html5-img
1 / 9

Parallel Python

Parallel Python. Ben Agar , Gal Paikin. Outline. What is Python Parallel Python pyMPI Efficiency – Python Vs. C Conclusions Questions. What is Python. High level programming language invented in late 1980s Philosophy : code readability, “short” codes, fast programming.

rumer
Télécharger la présentation

Parallel Python

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Parallel Python Ben Agar , Gal Paikin

  2. Outline • What is Python • Parallel Python • pyMPI • Efficiency – Python Vs. C • Conclusions • Questions

  3. What is Python • High level programming language invented in late 1980s • Philosophy : code readability, “short” codes, fast programming. • Programming paradigms: object oriented, imperative, functional programming • Indentation based runtime compilation.

  4. Parallel Python • Environment : Multiple CPUs, Multicore CPUs, Clusters. • The goal is to improve performance by parallel computing invisible to the user.

  5. Parallel Python with pyMPI • Developed by Pat Miller at the Lawrence Livermore National Laboratory • Provides Python level interface to MPI routines (bcast, barrier, reduce, send, recv, scatter, gather etc…) • pyMPIis a separate executable that incorporates Python • pyMPIruns on every processor and all executes the same Python code • First processor serves as the Master. All input read in by first processor and sent to all other processors. • Output can be controlled – either only from first processor, all processors or a mix • Extensive wrapping of MPI

  6. Efficiency • pyMPI messages contain more overhead than native languages MPI. • Message repetition

  7. pyMPI code example Calculating PI :

  8. Conclusions • Python is a fast, hands-on programming language • As a higher level language, python is slower than C or Fortran • pyMPI offers an MPI solution for python that is slower in performance yet worthwhile. • pyMPI slow factor is similar to the general python slower factor comparing to C.

  9. Questions?

More Related