ParCoreLab / CPU-Free-modelLinks
Source code for the CPU-Free model - a fully autonomous execution model for multi-GPU applications that completely excludes the involvement of the CPU beyond the initial kernel launch.
☆20Updated last year
Alternatives and similar repositories for CPU-Free-model
Users that are interested in CPU-Free-model are comparing it to the libraries listed below
Sorting:
- rocSHMEM intra-kernel networking runtime for AMD dGPUs on the ROCm platform.☆100Updated last week
- An extension library of WMMA API (Tensor Core API)☆103Updated last year
- NUMA-aware multi-CPU multi-GPU data transfer benchmarks☆24Updated last year
- ☆106Updated last year
- Matrix Multiply-Accumulate with CUDA and WMMA( Tensor Core)☆139Updated 5 years ago
- Tartan: Evaluating Modern GPU Interconnect via a Multi-GPU Benchmark Suite☆66Updated 6 years ago
- ☆39Updated 5 years ago
- A Top-Down Profiler for GPU Applications☆20Updated last year
- ☆42Updated 3 months ago
- ☆55Updated 3 months ago
- CUDA Flux is a profiler for GPU applications which reports the basic block executions frequencies of compute kernels☆32Updated 4 years ago
- 🎃 GPU load-balancing library for regular and irregular computations.☆62Updated last year
- GVProf: A Value Profiler for GPU-based Clusters☆51Updated last year
- ☆47Updated 5 years ago
- Implementation and analysis of five different GPU based SPMV algorithms in CUDA☆41Updated 6 years ago
- A hierarchical collective communications library with portable optimizations☆36Updated 8 months ago
- A memory profiler for NVIDIA GPUs to explore memory inefficiencies in GPU-accelerated applications.☆25Updated 10 months ago
- ☆50Updated 6 years ago
- Implementation of TSM2L and TSM2R -- High-Performance Tall-and-Skinny Matrix-Matrix Multiplication Algorithms for CUDA☆35Updated 5 years ago
- Multi-GPU communication profiler and visualizer☆31Updated last year
- Matrix multiplication on GPUs for matrices stored on a CPU. Similar to cublasXt, but ported to both NVIDIA and AMD GPUs.☆32Updated 5 months ago
- My notes on various HPC papers.☆22Updated 2 years ago
- Artifacts of EVT ASPLOS'24☆26Updated last year
- ☆81Updated 2 years ago
- ❤️ CUDA/C++ GPU graph analytics simplified.☆31Updated 2 years ago
- Thunder Research Group's Collective Communication Library☆40Updated last month
- GPU Performance Advisor☆66Updated 3 years ago
- End to End steps for adding custom ops in PyTorch.☆23Updated 5 years ago
- Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.☆89Updated 2 years ago
- [DEPRECATED] Moved to ROCm/rocm-systems repo☆162Updated last week