Smart Multicore Embedded Systems

1. Front Matter

   Pages i-xxvi

   PDF

2. Parallel Programming Models and Methodologies

   1. Front Matter

      Pages 1-1

      PDF

   2. Parallel Programming Models

      • Vassilios V. Dimakopoulos

      Pages 3-20

   3. Compilation Tool Chains and Intermediate Representations

      • Julien Mottin, François Pacull, Ronan Keryell, Pascal Schleuniger

      Pages 21-32

3. HW/SW Architectures Concepts

   1. Front Matter

      Pages 33-33

      PDF

   2. The STHORM Platform

      • Julien Mottin, Mickael Cartron, Giulio Urlini

      Pages 35-43

   3. The Architecture and the Technology Characterization of an FPGA-Based Customizable Application-Specific Vector Coprocessor (ASVP)

      • Roman Bartosiński, Martin Daněk, Leoš Kafka, Lukáš Kohout, Jaroslav Sýkora

      Pages 45-77

4. Run-Time and Faults Management

   1. Front Matter

      Pages 79-79

      PDF

   2. Fault Tolerance

      • Giovanni Agosta, Mickael Cartron, Antonio Miele

      Pages 81-101

   3. Introduction to Dynamic Code Generation: An Experiment with Matrix Multiplication for the STHORM Platform

      • Damien Couroussé, Victor Lomüller, Henri-Pierre Charles

      Pages 103-122

5. Case Studies

   1. Front Matter

      Pages 123-123

      PDF

   2. Signal Processing: Radar

      • Michel Barreteau, Claudia Cantini

      Pages 125-138

   3. Image Processing: Object Recognition

      • Marius Bozga, George Chasapis, Vassilios V. Dimakopoulos, Aggelis Aggelis

      Pages 139-157

   4. Video Processing: Foreground Recognition in the ASVP Platform

      • Petr Honzík, Roman Bartosiński, Martin Daněk, Leoš Kafka, Lukáš Kohout, Jaroslav Sýkora

      Pages 159-175

This book provides a single-source reference to the state-of-the-art of high-level programming models and compilation tool-chains for embedded system platforms. The authors address challenges faced by programmers developing software to implement parallel applications in embedded systems, where very often they are forced to rewrite sequential programs into parallel software, taking into account all the low level features and peculiarities of the underlying platforms. Readers will benefit from these authors’ approach, which takes into account both the application requirements and the platform specificities of various embedded systems from different industries. Parallel programming tool-chains are described that take as input parameters both the application and the platform model, then determine relevant transformations and mapping decisions on the concrete platform, minimizing user intervention and hiding the difficulties related to the correct and efficient use of memory hierarchy and low level code generation.

• Embedded Systems Software
• Many-core
• Many-core Programming
• Multi-core
• Multi-core Programming
• Parallel Programming
• Programming Parallel Applications

• Computer Science Department, University of Pisa, Pisa, Italy

  Massimo Torquati

• Delft University of Technology, Delft, The Netherlands

  Koen Bertels

• Informatics and Mathematical Modeling, DTU Informatik, Lyngby, Denmark

  Sven Karlsson

• Commissariat à l’énergie atomique et aux énergies alternatives, CEA LetiMinatec, Grenoble, France

  François Pacull

This book provides a single-source reference to the state-of-the-art of high-level programming models and compilation tool-chains for embedded system platforms.  The authors address challenges faced by programmers developing software to implement parallel applications in embedded systems, where very often they are forced to rewrite sequential programs into parallel software, taking into account all the low level features and peculiarities of the underlying platforms.  Readers will benefit from these authors’ approach, which takes into account both the application requirements and the platform specificities of various embedded systems from different industries.  Parallel programming tool-chains are described that take as input parameters both the application and the platform model, then determine relevant transformations and mapping decisions on the concrete platform, minimizing user intervention and hiding the difficulties related to the correct and efficient use of memory hierarchy and low level code generation.

This book discusses both basic concepts on parallel programming as well as advanced topics and issues related to the use of real embedded applications. The book derives from the experience and results obtained in the 3-year European ARTEMIS project SMECY (Smart Multi-core Embedded Systems, project number 100230)involving 27 partners in 9 European countries. This represents a concrete experience of work in the embedded system area, where applications, tools and platforms providers worked together in a coordinated way with the goal to obtain new, high level programming tool-chains for current and forthcoming embedded many-core platforms.                        

·         Describes tools and programming models for multicore embedded systems;

·         Emphasizes throughout performance per watt scalability;

·         Discusses realistic limits of software parallelization;

·         Enables software migration from single to multi-core;

·         Includes coverage of fault-tolerance and dynamic reconfiguration;

·         Uses case studies to demonstrate techniques presented.