Skip to content

Conversation

@caugonnet
Copy link

This PR introduces a new version of the MiniWeather benchmark based on the CUDASTF programming model.

CUDASTF is shipped in NVIDIA's CCCL project, and implements task-parallelism as a C++ header only library.

This example shows how to leverage CUDA graphs to hide latencies on small problem sizes, or to scale parallel_for kernels over multiple devices of the same machine (e.g. a DGX platform).

@janciesko
Copy link

Following #20, we might want to use a naming directory structure cpp_$(project_name). In this case project_name is cudastf.

@mrnorman
Copy link
Owner

Sorry for the long delay. I'm still not getting notified of PRs even though I'm "watching" this on github. I'll look at this soon, and thanks so much for submitting it.

@caugonnet
Copy link
Author

caugonnet commented Jan 15, 2025 via email

caugonnet and others added 4 commits January 24, 2025 10:28
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

Successfully merging this pull request may close these issues.

3 participants