NVIDIA / gdrcopy
A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology
☆854Updated 2 months ago
Related projects: ⓘ
- ☆306Updated 4 months ago
- CUDA Kernel Benchmarking Library☆481Updated 3 months ago
- Examples demonstrating available options to program multiple GPUs in a single node or a cluster☆528Updated last month
- Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)☆1,115Updated this week
- ☆464Updated this week
- NCCL Tests☆819Updated last month
- ROCm Communication Collectives Library (RCCL)☆250Updated this week
- A tool for bandwidth measurements on NVIDIA GPUs.☆284Updated 3 months ago
- A single-header C++ library for simplifying the use of CUDA Runtime Compilation (NVRTC).☆513Updated 3 months ago
- Unified Collective Communication Library☆190Updated 2 weeks ago
- Library for specialized dense and sparse matrix operations, and deep learning primitives.☆839Updated this week
- Open Fabric Interfaces☆549Updated this week
- Repository for nvCOMP docs and examples. nvCOMP is a library for fast lossless compression/decompression on the GPU that can be downloade…☆555Updated last week
- RAPIDS Memory Manager☆472Updated this week
- [ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl☆1,669Updated 11 months ago
- oneAPI Collective Communications Library (oneCCL)☆189Updated 3 weeks ago
- The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resou…☆279Updated last week
- A GPU benchmark tool for evaluating GPUs and CPUs on mixed operational intensity kernels (CUDA, OpenCL, HIP, SYCL, OpenMP)☆352Updated last month
- Infiniband Verbs Performance Tests☆583Updated this week
- RDMA and SHARP plugins for nccl library☆153Updated last month
- CUDA Core Compute Libraries☆1,132Updated this week
- oneAPI Math Kernel Library (oneMKL) Interfaces☆606Updated last week
- An unofficial cuda assembler, for all generations of SASS, hopefully ：）☆388Updated last year
- STREAM, for lots of devices written in many programming models☆323Updated 3 weeks ago
- Microsoft Collective Communication Library☆304Updated 11 months ago
- Hardware locality (hwloc)☆563Updated this week
- This is a plugin which lets EC2 developers use libfabric as network provider while running NCCL applications.☆137Updated this week
- Assembler for NVIDIA Volta and Turing GPUs☆195Updated 2 years ago
- ☆215Updated 3 weeks ago
- NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs☆379Updated 2 weeks ago