Compyle
latest

Contents:

  • An overview
  • Installation
  • Using Compyle
Compyle
  • Docs »
  • Welcome to Compyle’s documentation!
  • Edit on GitHub

Welcome to Compyle’s documentation!¶

Compyle allows users to execute a restricted subset of Python (almost similar to C) on a variety of HPC platforms. Currently we support multi-core CPU execution using Cython, and support GPU devices using OpenCL and CUDA.

You can try Compyle online on a Google Colab notebook.

Contents:

  • An overview
    • Simple example
    • More examples
    • Citing Compyle
  • Installation
    • Installing the bleeding edge
    • Setting up on GNU/Linux
    • Installation with conda on MacOS
    • Possible issues on MacOS
    • Setting up on Windows
    • Setting up OpenCL/CUDA
    • Using the configuration file
  • Using Compyle
    • An overview of functionality
    • Annotating functions
    • JIT transpilation
    • Declaring variables
    • Writing the functions
    • Common parallel algorithms
    • Debugging
    • Abstracting out arrays
    • Choice of backend and configuration
    • Templates
    • Low level functionality

Indices and tables¶

  • Index
  • Module Index
  • Search Page
Next

© Copyright 2018-2021, PySPH Developers Revision e6584827.

Built with Sphinx using a theme provided by Read the Docs.