« Previous 1 2 3 4
High-Performance Python – Distributed Python
Summary
This is the final article in the Python series. Python, an amazing language with a huge number of modules is starting to dominate various technical and non-technical areas as the language of choice. I hope these articles have presented some of the more common tools for improving the performance of numerically intense computations. The tools allow you to write code in C/C++ or Fortran and call it from within the Python interpreter. You can also use some of these tools to run OpenMP code that lets you use all available CPU cores. Python code can also be compiled with a just-in-time (JIT) compiler to improve performance by using all of the CPU cores and by running Python code on GPUs. Other tools allow you to run code on GPUs from within Python. Finally are the tools that allow Python to run on distributed environments on top of very high performance network frameworks and the Pythonic tools for running code built with NumPy, pandas, and scikit-learn, although you can also run general Python code. I hope you appreciate the rich variety of tools and how they interoperate.
« Previous 1 2 3 4
Related content
-
High-Performance Python 1
Although Python is a popular language, in the high-performance world, it is not known for being fast. A number of tactics have been employed to make Python faster. We look at three: Numba, Cython, and ctypes.
-
Run One Program at any Scale with Legate
R un Python NumPy code on distributed heterogeneous systems without changing a single line of code .
-
Pandas: Data analysis with Python
The Python Data Analysis Library, or Pandas, is built on top of the fast math library NumPy and makes analysis of large volumes of data an easy and efficient experience. -
Data Analysis with Panda
The Python Data Analysis Library, or Pandas, is built on top of the fast math library NumPy and makes analysis of large volumes of data an easy and efficient experience.
-
HPC Desktop
HPC Desktop is a way to help new users start using HPC .