| Document Type
|
:
|
BL
|
| Record Number
|
:
|
877215
|
| Main Entry
|
:
|
Pas, Ruud van der
|
| Title & Author
|
:
|
Using OpenMP - the next step : : affinity, accelerators, tasking, and SIMD /\ Ruud van der Pas, Eric Stotzer, and Christian Terboven.
|
| Publication Statement
|
:
|
Cambridge, Massachusetts :: The MIT Press,, [2017]
|
| Series Statement
|
:
|
Scientific and engineering computation
|
| Page. NO
|
:
|
1 online resource (xxi, 365 pages) :: illustrations
|
| ISBN
|
:
|
0262344017
|
|
|
:
|
: 9780262344012
|
|
|
:
|
0262534789
|
|
|
:
|
9780262534789
|
| Bibliographies/Indexes
|
:
|
Includes bibliographical references and index.
|
| Contents
|
:
|
Intro; Contents; Series Foreword; Foreword; Preface; 1 A Recap of OpenMP 2.5; 1.1 OpenMP Directives and Syntax; 1.2 Creating a Parallel Program with OpenMP; 1.2.1 The Parallel Region; 1.2.2 The OpenMP Execution Model; 1.2.3 The OpenMP Memory Model; 1.3 The Worksharing Constructs; 1.3.1 The Loop Construct; 1.3.2 The Sections Construct; 1.3.3 The Single Construct; 1.3.4 The Fortran Workshare Construct; 1.3.5 The Combined Worksharing Constructs; 1.4 The Master Construct; 1.5 Nested Parallelism; 1.6 Synchronization Constructs; 1.6.1 The Barrier Construct; 1.6.2 The Critical Construct
|
|
|
:
|
1.6.3 The Atomic Construct1.6.4 The Ordered Construct; 1.7 The OpenMP 2.5 Environment Variables; 1.8 The OpenMP 2.5 Runtime Functions; 1.9 Internal Control Variables in OpenMP; 1.10 Concluding Remarks; 2 New Features in OpenMP; 2.1 Enhancements to Existing Constructs; 2.1.1 The Schedule Clause; 2.1.2 The If Clause; 2.1.3 The Collapse Clause; 2.1.4 The Linear Clause; 2.1.5 The Critical Construct; 2.1.6 The Atomic Construct; 2.2 New Environment Variables; 2.3 New Runtime Functions; 2.3.1 Runtime Functions for Thread Management, Thread Scheduling, and Nested Parallelism
|
|
|
:
|
2.3.2 Runtime Functions for Tasking, Cancellation, and Thread Affi nity2.3.3 Runtime Functions for Locking; 2.3.4 Runtime Functions for Heterogeneous Systems; 2.3.5 Usage Examples of the New Runtime Functions; 2.4 New Functionality; 2.4.1 Changed Ownership of Locks; 2.4.2 Cancellation; 2.4.3 User-Defined Reduction; 2.4.4 The Doacross Loop; 2.5 Concluding Remarks; 3 Tasking; 3.1 Hello Task; 3.1.1 Parallelizing a Palindrome; 3.1.2 Parallelizing a Sentence with a Palindrome; 3.1.3 Closing Comments on the Palindrome Example; 3.2 Using Tasks to Parallelize a Linked List
|
|
|
:
|
3.2.1 The Sequential Version of the Linked List Program3.2.2 The Parallel Version of the Linked List Program; 3.2.3 Closing Comments on the Linked List Example; 3.3 Sorting Things Out with Tasks; 3.3.1 The Sequential Quicksort Algorithm; 3.3.2 The OpenMP Quicksort Algorithm; 3.3.3 Fine-Tuning the OpenMP Quicksort Algorithm; 3.3.4 Closing Comments on the OpenMP Quicksort Algorithm; 3.4 Overlapping I/O and Computations Using Tasks; 3.4.1 Using Tasks and Task Dependences; 3.4.2 Using the Taskloop Construct; 3.4.3 Closing Comments on the Pipeline Example; 3.5 The Data Environment with Tasks
|
|
|
:
|
3.6 What is a Task?3.7 Task Creation, Synchronization, and Scheduling; 3.8 The Taskloop Construct; 3.9 Concluding Remarks; 4 Thread A nity; 4.1 The Characteristics of a cc-NUMA Architecture; 4.2 First Touch Data Placement; 4.2.1 The Pros and Cons of First Touch Data Placement; 4.2.2 How to Exploit the First Touch Policy; 4.3 The Need for Thread A nity Support; 4.4 The OpenMP Thread A nity Philosophy; 4.5 The OpenMP Places Concept; 4.5.1 Defining OpenMP Places Using Sets with Numbers; 4.5.2 The OpenMP Place List; 4.5.3 Defining OpenMP Places Using Abstract Names
|
| Abstract
|
:
|
A guide to the most recent, advanced features of the widely used OpenMP parallel programming model, with coverage of major features in OpenMP 4.5. This book offers an up-to-date, practical tutorial on advanced features in the widely used OpenMP parallel programming model. Building on the previous volume, Using OpenMP: Portable Shared Memory Parallel Programming (MIT Press), this book goes beyond the fundamentals to focus on what has been changed and added to OpenMP since the 2.5 specifications. It emphasizes four major and advanced areas: thread affinity (keeping threads close to their data), accelerators (special hardware to speed up certain operations), tasking (to parallelize algorithms with a less regular execution flow), and SIMD (hardware assisted operations on vectors). As in the earlier volume, the focus is on practical usage, with major new features primarily introduced by example. Examples are restricted to C and C++, but are straightforward enough to be understood by Fortran programmers. After a brief recap of OpenMP 2.5, the book reviews enhancements introduced since 2.5. It then discusses in detail tasking, a major functionality enhancement; Non-Uniform Memory Access (NUMA) architectures, supported by OpenMP; SIMD, or Single Instruction Multiple Data; heterogeneous systems, a new parallel programming model to offload computation to accelerators; and the expected further development of OpenMP.
|
| Subject
|
:
|
Application program interfaces (Computer software)
|
| Subject
|
:
|
Parallel programming (Computer science)
|
| Subject
|
:
|
Application program interfaces (Computer software)
|
| Subject
|
:
|
Parallel programming (Computer science)
|
| Subject
|
:
|
OpenMP (Application program interface)
|
|
|
:
|
OpenMP (Application program interface)
|
| Dewey Classification
|
:
|
005.2/75
|
| LC Classification
|
:
|
QA76.642.P427 2017
|
| Added Entry
|
:
|
Stotzer, Eric
|
|
|
:
|
Terboven, Christian
|