Optimizing HPC Applications with Intel Cluster Tools

By Alexander Supalov , Andrey Semin , Michael Klemm , Christopher Dahnken

Optimizing HPC Applications with Intel Cluster Tools Cover Image

Optimizing HPC Applications with Intel® Cluster Tools combines an easygoing and informal style with a systematic methodology of parallel program optimization. Real-life examples convey the best known optimization methods applicable in both Linux and Microsoft® Windows environments.

Full Description

  • ISBN13: 978-1-4302-6496-5
  • 250 Pages
  • User Level: Intermediate to Advanced
  • Publishing October 22, 2014
  • Print Book Price: $39.99
  • eBook Price: $0.00

Related Titles

Full Description

Optimizing HPC Applications with Intel® Cluster Tools takes the reader on a tour of the quickly growing area of High Performance Computing: optimization of hybrid programs. These programs combine distributed memory and shared memory programming models and use the Message Passing Interface (MPI), OpenMP, Intel® Thread Building Blocks (TBB), Intel® Cilk Plus, and other ways to achieve ultimate performance and power consumption goals on enterprise-class workstations and computational clusters.

The book combines an easygoing and informal style with a systematic methodology of parallel program optimization proven by years of experience, in the context of Intel’s platforms and software-development tool environments.

Real-life application examples convey in a practical, hands-on manner the best known optimization methods applicable in both Linux and Microsoft® Windows environments.

Although primary attention is focused on hybrid applications and heterogeneous installations that mix Intel® Xeon and Intel® Xeon Phi™ processors, the optimization of purely distributed memory, shared memory, and even sequential applications on homogeneous clusters and workstations built on Intel® Xeon® is also covered. The reader can easily focus on the applicable sections clearly marked by respective "trails." For example, there is a trail for MPI programmers, a trail for OpenMP programmers, and so on. They can be combined at will to suit the reader’s needs.

On top of the tutorial and reference content, the authors address, unveil, and refute many myths and misconceptions surrounding the topic. The text is augmented and enriched by descriptions of real-life situations, sometimes funny and always instructive in their bearing.

What you’ll learn

-Practical, hands-on examples show how to make clusters and workstations based on Intel® Xeon and Intel® Xeon Phi™ processors “sing” in Linux* and Microsoft® Windows®* environments.

-Master the synergy of Intel® Cluster Studio XE that includes Intel® Composer XE, Intel® MPI Library, Intel® Trace Analyzer and Collector, Intel® VTune™ Amplifier XE, and many other useful tools.

-Achieve immediate and tangible optimization results while refining your understanding of the software design principles.

Who this book is for

Software professionals will use this book to design, develop, and especially optimize their parallel programs on Intel platforms. A student of computer science or engineering will read it as a comprehensive reader for many courses offered around the world. A casual reader will enjoy a true life adventure in the exciting world of parallel computing.

Table of Contents

Table of Contents

Foreword (Bill Gropp or Bronis de Supinski)

Preface

Chapter 1: No Time to Read this Book?

Chapter 2: Overview of Platform Architectures

Chapter 3: Top-Down Software Optimization

Chapter 4: Addressing System Bottlenecks

Chapter 5: Addressing Application Bottlenecks: Distributed Memory

Chapter 6: Addressing Application Bottlenecks: Shared Memory

Chapter 7: Addressing Microarchitecture Bottlenecks

Chapter 8: Application Design Implications

    Errata

    Please Login to submit errata.

    No errata are currently published