High Performance Python for Scientific Computing
Event Type
Tutorial
Advanced
Algorithms
Intermediate
Programming Systems
TimeSunday, November 13th8:30am - 5pm
Location355-E
DescriptionToday’s HPC mainstream languages and programming models consist mainly of Fortran, C/C++, OpenMP, and MPI. Simple-to-use scripting languages such as Python are being used beyond pre and post processing of data. The learning curve for Python is relatively low, and it is a natural first step for those scientist/domain specialists to dip their proverbial toes into computational science. The burgeoning use of high performance compute platforms as applied to big data analytics and machine learning raises the performance requirements as Python is well used in these areas. Scaling up performance of Python applications is challenging without having to rewrite the application in a native language.
In this tutorial participants will learn about the latest developments and tools for high performance Python for scikit-learn, NumPy/SciPy/Pandas, mpi4py, numba, etc. The audience will learn how to apply low overhead profiling tools to analyze mixed C/C++ and Python applications to detect performance bottlenecks in the code and to pinpoint hotspots as the target for performance tuning. Join us and learn the best known methods, tools, and libraries to get the best performance from your Python application.
In this tutorial participants will learn about the latest developments and tools for high performance Python for scikit-learn, NumPy/SciPy/Pandas, mpi4py, numba, etc. The audience will learn how to apply low overhead profiling tools to analyze mixed C/C++ and Python applications to detect performance bottlenecks in the code and to pinpoint hotspots as the target for performance tuning. Join us and learn the best known methods, tools, and libraries to get the best performance from your Python application.
