Python Parallel Programming Cookbook

图书信息

作者	Giancarlo Zaccone
出版社	Packt Publishing
ISBN	9781785286728
出版时间	2015-08-26
字数	127.8万
分类	进口书,外文原版书,电脑,网络

读书简介

This book is intended for software developers who want to use parallel programming techniques to write powerful and efficient code. After reading this book, you will be able to master the basics and the advanced features of parallel computing. The Python programming language is easy to use and allows nonexperts to deal with and easily understand the topics exposed in this book.

目录

Python Parallel Programming Cookbook

Table of Contents

Python Parallel Programming Cookbook

Credits

About the Author

About the Reviewers

www.PacktPub.com

Support files, eBooks, discount offers, and more

Why Subscribe?

Free Access for Packt account holders

Preface

What this book covers

What you need for this book

Who this book is for

Sections

Getting ready

How to do it…

How it works…

There's more…

See also

Conventions

Reader feedback

Customer support

Downloading the example code

Errata

Piracy

Questions

1. Getting Started with Parallel Computing and Python

Introduction

The parallel computing memory architecture

SISD

MISD

SIMD

MIMD

Memory organization

Shared memory

Distributed memory

Massively parallel processing

A cluster of workstations

The heterogeneous architecture

Parallel programming models

The shared memory model

The multithread model

The message passing model

The data parallel model

How to design a parallel program

Task decomposition

Task assignment

Agglomeration

Mapping

Dynamic mapping

Manager/worker

Hierarchical manager/worker

Decentralize

How to evaluate the performance of a parallel program

Speedup

Efficiency

Scaling

Amdahl's law

Gustafson's law

Introducing Python

Getting ready

How to do it…

Python in a parallel world

Introducing processes and threads

Start working with processes in Python

Getting ready

How to do it…

How it works…

Start working with threads in Python

How to do it…

How it works…

2. Thread-based Parallelism

Introduction

Using the Python threading module

How to define a thread

How to do it…

How it works…

How to determine the current thread

How to do it…

How it works…

How to use a thread in a subclass

How to do it…

How it works…

Thread synchronization with Lock and RLock

How to do it…

How it works…

There's more…

Thread synchronization with RLock

How to do it…

How it works…

Thread synchronization with semaphores

Getting ready

How to do it…

How it works…

There's more…

Thread synchronization with a condition

Getting ready

How to do it…

How it works…

There's more…

Thread synchronization with an event

How to do it…

How it works…

Using the with statement

Getting ready

How to do it…

How it works…

There's more…

Thread communication using a queue

How to do it…

How it works…

Evaluating the performance of multithread applications

How to do it…

How it works…

The first test

The second test

The third test

The fourth test

There's more…

3. Process-based Parallelism

Introduction

How to spawn a process

How to do it...

How it works...

There's more...

How to name a process

How to do it...

How it works...

How to run a process in the background

How to do it...

How it works...

There's more...

How to kill a process

How to do it...

How it works...

How to use a process in a subclass

How to do it...

How it works...

How to exchange objects between processes

Using queue to exchange objects

How to do it...

How it works...

There's more...

Using pipes to exchange objects

How to do it...

How it works...

How to synchronize processes

How to do it...

How it works...

How to manage a state between processes

How to do it...

How it works...

How to use a process pool

How to do it…

How it works…

Using the mpi4py Python module

Getting ready

How to do it…

How it works…

There's more…

Point-to-point communication

How to do it…

How it works…

There's more…

Avoiding deadlock problems

How to do it…

How it works…

There's more…

Collective communication using broadcast

How to do it…

How it works…

There's more…

Collective communication using scatter

How to do it…

How it works…

There's more…

Collective communication using gather

How to do it…

How it works…

There's more…

Collective communication using Alltoall

How to do it…

How it works…

There's more…

The reduction operation

How to do it…

How it works…

How to optimize communication

How to do it…

How it works…

There's more…

4. Asynchronous Programming

Introduction

Using the concurrent.futures Python modules

Dealing with the process and thread pool

Getting ready

How to do it…

How it works…

There's more…

Event loop management with Asyncio

What is an event loop

Getting ready

How to do it…

How it works…

Handling coroutines with Asyncio

Getting ready

How to do it…

How it works…

Task manipulation with Asyncio

Getting ready

How to do it…

How it works…

Dealing with Asyncio and Futures

Getting ready

How to do it…

How it works…

There's more…

5. Distributed Python

Introduction

Using Celery to distribute tasks

How to do it…

See also

How to create a task with Celery

How to do it…

How it works…

There's more…

Scientific computing with SCOOP

Getting ready

How to do it…

How it works…

Handling map functions with SCOOP

Getting ready

How to do it…

How it works…

Remote Method Invocation with Pyro4

Getting ready

How to do it…

How it works…

Chaining objects with Pyro4

How to do it…

How it works…

Developing a client-server application with Pyro4

How to do it…

How it works…

Communicating sequential processes with PyCSP

Getting ready

How to do it…

How it works…

There's more…

Using MapReduce with Disco

Getting ready

How to do it…

How it works…

There's more…

A remote procedure call with RPyC

Getting ready

How to do it…

How it works…

6. GPU Programming with Python

Introduction

Using the PyCUDA module

A hybrid programming model

The kernel and thread hierarchy

Getting ready

How to do it…

How it works…

See also

How to build a PyCUDA application

How to do it…

How it works…

There's more…

Understanding the PyCUDA memory model with matrix manipulation

How to do it…

How it works…

Kernel invocations with GPUArray

How to do it…

How it works…

There's more…

Evaluating element-wise expressions with PyCUDA

How to do it…

How it works…

There's more…

The MapReduce operation with PyCUDA

How to do it…

How it works…

GPU programming with NumbaPro

Getting ready

How to do it…

How it works…

Using GPU-accelerated libraries with NumbaPro

How to do it…

How it works…

There's more…

Using the PyOpenCL module

Getting ready

How to do it…

How it works…

How to build a PyOpenCL application

How to do it…

How it works…

Evaluating element-wise expressions with PyOpenCl

How to do it…

How it works…

Testing your GPU application with PyOpenCL

How to do it…

How it works…

Index