2019

2019 Conference on Advanced Topics and Auto Tuning in
High-Performance Scientific Computing
February 15-16, 2019
Feb. 15 (IR1001) Auditorium Lecture Classroom, International Building 1F
Feb. 16  SC4009-1, College of Science
 National Sun Yat-sen University
Kaohsiung, Taiwan





Plenary Speaker

Prof. Kazuki Yoshizoe  (RIKEN)

Invited Speakers

Japan
  • Prof. Akihiro Fujii (Kogakuin University)
  • Prof. Takeshi Fukaya (Hokkaido University)
  • Prof. Akihiro Ida (The University of Tokyo)
  • Prof. Takahiro Katagiri (Nagoya University)
  • Prof. Kengo Nakajima (The University of Tokyo)
  • Prof. Junji Nakano (The Institute of Statistical Mathematics)
  • Prof. Satoshi Ohshima (Kyushu University)
  • Prof. Katsuhisa Ozaki (Shibaura Institute of Technology)
  • Prof. Reiji Suda (The University of Tokyo)
  • Prof. Teruo Tanaka (Kogakuin University)
  • Prof. Takeshi Terao (Shibaura Institute of Technology)
  • Prof. Tan Yiyu (RIKEN)
Taiwan
  • Prof. How-Wei Chen (National Central University)
  • Prof. Feng-Nan Hwang (National Central University)
  • Prof. Yihuang K. Kang (National Sun Yat-sen University)
  • Prof. Guan-Ju Peng (National Chung Hsing University)
  • Prof. Weichung Wang (National Taiwan University)
  • Prof. Chin-Tien Wu (National Chiao Tung University)
  • Prof. Jong Shinn Wu (National Chiao Tung University)
  • Prof. Yi-Ren Yeh (National Kaohsiung Normal University)

Local Committee

Prof. Chieh-Sen Huang (National Sun Yat-sen University)

Aims and Scope

The Conference on Advanced Topics and Auto Tuning in High-Performance Scientific Computing focuses on the scientific impacts due to the latest computer architectures and the approaches to achieve high-performance computing on these leading-edge computers. Advances in many-core architectures and high-end computers have unveiled their significances in the scientific discoveries and engineering achievements. The complexity of these newly developed computers, however, also leads to contemporary challenges to achieve the best efficiency of the highly promising computational capabilities. The conference encourages interdisciplinary communications between researchers from applied mathematics, statistics, computer science, physical sciences, engineering and industry to prompt innovations and breakthroughs in this exciting field. The main themes include, but not limited to, simulations, numerical methods, applications, hardware, and particularly software and algorithm auto-tuning via statistical methods.

Contact Person

Prof. Chieh-Sen Huang (National Sun Yat-sen University, e-mail : huangcs@math.nsysu.edu.tw)

Organizers

  • Chieh-Sen Huang (National Sun Yat-sen University)
  • Takahiro Katagiri (University of Nagoya)
  • Reiji Suda (The University of Tokyo)
  • Weichung Wang (National Taiwan University)
Sponsors




Program

Feb. 15, 2019 (Friday)

 

09:00 - 09:20 Registration

09:20 - 09:30 Opening  Prof. Chieh-Sen Huang / National Sun Yat-sen University

                         Prof. Takahiro Katagiri/ Nagoya University

 

09:30 - 10:30 Session I Advanced Linear Algebra Techniques (chair: Takahiro Katagiri)

  • Prof. Takeshi Fukaya (Hokkaido University)

Shifted Cholesky QR algorithm for computing the QR factorization of ill-conditioned matrices

  • Prof. Katsuhisa Ozaki (Shibaura Institute of Technology)

Test matrices with specified solutions for numerical linear algebra

§  Prof. Akihiro Fujii (Kogakuin University)

     Evaluation of Time segmented correction method for parallel time integration

 

10:30 – 11:10 Group Photo and Coffee Break

 

11:10 - 12:10 Session II Machine Learning and Its Applications (chair: Kazuki Yoshizoe)

  • Prof. Yi -Ren Yeh (National Kaohsiung Normal University)
    Semantics -preserving Locality Embedding for Zero-Shot Learning
  • Guan-Ju Peng (National Chung Hsing University)
    Joint and Direct Optimization for Dictionary Learning in Convolutional Sparse Representation
  • Prof. Yihuang K.Kang (National Sun-yat Sen University)

Towards Interpretable Machine Learning and Explainable AI

 

12:10 – 13:30 Lunch Break

 

13:30-14:30 Plenary Talk I (Kazuki Yoshizoe / RIKEN (chair: Weichung Wang)

AlphaGo for Chemistry: Deep Learning and Tree Search Finds New Molecules

 14:30 - 15:30 Session III Advanced HPSC Techniques for Matrix Computation and Its Applications (chair :Prof. Kengo Nakajima)

  • Prof. Takeshi Terao (Shibaura Institute of Technology)

CholeskyQR algorithms for ill-conditioned matrices on large-scale parallel systems

  • Prof. Tan Yiyu (RIKEN)

Design and Implementation of an OpenCL based Matrix Multiplier

  • Prof. Akihiro Ida (The University of Tokyo)

Matrix Arithmetic Using Lattice H-matrix Representations

 

15:30 - 16:00 Coffee Break


16:00 - 17:00 Session IV  Efficient HPSC Technique on Automatic Tuning (chair: Chin-Tien Wu)

   §  Prof. Takahiro Katagiri (Nagoya University) 
     Toward Auto-tuning of Preconditioners for Sparse Iterative Solvers by Deep Learning
   §  Prof. Teruo Tanaka(Kogakuin University) 
     Enhancement of Performance Parameter Search Method for Multiple Parameter Estimation

§  Prof. Reiji Suda (The University of Tokyo)

Generalized Diamond Type Matrix Powers Kernel on OpenMP

 

18:00 - 20:00 Banquet (The Sunset Beach Resort)

 

Feb. 16, 2019 (Saturday)

 

09:00 - 09:10 Registration

 9:10 - 10:30 Session V High-Performance Numerical Libraries/Solvers and Statistical Computing (chair: Reiji Suda)

  • Prof. Kegno Nakajima (The University of Tokyo)

Numerical Library with High-Performance/Adaptive-Precision/High-Reliability: Extension of ppOpen-HPC towards the Post Moore Era

  • Prof. Juni Nakano (The Institute of Statistical Mathematics)

A package for multiple precision arithmetic on R for statistical computing

§  Prof. Satoshi Ohshima (Kyushu University)

Trying to accelerate many small BLAS calculations on GPU

  • Prof. Jong Shinn Wu (National Chiao Tung University)

A Parallel Computational Platform for General PDE Solvers Using Unstructured-Grid Finite-    Volume Method – ultraMPP

 

10:30 – 10:50 Intermission


10:50 - 12:10 Session VI Advanced Methods for Differential Equations and Its Applications

(chair: Chieh-Sen Huang)

  • Prof. Jong Shinn Wu (National Chiao Tung University)

A Parallel Scientific Computing Platform: RAPIT( Rigorous Advanced Plasma Integration Testbed)

  • Prof. Feng-Nan Hwang (National Central University)

A nonlinear elimination preconditioner for fully coupled space-time solution algorithm with applications to high-Rayleigh number thermal convective flow problems

  • Prof. How-Wei Chen (National Central University)

Computational Challenges in Solid Earth System Studies – Lessons Learned and Where to Go?

  • Prof. Chin-Tien Wu (National Chiao Tung University)
    A study in image denoise and deblur

 

12:10 – 13:30 Closing and Lunch (Prof. Reiji Suda /The University of Tokyo )




Comments