merthidayetoglu / HiCCL
A hierarchical collective communications library with portable optimizations
☆32Updated 3 months ago
Alternatives and similar repositories for HiCCL:
Users that are interested in HiCCL are comparing it to the libraries listed below
- A Micro-benchmarking Tool for HPC Networks☆26Updated 2 months ago
- NCCL Profiling Kit☆127Updated 8 months ago
- Pytorch process group third-party plugin for UCC☆20Updated 11 months ago
- rocSHMEM intra-kernel networking runtime for AMD dGPUs on the ROCm platform.☆63Updated this week
- Multi-GPU communication profiler and visualizer☆26Updated 9 months ago
- Tartan: Evaluating Modern GPU Interconnect via a Multi-GPU Benchmark Suite☆64Updated 6 years ago
- ☆75Updated 2 years ago
- Synthesizer for optimal collective communication algorithms☆106Updated 11 months ago
- ☆91Updated 11 months ago
- Implementation of TSM2L and TSM2R -- High-Performance Tall-and-Skinny Matrix-Matrix Multiplication Algorithms for CUDA☆32Updated 4 years ago
- GPUDirect Async support for IB Verbs☆105Updated 2 years ago
- RCCL Performance Benchmark Tests☆60Updated last week
- 🎃 GPU load-balancing library for regular and irregular computations.☆62Updated 9 months ago
- Thunder Research Group's Collective Communication Library☆34Updated 10 months ago
- Microsoft Collective Communication Library☆60Updated 4 months ago
- TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches☆72Updated last year
- ☆23Updated 3 years ago
- ☆20Updated last month
- GPU Performance Advisor☆64Updated 2 years ago
- Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.☆86Updated 2 years ago
- ☆87Updated 2 weeks ago
- ☆23Updated 2 years ago
- Supplemental materials for The ASPLOS 2025 / EuroSys 2025 Contest on Intra-Operator Parallelism for Distributed Deep Learning☆23Updated 3 months ago
- GVProf: A Value Profiler for GPU-based Clusters☆49Updated 11 months ago
- Matrix multiplication on GPUs for matrices stored on a CPU. Similar to cublasXt, but ported to both NVIDIA and AMD GPUs.☆31Updated 3 months ago
- Unified Collective Communication Library☆237Updated this week
- NCCL Examples from Official NVIDIA NCCL Developer Guide.☆17Updated 6 years ago
- A pattern-based algorithmic autotuner for graph processing on GPUs.☆30Updated 3 months ago
- NUMA-aware multi-CPU multi-GPU data transfer benchmarks☆22Updated last year
- ☆48Updated 5 years ago