Book 2010

Software Automatic Tuning

From Concepts to State-of-the-Art Results


ISBN: 978-1-4419-6934-7 (Print) 978-1-4419-6935-4 (Online)

Table of contents (20 chapters)

  1. Front Matter

    Pages i-xiv

  2. Introduction

    1. Front Matter

      Pages 1-1

    2. Chapter

      Pages 3-15

      Software Automatic Tuning: Concepts and State-of-the-Art Results

  3. Achievements in Scientific Computing

    1. Front Matter

      Pages 17-17

    2. Chapter

      Pages 19-32

      ATLAS Version 3.9: Overview and Status

    3. Chapter

      Pages 33-48

      Autotuning Method for Deciding Block Size Parameters in Dynamically Load-Balanced BLAS

    4. Chapter

      Pages 49-67

      Automatic Tuning for Parallel FFTs

    5. Chapter

      Pages 69-85

      Dynamic Programming Approaches to Optimizing the Blocking Strategy for Basic Matrix Decompositions

    6. Chapter

      Pages 87-101

      Automatic Tuning of the Division Number in the Multiple Division Divide-and-Conquer for Real Symmetric Eigenproblem

    7. Chapter

      Pages 103-119

      Automatically Tuned Mixed-Precision Conjugate Gradient Solver

    8. Chapter

      Pages 121-133

      Automatically Tuned Sparse Eigensolvers

    9. Chapter

      Pages 135-152

      Systematic Performance Evaluation of Linear Solvers Using Quality Control Techniques

    10. Chapter

      Pages 153-173

      Application of Alternating Decision Trees in Selecting Sparse Linear Solvers

    11. Chapter

      Pages 175-192

      Toward Automatic Performance Tuning for Numerical Simulations in the SILC Matrix Computation Framework

    12. Chapter

      Pages 193-208

      Exploring Tuning Strategies for Quantum Chemistry Computations

    13. Chapter

      Pages 209-228

      Automatic Tuning of CUDA Execution Parameters for Stencil Processing

    14. Chapter

      Pages 229-252

      Static Task Cluster Size Determination in Homogeneous Distributed Systems

  4. Evolution to a General Paradigm

    1. Front Matter

      Pages 253-253

    2. Chapter

      Pages 255-274

      Algorithmic Parameter Optimization of the DFO Method with the OPAL Framework

    3. Chapter

      Pages 275-293

      A Bayesian Method of Online Automatic Tuning

    4. Chapter

      Pages 295-313

      ABCLibScript: A Computer Language for Automatic Performance Tuning

    5. Chapter

      Pages 315-334

      Automatically Tuning Task-Based Programs for Multicore Processors

    6. Chapter

      Pages 335-351

      Efficient Program Compilation Through Machine Learning Techniques

    7. Chapter

      Pages 353-370

      Autotuning and Specialization: Speeding up Matrix Multiply for Small Matrices with Compiler Technology

  5. Back Matter

    Pages 371-377