Learning Heterogeneous Programming

Structure

workspace/
├── cuda_dev/
│   ├── professional_cuda_c_programing/
│   ├── SGEMM/    # How to Optimize a CUDA Matmul
│   ├── ThMoPPO/  # Theory and Method of Program Performance Optimization
├── opencl_dev/
│   ├── cxx
│   │   ├── heterogeneous_computing_with_opencl/
│   ├── python
└── README.md

References

• Professional CUDA C Programming. John Cheng, Max Grossman, Ty McKercher.
• Theory and Method of Program Performance Optimization. Han Lin, Gao Wei
• https://siboehm.com/articles/22/CUDA-MMM
• https://github.com/siboehm/SGEMM_CUDA
• https://www.bookstack.cn/books/Heterogeneous-Computing-with-OpenCL-2.0