MPI for Python Part 1 | Lecture Note - Edubirdie

University:
Boston University
Course:
MET CS 201 | Introduction to Programming
Academic year:

2024
Views:

350

Pages:

15
Author:

Naomi Whitehead

MPI for Python Outline Communicators Point to Point Communication Collective Operations Compute Pi Mandelbrot Set Dynamic Process Management What is mpi4py? I I I Full-featured Python bindings for MPI. API based on the standard MPI-2 C++ bindings. Almost all MPI calls are supported. I I targeted to MPI-2 implementations. also works with MPI-1 implementations. Implementation Implemented with Cython I Code base far easier to write, maintain, and extend. I Faster than other solutions (mixed Python and C codes). I A pythonic API that runs at C speed ! Features – MPI-1 I Process groups and communication domains. I I I Point to point communication. I I I intracommunicators intercommunicators blocking (send/recv) nonblocking (isend/irecv + test/wait) Collective operations. I I I Synchronization (barrier) Communication (broadcast, scatter/gather) Global reductions (reduce, scan) Features – MPI-2 I Dynamic process management (spawn, connect/accept). I Parallel I/O (read/write). I One sided operations, a.k.a. RMA (put/get/accumulate). I Extended collective operations. Features – Python I Communication of Python objects. I I high level and very convenient, based in pickle serialization can be slow for large data (CPU and memory consuming)