High Performance Python; Improving Code Efficiency and Performance

This hands-on workshop will teach you how to profile and optimize Python workflows on computing devices ranging from personal computers to high performance computing clusters. Highlights include: Code profiling to identify bottlenecks Employing Numpy for vectorized operations Using Numba to compile Python code for improved speed Deploying Dask on Yale's HPC clusters to make use of distributed resources Accelerating Python code via GPUs with `cupy` and `numba-cuda` Training materials are available at https://github.com/ycrc/high_performance_python?tab=readme-ov-file#high_performance_python