Software Automatic Tuning

1. Front Matter

   Pages i-xiv

   PDF

2. Introduction

   1. Front Matter

      Pages 1-1

      PDF

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

      • Reiji Suda, Ken Naono, Keita Teranishi, John Cavazos

      Pages 3-15

3. Achievements in Scientific Computing

   1. Front Matter

      Pages 17-17

      PDF

   2. ATLAS Version 3.9: Overview and Status

      • R. Clint Whaley

      Pages 19-32

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

      • Yuta Sawa, Reiji Suda

      Pages 33-48

   4. Automatic Tuning for Parallel FFTs

      • Daisuke Takahashi

      Pages 49-67

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

      • Yusaku Yamamoto, Takeshi Fukaya

      Pages 69-85

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

      • Yusuke Ishikawa, Junichi Tamura, Yutaka Kuwajima, Takaomi Shigehara

      Pages 87-101

   7. Automatically Tuned Mixed-Precision Conjugate Gradient Solver

      • Serban Georgescu, Hiroshi Okuda

      Pages 103-119

   8. Automatically Tuned Sparse Eigensolvers

      • Ken Naono, Takao Sakurai, Masashi Egi

      Pages 121-133

   9. Systematic Performance Evaluation of Linear Solvers Using Quality Control Techniques

      • Shoji Itoh, Masaaki Sugihara

      Pages 135-152

   10. Application of Alternating Decision Trees in Selecting Sparse Linear Solvers

       • Sanjukta Bhowmick, Victor Eijkhout, Yoav Freund, Erika Fuentes, David Keyes

       Pages 153-173

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

       • Tamito Kajiyama, Akira Nukada, Reiji Suda, Hidehiko Hasegawa, Akira Nishida

       Pages 175-192

   12. Exploring Tuning Strategies for Quantum Chemistry Computations

       • Lakshminarasimhan Seshagiri, Meng-Shiou Wu, Masha Sosonkina, Zhao Zhang

       Pages 193-208

   13. Automatic Tuning of CUDA Execution Parameters for Stencil Processing

       • Katsuto Sato, Hiroyuki Takizawa, Kazuhiko Komatsu, Hiroaki Kobayashi

       Pages 209-228

   14. Static Task Cluster Size Determination in Homogeneous Distributed Systems

       • Hidehiro Kanemitsu, Gilhyon Lee, Hidenori Nakazato, Takashige Hoshiai, Yoshiyori Urano

       Pages 229-252

4. Evolution to a General Paradigm

   1. Front Matter

      Pages 253-253

      PDF

   2. Algorithmic Parameter Optimization of the DFO Method with the OPAL Framework

      • Charles Audet, Cong-Kien Dang, Dominique Orban

      Pages 255-274

   3. A Bayesian Method of Online Automatic Tuning

      • Reiji Suda

      Pages 275-293

Automatic Performance Tuning is a new software paradigm which enables software to be high performance in any computing environment. Its methodologies have been developed over the past decade, and it is now rapidly growing in terms of its scope and applicability, as well as in its scientific knowledge and technological methods. Software developers and researchers in the area of scientific and technical computing, high performance database systems, optimized compilers, high performance systems software, and low-power computing will find this book to be an invaluable reference to this powerful new paradigm.

• Adaptive algorithms
• Computing with GPGPU and accelators
• Multicore Processors
• Parallel and distributed computing
• Performance Debugging
• algorithms
• automatically-tuned code generation
• autonomic computing and context-aware computing
• computer-aided design (CAD)
• debugging
• hybrid systems
• low-power computing
• performance tuning
• simulation

• Central Research Laboratory, Hitachi Ltd., Kokubunji-shi, Tokyo, Japan

  Ken Naono

• Cray, Inc., St Paul, USA

  Keita Teranishi

• Dept. Computer & Information Sciences, University of Delaware, Newark, USA

  John Cavazos

• Dept. Computer Science, University of Tokyo, Tokyo, Japan

  Reiji Suda

Policies and ethics