book

Shared Memory Application Programming

Name: Shared Memory Application Programming
Author: Victor Alessandrini
ISBN: 9780128038208

by Victor Alessandrini

November 2015

Intermediate to advanced

556 pages

17h 34m

English

Morgan Kaufmann

Read now

Unlock full access

Cover image
Title page
Table of Contents
Copyright
Preface
Pedagogical ObjectivesProgramming EnvironmentsBook Organization
Biography
Acknowledgments
Chapter 1: Introduction and Overview
Abstract1.1 Processes and Threads1.2 Overview of Computing Platforms1.3 Memory System of Computing Platforms1.4 Parallel Processing Inside Cores1.5 External Computational Devices1.6 Final Comments
Chapter 2: Introducing Threads
Abstract2.1 Applications and Processes2.2 Multithreaded Processes2.3 Programming and Execution Models2.4 Benefits of Concurrent Programming
Chapter 3: Creating and Running Threads
Abstract3.1 Introduction3.2 Overview of Basic Libraries3.3 Overview of Basic Thread Management3.4 Using Posix Threads3.5 Using Windows Threads3.6 C++11 Thread Library3.7 SPool Utility3.8 SPool Examples3.9 First Look at OpenMP3.10 Database Search Example3.11 Conclusions3.12 Annex: Coding C++11 Time Durations

Chapter 4: Thread-Safe Programming
Abstract4.1 Introduction4.2 Some Library Functions are not Thread Safe4.3 Dealing with Random Number Generators4.4 Thread Local Storage Services4.5 Second Example: A Gaussian Random Generator4.6 Comments on Thread Local Storage4.7 Conclusion
Chapter 5: Concurrent Access to Shared Data
Abstract5.1 First Comments on Thread Synchronization5.2 Need for Mutual Exclusion Among Threads5.3 Different Kinds of Mutex Flavors5.4 Pthreads Mutual Exclusion5.5 Other Simple Examples5.6 Windows Mutual Exclusion5.7 OpenMP Mutual Exclusion5.8 C++11 Mutual Exclusion5.9 TBB Mutual Exclusion5.10 First Look at Atomic Operations5.11 Container Thread Safety5.12 Comments on Mutual Exclusion Best Practices
Chapter 6: Event Synchronization
Abstract6.1 Idle Waits Versus Spin Waits6.2 Condition Variables in Idle Waits6.3 Idle Waits in Pthreads6.4 Windows Condition Variables6.5 C++11 condition_variable Class6.6 Examples of Idle Wait6.7 C++11 Futures and Promises
Chapter 7: Cache Coherency and Memory Consistency
Abstract7.1 Introduction7.2 Cache Coherency Issue7.3 What is a Memory Consistency Model?7.4 Weak-Ordering Memory Models7.5 Pthreads Memory Consistency7.6 OpenMP Memory Consistency
Chapter 8: Atomic Types and Operations
Abstract8.1 Introduction8.2 C++11 std::atomic<T> Class8.3 Lock-Free Algorithms8.4 Synchronizing Thread Operations8.5 Examples of Atomic Synchronizations8.6 TBB atomic<T> Class8.7 Windows Atomic Services8.8 Summary
Chapter 9: High-Level Synchronization Tools
Abstract9.1 Introduction and Overview9.2 General Comments on High-Level Synchronization Tools9.3 Overview of the vath Synchronization Utilities9.4 Timers9.5 Boolean Locks9.6 SynchP< T > Template Class > Template Class9.7 Idle and Spin Barriers9.8 Blocking Barriers9.9 ThQueue<T> Class9.10 Reader-Writer Locks9.11 RWlock Class9.12 General Overview of Thread Pools
Chapter 10: OpenMP
AbstractOverview10.1 Basic Execution Model10.2 Configuring OpenMP10.3 Thread Management and Work-Sharing Directives10.4 Synchronization Directives10.5 Examples of Parallel and Work-Sharing Constructs10.6 Task API10.7 Task Examples10.8 Task Best Practices10.9 Cancellation of Parallel Constructs10.10 Offloading Code Blocks to Accelerators10.11 Thread Affinity10.12 Vectorization10.13 Annex: SafeCounter Utility Class
Chapter 11: Intel Threading Building Blocks
Abstract11.1 Overview11.2 TBB Content11.3 TBB Initialization11.4 Operation of the High-Level Algorithms11.5 Simple parallel_for Example
Chapter 12: Further Thread Pools
Abstract12.1 Introduction12.2 SPool Reviewed12.3 NPool Features12.4 NPool API12.5 Building Parallel Jobs12.6 Operation of the NPool12.7 Examples12.8 Running Parallel Routines in Parallel12.9 Hybrid MPI-Threads Example
Chapter 13: Molecular Dynamics Example
Abstract13.1 Introduction13.2 Molecular Dynamics Problem13.3 Integration of the Equations of Motion13.4 Md.C Sequential Code13.5 Parallel Implementations of Md.C
Chapter 14: Further Data Parallel Examples
Abstract14.1 Introduction14.2 Relaxation Methods14.3 First Example: Heat.C14.4 Parallel Implementation of Heat.C14.5 Heat Performance Issues14.6 Second Example: Sor.C14.7 Parallel Implementations of Sor.C14.8 Sor Performance Issues14.9 Alternative Approach to Data Dependencies
Chapter 15: Pipelining Threads
Abstract15.1 Pipeline Concurrency Pattern15.2 Example 1: Two-Dimensional Heat Propagation15.3 Sequential Code Heat.C15.4 Pipelined Versions15.5 Pipeline Classes15.6 Example: Pipelined Sor15.7 Pipelining Threads in TBB15.8 Some Performance Considerations15.9 Annex: Solution to the Heat Diffusion Equation15.10 Annex: FFT Routines
Chapter 16: Using the TBB Task Scheduler
Abstract16.1 Introduction16.2 Structure of the TBB Pool16.3 TBB Task Management Classes16.4 Complete Scheduler API: The Task Class16.5 Miscellaneous Task Features16.6 Using the TBB Scheduler16.7 Job Submission by Client Threads16.8 Example: Molecular Dynamics Code16.9 Recycling Parallel Region Tasks16.10 Annex: Task Class Member Functions
Annex A: Using the Software
A.1 Libraries RequiredA.2 Software OrganizationA.3 vath Classes
Annex B: C++ Function Objects and Lambda Expressions
B.1 Function ObjectsB.2 Function Object SyntaxB.3 Lambda Expressions
Bibliography
Index

Content preview from Shared Memory Application Programming

Index

ABarrier class 203, 419–420

algorithm 205, 205f

implementation 204–206

Accelerators, offloading code blocks to 292–297

Acquire operations 161

Acquire semantics 179

Acquire-release fence 161

Acquire-release memory model 175

sequential consistency compared with 177–178

Advanced reads 157–158

Affinity identity 470

AIX 160

Algorithms

ABarrier class 205, 205f

Box-Muller 97–98

divide and conquer 222

image-filtering 401

lock-free 125, 171–174

as alternative to critical sections 171

AReduction class 172–174

as optimistic approach 171

updating global data item 171–172

parallel quicksort 282–285

parallel_do 310, 328–329

parallel_for 309, 385

example of usage 317–320

parallel_for_each 310, 327–328

parallel_invoke 310, 329–330

parallel_reduce ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

NLP in Action: Attention mechanism and upgrading TorchText 0.9

Publisher Resources

ISBN: 9780128038208

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Shared Memory Application Programming

by Victor Alessandrini

Index

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.