Python Binding

COMPSs features a binding for Python 2 and 3 applications. The next subsections explain how to program a Python application for COMPSs and a brief overview on how to execute it.

Table of Contents

• Programming Model
  • Task Definition
    • Task Selection
      • Function parameters
      • Tasks within classes
    • Task Parameters
      • Objects
      • Files
      • Directories
      • Collections
      • Collections of files
      • Dictionaries
      • Streams
      • Standard Streams
    • Other Task Parameters
      • Task time out
      • Scheduler hints
      • On failure task behaviour
    • Task Parameters Summary
    • Task Return
    • Other task types
      • Binary decorator
      • OmpSs decorator
      • MPI decorator
      • MPMD MPI decorator
      • I/O decorator
      • COMPSs decorator
      • Multinode decorator
      • HTTP decorator
      • Reduction decorator
      • Container decorator
      • Software decorator
      • Julia decorator
      • Other task types summary
    • Task Constraints
      • Supported constraints
      • Dynamic constraints
      • Special constraints
    • Multiple Task Implementations
    • Prolog & Epilog
    • Data Transformation
  • API
    • Synchronization
      • Local Decorator
    • File/Object deletion
    • Task Groups
    • Other
    • API Summary
  • Failures and Exceptions
  • Integration with Numba
    • Basic usage
    • Advanced usage
      • Using Numba with GPUs
• Application Execution
  • Environment
  • Command
• Integration with Jupyter notebook
  • Environment Variables
  • API calls
  • Notebook execution
  • Notebook example
• Integration with emcee
  • Usage
  • Sample Application
  • Execution
• Distributed Data Set (DDS)
  • How it works?
  • How to use?
  • Available Methods
  • Examples
    • Wordcount
    • Pi estimation
    • Terasort
    • Inverted indexing
    • Transitive closure