muriloboratto / NCCLLinks
Sample examples of how to call collective operation functions on multi-GPU environments. A simple example of using broadcast, reduce, allGather, reduceScatter and sendRecv operations.
☆34Updated 2 years ago
Alternatives and similar repositories for NCCL
Users that are interested in NCCL are comparing it to the libraries listed below
Sorting:
- Matrix Multiply-Accumulate with CUDA and WMMA( Tensor Core)☆139Updated 5 years ago
- Efficient Distributed GPU Programming for Exascale, an SC/ISC Tutorial☆295Updated this week
- Instructions, Docker images, and examples for Nsight Compute and Nsight Systems☆131Updated 5 years ago
- An extension library of WMMA API (Tensor Core API)☆103Updated last year
- ☆136Updated 3 months ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆183Updated 7 months ago
- Fast GPU based tensor core reductions☆13Updated 2 years ago
- Examples of CUDA implementations by Cutlass CuTe☆222Updated 2 months ago
- Optimize GEMM with tensorcore step by step☆32Updated last year
- A lightweight design for computation-communication overlap.☆160Updated last week
- ☆101Updated 3 months ago
- ☆27Updated 6 months ago
- CUDA Matrix Multiplication Optimization☆218Updated last year
- CUTLASS and CuTe Examples☆72Updated last month
- Sample Codes using NVSHMEM on Multi-GPU☆24Updated 2 years ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆107Updated 3 months ago
- Benchmark code for the "Online normalizer calculation for softmax" paper☆98Updated 7 years ago
- Training material for Nsight developer tools☆163Updated last year
- ☆106Updated last year
- NCCL Examples from Official NVIDIA NCCL Developer Guide.☆18Updated 7 years ago
- ☆131Updated 8 months ago
- Chimera: bidirectional pipeline parallelism for efficiently training large-scale models.☆66Updated 5 months ago
- ☆50Updated 6 years ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆40Updated 6 months ago
- Dissecting NVIDIA GPU Architecture☆104Updated 3 years ago
- rocSHMEM intra-kernel networking runtime for AMD dGPUs on the ROCm platform.☆100Updated this week
- ☆98Updated 11 months ago
- ☆111Updated 8 months ago
- A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores☆53Updated last year
- Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.☆89Updated 2 years ago