目录
- .github[General] Add issue templates7个月前
- cmake_configRevert "Disable nvshmem4py device APIs to allow for 0.1.3 release with just host features"5个月前
- examplesRename tile reduce7个月前
- nvshmem4pyremove build artifacts5个月前
- perftestibgda_device: Add qpair-specific APIs7个月前
- pkgVersion: 3.4.5-08个月前
- scriptsRestore protected files6个月前
- srcadd newline for CMakeLists.txt5个月前
- .gitattributesFix sync_latency perftest11个月前
- .gitignore[ADMIN] Some cleanup in .gitignore6个月前
- .pre-commit-config.yamlVersion: 3.4.5-08个月前
- CMakeLists.txtMerge main back into devel after RC6个月前
- Compatibility.mdVersion: 3.4.5-08个月前
- License.txtVersion: 3.4.5-08个月前
- README.mdVersion: 3.4.5-08个月前
- changelogVersion: 3.4.5-08个月前
- nvshmem_bootstrap.symVersion: 3.4.5-08个月前
- nvshmem_host.symVersion: 3.4.5-08个月前
- nvshmem_transport.symVersion: 3.4.5-08个月前
邀请码
版权所有：中国计算机学会技术支持：开源发展技术委员会
京ICP备13000930号-9
京公网安备 11010802032778号
NVSHMEM Overview
NVSHMEM™ is a parallel programming interface based on OpenSHMEM that provides efficient and scalable communication for NVIDIA GPU clusters. NVSHMEM creates a global address space for data that spans the memory of multiple GPUs and can be accessed with fine-grained GPU-initiated operations, CPU-initiated operations, and operations on CUDA® streams.
Quick Links
Please see the following public links for information on building and working wih NVSHMEM:
Project Homepage
Release Notes
Installation Guide
Best Practice Guide
API Documentation
Devzone Topic Page
The maintainers of the NVSHMEM project can also be contacted by e-mail at nvshmem@nvidia.com