Kyushu University Academic Staff Educational and Research Activities Database
Researcher information (To researchers) Need Help? How to update
Kenji Ono Last modified date:2023.11.27

Professor / Graduate School and Faculty of Information Science and Electrical Engineering, Department of Informatics
Section of Applied Data Science
Research Institute for Information Technology

Graduate School
Undergraduate School
Other Organization
Administration Post

E-Mail *Since the e-mail address is not displayed in Internet Explorer, please use another web browser:Google Chrome, safari.
 Reseacher Profiling Tool Kyushu University Pure
Academic Degree
Dr. Eng.
Country of degree conferring institution (Overseas)
Field of Specialization
Computational Fluid Dynamics, Visualization, High-performance parallel computing
ORCID(Open Researcher and Contributor ID)
Total Priod of education and research career in the foreign country
Outline Activities
Research – Computational fluid dynamics simulation, Visualization, Parallel computing;

Education – Numerical analysis and its exercise;

Service – Operation and support of supercomputers;

Others – Commissioned project of science and technology research funded by MEXT, CREST, JHPCN;
Research Interests
  • Research and development for in-situ / in-transit visualization / data processing infrastructure
    keyword : visualization system, parallel processing, usability, remote processing
  • Finding natural lows from data using deep learning
    keyword : Deep learning, Genetic programming, Lasso
  • Interaction between real world and virtual world through VR/AR technology
    keyword : HMD, UI
  • Reconstruction of turbulent model using machine learning
    keyword : Deep learning, LES turbulence modeling, CFD
  • Research of parallel computing method in time integration
    keyword : multi-grid algorithm in time, parareal method
  • Research and development of technologies for upstream design
    keyword : Derivation of idea
  • Research of large-scale parallel grid generation
    keyword : CAD data, geometry, CFD
  • Construction of an environment to support execution of simulation
    keyword : workflow, data management, multi-platform, eco-system
  • Technology development of large-scale parallel visualization system
    keyword : sort-last image compositing, ray tracing, multi-platform, data model
  • Development of thermal flow simulator for flow around complex geometries
    keyword : Cartesian mesh, Mesh generation
Current and Past Project
  • Develop an integrated framework to manage various data to design products, analytic tools to extract data by various methods, and useful display technology to visualize information. Then, apply the developed system to validation cases, and confirm effectiveness.
Academic Activities
1. Shiyao Xie, Akinori Miura, Kenji Ono, Error-bounded Scalable Parallel Tensor Train Decomposition, 25th Workshop on Advances in Parallel and Distributed Computational Models to be held in conjunction with 37th IEEE International Parallel and Distributed Processing Symposium IPDPS May 15-19, 2023, St. Petersburg, Florida, USA, 2023.05.
2. T. Mitsuda, K. Ono, A Scalable Parallel Partition Tridiagonal Solver for Many-Core and Low B/F Processors, 2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 10.1109/IPDPSW55747.2022.00142, 860-869, 2022.06.
3. Hagita, Katsumi, Murashima, Takahiro, Ogino, Masao, Omiya, Manabu, Ono, Kenji, Deguchi, Tetsuo, Jinnai, Hiroshi and Kawakatsu, Toshihiro, Efficient compressed database of equilibrated configurations of ring-linear polymer blends for MD simulations, Scientific Data,, 9, 40, 2022.02, To effectively archive configuration data during molecular dynamics (MD) simulations of polymer systems, we present an efficient compression method with good numerical accuracy that preserves the topology of ring-linear polymer blends. To compress the fraction of floating-point data, we used the Jointed Hierarchical Precision Compression Number - Data Format (JHPCN-DF) method to apply zero padding for the tailing fraction bits, which did not affect the numerical accuracy, then compressed the data with Huffman coding. We also provided a dataset of well-equilibrated configurations of MD simulations for ring-linear polymer blends with various lengths of linear and ring polymers, including ring complexes composed of multiple rings such as polycatenane. We executed 109 MD steps to obtain 150 equilibrated configurations. The combination of JHPCN-DF and SZ compression achieved the best compression ratio for all cases. Therefore, the proposed method enables efficient archiving of MD trajectories. Moreover, the publicly available dataset of ring-linear polymer blends can be employed for studies of mathematical methods, including topology analysis and data compression, as well as MD simulations..
4. Issei Koga, Kenji Ono, Effective Pre-processing of Genetic Programming for Solving Symbolic Regression in Equation Extraction, Communications in Computer and Information Science, 1040, 89-103, 2019.08, Estimating a form of equation that explains data is very useful to understand various physical, chemical, social, and biological phenomena. One effective approach for finding the form of an equation is to solve the symbolic regression problem using genetic programming (GP). However, this approach requires a long computation time because of the explosion of the number of combinations of candidate functions that are used as elements to construct equations. In the present paper, a novel method to effectively eliminate unnecessary functions from an initial set of functions using a deep neural network was proposed to reduce the number of computations of GP. Moreover, a method was proposed to improve the accuracy of the classification using eigenvalues when classifying whether functions are required for symbolic regression. Experiment results showed that the proposed method can successfully classify functions with over 90{\%} of the data created in the present study..
5. Kenji Ono, Takanori Uchida, High-Performance Parallel Simulation of Airflow for Complex Terrain Surface, Modelling and Simulation in Engineering, 10.1155/2019/5231839, 2019, 2019.02, It is important to develop a reliable and high-throughput simulation method for predicting airflows in the installation planning phase of windmill power plants. This study proposes a two-stage mesh generation approach to reduce the meshing cost and introduces a hybrid parallelization scheme for atmospheric fluid simulations. The meshing approach splits mesh generation into two stages: in the first stage, the meshing parameters that uniquely determine the mesh distribution are extracted, and in the second stage, a mesh system is generated in parallel via an in situ approach using the parameters obtained in the initialization phase of the simulation. The proposed two-stage approach is flexible since an arbitrary number of processes can be selected at run time. An efficient OpenMP-MPI hybrid parallelization scheme using a middleware that provides a framework of parallel codes based on the domain decomposition method is also developed. The preliminary results of the meshing and computing performance show excellent scalability in the strong scaling test..
6. Tomohiro Kawanabe, Jorji Nonaka, Kenji Ono, Chowder
Dynamic contents sharing through remote tiled display system, 11th International Symposium on Visual Information Communication and Interaction, VINCI 2018 VINCI 2018 - 11th International Symposium on Visual Information Communication and Interaction, 10.1145/3231622.3232504, 108-109, 2018.08, Due to the continuous increase in the scale of numerical simulations, research on visualization has shifted to in-situ/in-transit approaches. The interactivity of large-scale visualization has also become increasingly important. In order to observe large-scale visualization data in detail, high-resolution displays, such as those with 8K or 16K resolutions, give an opportunity to inspire new discovery. With the commoditization of high-resolution displays, tiled display walls (TDWs) have facilitated their use for the collaborative research, where a large screen size is required for sharing the content among multiple sites. In this paper, we propose a remote collaboration method that utilizes a TDW driver (ChOWDER), which enables content sharing among multiple sites even with different display configurations, and a visualization application (HIVE) for dynamic content sharing of interactive visualization results..
7. Mikio Iizuka, Kenji Ono, Influence of the phase accuracy of the coarse solver calculation on the convergence of the parareal method iteration for hyperbolic PDEs, Computing and Visualization in Science, 2018.05.
8. Tomohiro Kawanabe, Jorji Nonaka, Kazuma Hatta, Kenji Ono, ChOWDER
An adaptive tiled display wall driver for dynamic remote collaboration, 15th International Conference on Cooperative Design, Visualization, and Engineering, CDVE 2018 Cooperative Design, Visualization, and Engineering - 15th International Conference, CDVE 2018, Proceedings, 10.1007/978-3-030-00560-3_2, 11-15, 2018.01, Herein, we propose a web-based tiled display wall (TDW) system that is capable of supporting collaborative activities among multiple remote sites. Known as the Cooperative Workspace Driver (ChOWDER), this system introduces the virtual display area (VDA) concept as a method for handling various display configuration environments with different physical resolutions and aspect ratios. This concept, which is one of ChOWDER’s key features, allows ad hoc participation among multiple sites to facilitate remote collaboration and cooperative work..
9. Fan Hong, Chongke Bi, Hanqi Guo, Kenji Ono, Xiaoru Yuan, Compression-based integral curve data reuse framework for flow visualization, Journal of Visualization, 10.1007/s12650-017-0428-4, 20, 4, 859-874, 2017.11, [URL], Currently, by default, integral curves are repeatedly re-computed in different flow visualization applications, such as FTLE field computation, source-destination queries, etc., leading to unnecessary resource cost. We present a compression-based data reuse framework for integral curves, to greatly reduce their retrieval cost, especially in a resource-limited environment. In our design, a hierarchical and hybrid compression scheme is proposed to balance three objectives, including high compression ratio, controllable error, and low decompression cost. Specifically, we use and combine digitized curve sparse representation, floating-point data compression, and octree space partitioning to adaptively achieve the objectives. Results have shown that our data reuse framework could acquire tens of times acceleration in the resource-limited environment compared to on-the-fly particle tracing, and keep controllable information loss. Moreover, our method could provide fast integral curve retrieval for more complex data, such as unstructured mesh data..
10. Seigo Imamura, Kenji Ono, Mitsuo Yokokawa, Iterative-method performance evaluation for multiple vectors associated with a large-scale sparse matrix, International Journal of Computational Fluid Dynamics, 10.1080/10618562.2016.1234046, 30, 6, 395-401, 2016.07, Ensemble computing, which is an instance of capacity computing, is an effective computing scenario for exascale parallel supercomputers. In ensemble computing, there are multiple linear systems associated with a common coefficient matrix. We improve the performance of iterative solvers for multiple vectors by solving them at the same time, that is, by solving for the product of the matrices. We implemented several iterative methods and compared their performance. The maximum performance on Sparc VIIIfx was 7.6 times higher than that of a naïve implementation. Finally, to deal with the different convergence processes of linear systems, we introduced a control method to eliminate the calculation of already converged vectors..
1. Kenji Ono, Toshihiro Kato, Satoshi Ohshima, Takeshi Nanri, Scalable Direct-Iterative Hybrid Solver for Sparse Matrices on Multi-Core and Vector Architectures, International Conference on High Performance Computing in Asia-Pacific Region, 2019.12, In the present paper, we propose an efficient direct-iterative hybrid solver for sparse matrices that can derive the scalability of the latest multi-core, many-core, and vector architectures and examine the execution performance of the proposed SLOR-PCR method.
We also present an efficient implementation of the PCR algorithm for SIMD and vector architectures so that it is easy to output instructions optimized by the compiler.
The proposed hybrid method has high cache reusability, which is favorable for modern low B/F architecture because efficient use of the cache can mitigate the memory bandwidth limitation.
The measured performance revealed that the SLOR-PCR solver showed excellent scalability up to 352 cores on the cc-NUMA environment, and
the achieved performance was higher than that of the conventional Jacobi and Red-Black ordering method by a factor of 3.6 to 8.3 on the SIMD architecture.
In addition, the maximum speedup in computation time was observed to be a factor of 6.3 on the cc-NUMA architecture with 352 cores..
2. Seigo Imamura, Mikio Iizuka, Kenji Ono, Mitsuo Yokokawa, Building the Performance Model of Parareal Method, 28th International Conference on Parallel Computational Fluid Dynamics Parallel CFD2016, 2016.05.
3. Mikio Iizuka, Kenji Ono, Convergence Rate of Parareal Method with Modified Newmark-Beta Algorithm for 2nd-Order ODE, 17th SIAM Conference on Parallel Processing for Scientific Computing, 2016.04.
Membership in Academic Society
  • Association for Computing Machinery
  • Information Processing Society of Japan
  • The Japan Society for Computational Engineering and Science
  • The Japan Society of Mechanical Engineers
  • The Japan Society of Fluid Mechanics
  • IEEE