ekondis / mixbench
A GPU benchmark tool for evaluating GPUs and CPUs on mixed operational intensity kernels (CUDA, OpenCL, HIP, SYCL, OpenMP)
☆372Updated this week
Alternatives and similar repositories for mixbench:
Users that are interested in mixbench are comparing it to the libraries listed below
- Stretching GPU performance for GEMMs and tensor contractions.☆231Updated this week
- Archived implementation of BLAS using the SYCL open standard. See oneMath for a replacement.☆262Updated this week
- Examples for HIP☆203Updated last month
- CUDA Kernel Benchmarking Library☆547Updated last month
- STREAM, for lots of devices written in many programming models☆325Updated 4 months ago
- ROCm Communication Collectives Library (RCCL)☆289Updated this week
- Next generation BLAS implementation for ROCm platform☆355Updated this week
- Profiling Tools Interfaces for GPU (PTI for GPU) is a set of Getting Started Documentation and Tools Library to start performance analysi…☆213Updated this week
- ROCm Parallel Primitives☆168Updated this week
- A GPU benchmark suite for assessing on-chip GPU memory bandwidth☆104Updated 7 years ago
- A tool which profiles OpenCL devices to find their peak capacities☆424Updated 3 weeks ago
- oneAPI Collective Communications Library (oneCCL)☆218Updated this week
- ☆241Updated this week
- AMD's graph optimization engine.☆196Updated this week
- Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators