Intel Threading Building Blocks: Outfitting C++ for Multi-core Processor Parallelism (Paperback)

Description

Multi-core chips from Intel and AMD offer a dramatic boost in speed and responsiveness, and plenty of opportunities for multiprocessing on ordinary desktop computers. But they also present a challenge: More than ever, multithreading is a requirement for good performance. This guide explains how to maximize the benefits of these processors through a portable C++ library that works on Windows, Linux, Macintosh, and Unix systems. With it, you'll learn how to use Intel Threading Building Blocks (TBB) effectively for parallel programming -- without having to be a threading expert.

Written by James Reinders, Chief Evangelist of Intel Software Products, and based on the experience of Intel's developers and customers, this book explains the key tasks in multithreading and how to accomplish them with TBB in a portable and robust manner. With plenty of examples and full reference material, the book lays out common patterns of uses, reveals the gotchas in TBB, and gives important guidelines for choosing among alternatives in order to get the best performance.

You'll learn how Intel Threading Building Blocks:

• Enables you to specify tasks instead of threads for better portability, easier programming, more understandable source code, and better performance and scalability in general
• Focuses on the goal of parallelizing computationally intensive work to deliver high-level solutions
• Is compatible with other threading packages, and doesn't force you to pick one package for your entire program
• Emphasizes scalable, data-parallel programming, which allows program performance to increase as you add processors
• Relies on generic programming, which enables you to write the best possible algorithms with the fewest constraints

Any C++ programmer who wants to write an application to run on a multi-core system will benefit from this book. TBB is also very approachable for a C programmer or a C++ programmer without much experience with templates. Best of all, you don't need experience with parallel programming or multi-core processors to use this book.

Table of Contents

Foreword

Note from the Lead Developer of Intel Threading Building Blocks

Preface

1. Why Threading Building Blocks?

     Overview

     Benefits

2. Thinking Parallel

     Elements of Thinking Parallel

     Decomposition

     Scaling and Speedup

     What Is a Thread?

     Mutual Exclusion and Locks

     Correctness

     Abstraction

     Patterns

     Intuition

3. Basic Algorithms

     Initializing and Terminating the Library

     Loop Parallelization

     Recursive Range Specifications

     Summary of Loops

4. Advanced Algorithms

     Parallel Algorithms for Streams

5. Containers

     concurrent_queue

     concurrent_vector

     concurrent_hash_map

6. Scalable Memory Allocation

     Limitations

     Problems in Memory Allocation

     Memory Allocators

     Replacing malloc, new, and delete

7. Mutual Exclusion

     When to Use Mutual Exclusion

     Mutexes

     Mutexes

     Atomic Operations

8. Timing

9. Task Scheduler

     When Task-Based Programming Is Inappropriate

     Much Better Than Raw Native Threads

     Initializing the Library Is Your Job

     Example Program for Fibonacci Numbers

     Task Scheduling Overview

     How Task Scheduling Works

     Recommended Task Recurrence Patterns

     Making Best Use of the Scheduler

     Task Scheduler Interfaces

     Task Scheduler Summary

10. Keys to Success

     Key Steps to Success

     Relaxed Sequential Execution

     Safe Concurrency for Methods and Libraries

     Debug Versus Release

     For Efficiency's Sake

     Enabling Debugging Features

     Mixing with Other Threading Packages

     Naming Conventions

11. Examples

     The Aha! Factor

     A Few Other Key Points

     parallel_for Examples

     The Game of Life

     Parallel_reduce Examples

     CountStrings: Using concurrent_hash_map

     Quicksort: Visualizing Task Stealing

     A Better Matrix Multiply (Strassen)

     Advanced Task Programming

     Packet Processing Pipeline

     Memory Allocation

     Game Threading Example

     Physics Interaction and Update Code

     Open Dynamics Engine

12. History and Related Projects

     Libraries

     Languages

     Pragmas

     Generic Programming

     Caches

     Costs of Time Slicing

     Quick Introduction to Lambda Functions

     Further Reading

Index