Program

October 1st
Wednesday
9:00


Opening Talk   


9:05





10:05

Invited Talk 1
Chair: Reiji Suda

9:05 - 10:05

John Cavazos
(University of Delaware)

"Intelligent Compilers"
  abstract  slide(pdf)

10:05

10:25
Break
10:25




















11:55

Session 1: Automatic Tuning for Computing System Infrastructure
Chair: Keita Teranishi

10:25 - 10:55

Edward Walker*
(The University of Texas at Austin)

"Continuous Adaptation for High Performance Throughput Computing across Distributed Clusters"
  abstract  slide(pdf)

10:55 - 11:25

Genaro Costa*1, Josep Jorba2, Anna Morajko1, Tomas Margalef1, Emilio Luque1
(1: Universitat Autònoma de Barcelona, 2: Universitat Oberta de Catalunya)

"Performance Models for Dynamic Tuning of Parallel Applications on Computational Grids"
  abstract  slide(pdf)

11:25 - 11:55

Hiroyuki Takizawa*1, Katuto Sato1,Hiroaki Kobayashi 1 (1: Tohoku University)

"SPRAT: Runtime Processor Selection for Energy-aware Computing"
  abstract  slide(pdf)

11:55

13:30
Lunch
13:30



14:30

Invited Talk 2
Chair: Ken Naono

13:30 - 14:30

Sylvain Guinepain1, Le Gruenwald*1
(1: University of Oklahoma)

"Using Cluster Computing to Support Automatic and Dynamic Database Clustering"
  abstract  slide(pdf)

14:50



























16:50

Session 2 Automatic Tuning for Scientific/Matrix Computing
Chair: Takahiro Katagiri

14:50 - 15:20

Takeshi Fukaya*1, Yusaku Yamamoto1, Shao-Liang Zhang1
(1: Nagoya University)

"A Dynamic Programming Approach to Optimizing the Blocking Strategy for the Householder QR Decomposition"
  abstract  slide(pdf)

15:20 - 15:50

Warren Armstrong*1, Alistair P. Rendell1
(1: Australian National University)

"Reinforcement Learning for Automated Performance Tuning: Initial Evaluation for Sparse Matrix Format Selection"
  abstract  slide(pdf)

15:50 - 16:20

Keith Seymour*1, Haihang You1, Jack Dongarra1
(1: University of Tennessee)

"A Comparison of Search Heuristics for Empirical Code Optimization"
  abstract  slide(pdf)

16:20 - 16:50

DAQI REN*1, Dennis Giannacopoulos2, Reiji Suda1
(1: University of Tokyo, 2: McGill University)

"An Optimized Dynamic Load Balancing Method for Parallel 3-D Mesh Refinement for Finite Element Electromagnetics with Tetrahedra"
  abstract  slide(pdf)

16:50

17:00
Closing


Back to the iWAPT2008 main page