c3sr / comm_scope
NUMA-aware multi-CPU multi-GPU data transfer benchmarks
☆23Updated last year
Alternatives and similar repositories for comm_scope:
Users that are interested in comm_scope are comparing it to the libraries listed below
- ☆43Updated 4 years 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 9 months ago
- rocSHMEM intra-kernel networking runtime for AMD dGPUs on the ROCm platform.☆66Updated this week
- Tartan: Evaluating Modern GPU Interconnect via a Multi-GPU Benchmark Suite☆64Updated 6 years 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
- Implementation and analysis of five different GPU based SPMV algorithms in CUDA☆39Updated 6 years ago
- My notes on various HPC papers.☆22Updated 2 years ago
- An extension library of WMMA API (Tensor Core API)☆93Updated 8 months ago
- Multi-GPU communication profiler and visualizer☆28Updated 9 months ago
- ☆17Updated 5 years ago
- CSR-based SpGEMM on nVidia and AMD GPUs☆45Updated 8 years ago
- Implementation of TSM2L and TSM2R -- High-Performance Tall-and-Skinny Matrix-Matrix Multiplication Algorithms for CUDA☆32Updated 4 years ago
- Multiple 1-stencil implementations using nvidia cuda.☆13Updated 7 years ago
- Efficient SpGEMM on GPU using CUDA and CSR☆51Updated last year
- Source code for the CPU-Free model - a fully autonomous execution model for multi-GPU applications that completely excludes the involveme…☆17Updated 11 months ago
- A GPU benchmark suite for assessing on-chip GPU memory bandwidth☆104Updated 7 years ago
- Performance Prediction Toolkit☆51Updated 3 months ago
- GPU Performance Advisor☆64Updated 2 years ago
- Chai☆43Updated last year
- Advanced Profiling and Analytics for AMD Hardware☆144Updated this week
- ❤️ CUDA/C++ GPU graph analytics simplified.☆31Updated 2 years ago
- Prototype of OpenSHMEM for NVIDIA GPUs, developed as part of DoE Design Forward☆24Updated 6 years ago
- SYCL Benchmark Suite☆64Updated last month
- ☆49Updated 5 years ago
- A tool for generating information about the matrix multiplication instructions in AMD Radeon™ and AMD Instinct™ accelerators☆80Updated this week
- ☆92Updated 11 months ago
- Benchmark for measuring the performance of sparse and irregular memory access.☆76Updated last month
- Subset of BLAS routines optimized for NVIDIA GPUs☆68Updated 2 years ago
- Multi-GPU dynamic scheduler using PGAS style cross-GPU communication☆28Updated last year