Copy link
Contributor

I am working on CUDA and Halide. I have compiled and ran few examples. When i opened my working directory, i found a file "kernel.ptx". I opened it and found this.

  1. .version 2.0
  2. .target sm_20

Does Halide support only devices with compute capability 2.0??

@abadams
Copy link
Member

abadams commented Aug 24, 2012

I assume sm_20 means we're using shared memory model 2.0, i.e. we have floating point atomics. Perhaps @jrk can clarify. I'm guessing this may change when we update the ptx backend to llvm 3.2

@jrk
Copy link
Member

jrk commented Sep 5, 2012

It requires version 2.0 or greater. It is unlikely to ever support version 1.0, without a strong and explicit demand.

As for the kernel.ptx file, it's a debug log of the generated PTX emitted by the compiler.

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

3 participants