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
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)
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
Download the Program Booklet PDF
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 )
Conference Registration
Poster