uxlfoundation / oneCCLLinks
oneAPI Collective Communications Library (oneCCL)
☆245Updated this week
Alternatives and similar repositories for oneCCL
Users that are interested in oneCCL are comparing it to the libraries listed below
Sorting:
- Unified Collective Communication Library☆276Updated this week
- ROCm Communication Collectives Library (RCCL)☆389Updated last week
- rocSHMEM intra-kernel networking runtime for AMD dGPUs on the ROCm platform.☆121Updated this week
- oneCCL Bindings for Pytorch*☆102Updated 2 months ago
- Bandwidth test for ROCm☆66Updated last week
- [DEPRECATED] Moved to ROCm/rocm-libraries repo☆253Updated last week
- RCCL Performance Benchmark Tests☆75Updated this week
- Magnum IO community repo☆100Updated 2 months ago
- ☆376Updated last year
- Profiling Tools Interfaces for GPU (PTI for GPU) is a set of Getting Started Documentation and Tools Library to start performance analysi…☆248Updated 2 weeks ago
- oneAPI Level Zero Conformance & Performance test content☆57Updated last week
- OpenAI Triton backend for Intel® GPUs☆212Updated this week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆425Updated this week
- PArametrized Recommendation and Ai Model benchmark is a repository for development of numerous uBenchmarks as well as end to end nets for…☆153Updated last week
- ☆63Updated 10 months ago
- RDMA and SHARP plugins for nccl library☆210Updated this week
- SYCL* Templates for Linear Algebra (SYCL*TLA) - SYCL based CUTLASS implementation for Intel GPUs☆41Updated this week
- A GPU benchmark tool for evaluating GPUs and CPUs on mixed operational intensity kernels (CUDA, OpenCL, HIP, SYCL, OpenMP)☆424Updated 9 months ago
- [DEPRECATED] Moved to ROCm/rocm-systems repo☆166Updated last week
- A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")☆357Updated last week
- STREAM, for lots of devices written in many programming models☆350Updated last month
- Microsoft Collective Communication Library☆367Updated 2 years ago
- A tool for bandwidth measurements on NVIDIA GPUs.☆550Updated 6 months ago
- NCCL Profiling Kit☆145Updated last year
- pytorch ucc plugin☆23Updated 4 years ago
- NCCL Fast Socket is a transport layer plugin to improve NCCL collective communication performance on Google Cloud.☆121Updated last year
- CUDA Kernel Benchmarking Library☆742Updated last week
- Assembler for NVIDIA Volta and Turing GPUs☆230Updated 3 years ago
- A hierarchical collective communications library with portable optimizations☆36Updated 10 months ago
- TransferBench is a utility capable of benchmarking simultaneous copies between user-specified devices (CPUs/GPUs)☆47Updated 2 weeks ago