• My research interests include the design and development of high-performance supercomputing systems and their applications. Targeted areas range from the key components of supercomputing systems, which include processor architectures, memory subsystems, network systems, task schedulers, and compilers, to high-performance multimedia processing algorithms such as photo-realistic computer graphics.

Currently I am conducting joint-research projects with several companies in the fields of high-performance computer architecture design and advanced simulation technologies for industrial design such as next-generation supercomputers and highly efficient and comfortable regional jets.

• As modern supercomputers are getting larger and more complicated, it is not so easy to exploit their potential performance. It is necessary to develop a simulation code with considering various factors for both hardware and software reasons, and hence expert knowledge and experiences about supercomputing are often needed to achieve high actual performance. Our research interests focus on shaping future supercomputing systems and their applications, especially system software technologies for effectively using the future supercomputers. Also we are always exploring how to make good use of the state-of-the-art hardware and software technologies in order to enable unprecedented-scale and more advanced simulations.
• From beginning (apply for use of our supercomputer) to end (get a solution), we can consistently support developing large-scale practical simulation, which is feasible only by using the supercomputer. As a supercomputing center, we have a long history of parallelizing and accelerating a lot of practical simulation programs. In addition, we are looking for research collaborators who are interested in streamlining and/or facilitating large-scale scientific software development.

• We will develop a brainmorphic computing hardware, which realizes the brain-specific functions such as conscious/sub-conscious process, self, selective attention, and so on, by directly using inherent physics and dynamics of constituent devices. The resulting hardware would be small, efficient, high-performance. Some examples include the chaotic neural network reservoir, optimization through high-dimensional complex dynamics, and neural network composed of spin-orbit torque nano-devices.
• The resulting hardware is suitable for the edge AI which learns users’ personal behavior. Examples include watching service devices embedded in hearing aids or dental implants, which monitor and learn personal cardiac and brain-wave signals or saliva ingredients, to detect abnormal situations.

Edge AI devices, especially for peri-personal space), Time-series processing (prediction, recognition, and categorization), Online real-time learning.

• We are investigating high-speed vision systems that enable real-time image acquisition and visual processing at frame rates substantially higher than the standard video rate.

High-speed vision systems are useful for fast measurement and control of dynamic systems in general. When combined with external facilities such as high-speed projectors or acceleration sensors, they enable further wider applications including fast 3D measurement or object identification.

• We are investigating high-speed vision systems that enable real-time image acquisition and visual processing at frame rates substantially higher than the standard video rate.

High-speed vision systems are useful for fast measurement and control of dynamic systems in general. When combined with external facilities such as high-speed projectors or acceleration sensors, they enable further wider applications including fast 3D measurement or object identification.