DataFlow Supercomputing Essentials

Algorithms, Applications and Implementations

  • Veljko Milutinovic
  • Milos Kotlar
  • Marko Stojanovic
  • Igor Dundic
  • Nemanja Trifunovic
  • Zoran Babovic

Part of the Computer Communications and Networks book series (CCN)

Table of contents

  1. Front Matter
    Pages i-xi
  2. Algorithms

    1. Front Matter
      Pages 1-1
    2. Veljko Milutinovic, Milos Kotlar, Marko Stojanovic, Igor Dundic, Nemanja Trifunovic, Zoran Babovic
      Pages 3-44
  3. Applications

    1. Front Matter
      Pages 45-45
    2. Veljko Milutinovic, Milos Kotlar, Marko Stojanovic, Igor Dundic, Nemanja Trifunovic, Zoran Babovic
      Pages 47-92
    3. Veljko Milutinovic, Milos Kotlar, Marko Stojanovic, Igor Dundic, Nemanja Trifunovic, Zoran Babovic
      Pages 93-107
  4. Implementations

    1. Front Matter
      Pages 109-109
    2. Veljko Milutinovic, Milos Kotlar, Marko Stojanovic, Igor Dundic, Nemanja Trifunovic, Zoran Babovic
      Pages 111-126
    3. Veljko Milutinovic, Milos Kotlar, Marko Stojanovic, Igor Dundic, Nemanja Trifunovic, Zoran Babovic
      Pages 127-148
  5. Back Matter
    Pages 149-150

About this book

Introduction

This illuminating text/reference reviews the fundamentals of programming for effective DataFlow computing. The DataFlow paradigm enables considerable increases in speed and reductions in power consumption for supercomputing processes, yet the programming model requires a distinctly different approach. The algorithms and examples showcased in this book will help the reader to develop their understanding of the advantages and unique features of this methodology.

This work serves as a companion title to DataFlow Supercomputing Essentials: Research, Development and Education, which analyzes the latest research in this area, and the training resources available.

Topics and features:

  • Presents an implementation of Neural Networks using the DataFlow paradigm, as an alternative to the traditional ControlFlow approach
  • Discusses a solution to the three-dimensional Poisson equation, using the Fourier method and DataFlow technology
  • Examines how the performance of the Binary Search algorithm can be improved through implementation on a DataFlow architecture
  • Reviews the different way of thinking required to best configure the DataFlow engines for the processing of data in space flowing through the devices
  • Highlights how the DataFlow approach can efficiently support applications in big data analytics, deep learning, and the Internet of Things

This indispensable volume will benefit all researchers interested in supercomputing in general, and DataFlow computing in particular. Advanced undergraduate and graduate students involved in courses on Data Mining, Microprocessor Systems, and VLSI Systems, will also find the book to be an invaluable resource.

Keywords

DataFlow Big Data Supercomputing Field-programmable gate array Neural networks

Authors and affiliations

  • Veljko Milutinovic
    • 1
  • Milos Kotlar
    • 2
  • Marko Stojanovic
    • 3
  • Igor Dundic
    • 4
  • Nemanja Trifunovic
    • 5
  • Zoran Babovic
    • 6
  1. 1.School of Electrical EngineeringUniversity of BelgradeBelgradeSerbia
  2. 2.School of Electrical EngineeringUniversity of BelgradeBelgradeSerbia
  3. 3.School of Electrical EngineeringUniversity of BelgradeBelgradeSerbia
  4. 4.University of BernBern/Fribourg/NeuchâtelSwitzerland
  5. 5.Maxeler TechnologiesLondonUnited Kingdom
  6. 6.School of Electrical EngineeringUniversity of BelgradeBelgradeSerbia

Bibliographic information

  • DOI https://doi.org/10.1007/978-3-319-66125-4
  • Copyright Information Springer International Publishing AG 2017
  • Publisher Name Springer, Cham
  • eBook Packages Computer Science
  • Print ISBN 978-3-319-66124-7
  • Online ISBN 978-3-319-66125-4
  • Series Print ISSN 1617-7975
  • Series Online ISSN 2197-8433
  • About this book
Industry Sectors
Pharma
Automotive
Electronics
Telecommunications
Aerospace