| 09:30-17:00 (Lobby/Auditorium, Kobe U.) |
(Registration) |
| Opening Remarks | |
| 09:50-10:00 | Openning Remarks Hiroyuki Takizawa (Tohoku University, Japan)(General Chair, iWAPT2012) |
| Session 1: Linear algebra, Chair: Yusaku Yamamoto (Kobe University, Japan) | |
| 10:00-10:30 |
A Smart Tuning Strategy for Restart Frequency of GMRES(m) with Hierarchical Cache Sizes Takahiro Katagiri (The University of Tokyo, Japan), Pierre-Yves Aquilanti (A*STAR Computational Resource Centre, Singapore), Serge Petiton (LIFL, Universite Lille 1 Science et Technologie, France) |
| 10:30-11:00 |
Auto-Tuning of Numerical Programs by Block Multi-Color Ordering Code Generation and Job-level Parallel Execution Tatsuya Abe (RIKEN AICS, Japan), Mitsuhisa Sato (RIKEN AICS/University of Tsukuba, Japan) |
| 11:00-11:30 |
Accelerating the Reorthogonalization on Singular Vectors with a Multi-Core Processor Hiroki Toyokawa (CyberAgent Inc./Kyoto University, Japan), Hiroyuki Ishigami (Kyoto University, Japan), Kinji Kimura (Kyoto University, Japan), Masami Takata (Nara Women's University, Japan), Yoshimasa Nakamura (Kyoto University, Japan) |
| 11:30-12:00 |
Designing Linear Algebra Algorithms by Transformation: Mechanizing the Expert Developer Bryan Marker (University of Texas at Austin, USA), Jack Poulson (University of Texas at Austin, USA), Don Batory (University of Texas at Austin, USA), Robert van de Geijn (University of Texas at Austin, USA) |
| 12:00-13:10 | (Lunch Break) |
| Session 2: Programming models and performance models I, Chair: Richard Vuduc (Georgia Institute of Technology, USA) | |
| 13:10-13:40 |
A Domain-Specific Compiler for Linear Algebra Operations Diego Fabregat-Traver (RWTH-Aachen, Germany), Paolo Bientinesi (RWTH-Aachen, Germany) |
| 13:40-14:30 |
(Invited Talk) Automatic Modeling and Ranking of Algorithms Paolo Bientinesi (RWTH-Aachen, Germany) |
| Session 3: Programming models and performance models II, Chair: Takahiro Katagiri (The University of Tokyo, Japan) | |
| 14:50-15:20 |
A Predictive Performance Model for Stencil Codes on Multicore CPUs Andreas Schafer (University Erlangen-Nuremberg, Germany), Dietmar Fey (University Erlangen-Nuremberg, Germany) |
| 15:20-15:50 |
Automatic Tuning of Parallel Multigrid Solvers using OpenMP/MPI Hybrid Parallel Programming Models Kengo Nakajima (The University of Tokyo, Japan) |
| 15:50-16:20 |
Auto-tuning the Matrix Powers Kernel with SEJITS Jeffrey Morlan (University of California, Berkeley, USA), Shoaib Kamil (University of California, Berkeley, USA), Armando Fox (University of California, Berkeley, USA) |
| 16:20-16:40 (Lounge/Auditorium, Kobe U.) |
(Coffee Break) |
| Session 4: GPU, Chair: Takeshi Iwashita (Kyoto University, Japan) | |
| 16:40-17:30 |
(Invited Talk) Autotuning BLAS for GPUs: Matrix Multiplication on Fermi and Kepler Jakub Kurzak (University of Tennessee, USA) |
| 17:30-18:00 |
Automatic Parameter Optimization for Edit Distance Algorithm on GPU Ayumu Tomiyama (The University of Tokyo, Japan), Reiji Suda (The University of Tokyo, Japan) |
| 18:00-18:30 |
Adaptive off-line tuning for optimized composition of components for heterogeneous many-core systems Lu Li (Linkoping University, Sweden), Usman Dastgeer (Linkoping University, Sweden), Christoph Kessler (Linkoping University, Sweden) |
| Closing Remarks | |
| 18:30-18:40 | Closing Remarks Richard Vuduc (Georgia Institute of Technology, USA)(PC Chair, iWAPT2012) |