NVIDIA/nvshmem

NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process communication and coordination overheads by allowing programmers to perform one-sided communication from within CUDA kernels and on CUDA streams.

55
/ 100
Established

This is a parallel programming interface for NVIDIA GPUs that helps developers of high-performance computing applications to build programs that communicate efficiently across multiple GPUs. It allows direct, one-sided communication between GPUs, reducing the overhead typically associated with data sharing in large-scale simulations or machine learning models. HPC developers or researchers working with GPU clusters will find this useful for optimizing their multi-GPU applications.

477 stars.

Use this if you are developing high-performance applications on NVIDIA GPU clusters and need to optimize communication between GPUs for speed and efficiency.

Not ideal if you are working with single-GPU applications or do not require fine-grained control over GPU communication.

GPU programming High-performance computing Parallel programming Multi-GPU systems Scientific computing
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 20 / 25

How are scores calculated?

Stars

477

Forks

65

Language

C++

License

Last pushed

Mar 10, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVIDIA/nvshmem"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.