Yasushi Inoguchi Professor
Research Center For Advanced Computing Infrastructure
B.E. degree from Tohoku University(1991), M.S. degree from JAIST(1994), Ph.D. degree from JAIST(1997)
2008/4/1-2009/3/31University of South FloridaCourtesy Senior Research Scholar
Massively Parallel Computers, Interconnection of Multi-processor Systems, Fault-Tolerant and Thermal Analysis of WSI stacks.
Massively Parallel, Computer Architecture, Reconfigurable System, e-Learning
Interconnection networks for Massively Parallel Computer
Multiprocessor systems consisting of millions of processing elements have been expected to solve advanced scientific and engineering problems in the next decade. Since the interconnection network is one of the critical components of multiprocessor systems, they are required network feature such as smaller diameter, easy VLSI implementation, fault-tolerant schemes, and good expandability. We are studying hierarchical interconnection network named as Shifted Recursive Torus (SRT) for scientific computing, and discuss network performance, routing algorithms, and fault-tolerant schemes.
Cooling Schemes for 3D Stacked Implementation
For 3D Stacked Implementation systems, cooling is one of the most crucial problems to implement massively parallel systems. On the other hand, the reconfiguration to avoid defects on wafers is also important for wafer scale integration systems and some unused processing elements (PEs) are remained as a result of reconfiguration. Since operative PEs generate heavy heat but unused PEs generate no heat, we can cool the stacks replacing these PEs. We are studying reconfiguration algorithms for Shifted Recursive Torus (SRT) network in 3D stacked implementation by considering thermo-radiation in stacked wafers implementation. We discuss cooling schemes for SRT networks to keep highly cooling network performance in stacked wafers implementation. Cooling approaches have been proposed for SRT in stacked implementation. Introducing a thermo-radiation model into SRT in stacked implementation, cooling and reconfiguration performance of SRT is evaluated.
Multi-port Memory Computer Architectures
It is important for multiprocessor systems to increase communication speed between processing elements. We discuss a hypercube multiprocessor based on a multiport memory which is able to reduce the communication overhead. A prototype multiprocessor system is constructed to evaluate the communication performance of a multiport memory scheme. It is confirmed that high communication performance is realized by prototype system consisting of multiport memory.
Ultra fine grained parallel processing by hard ware programming
Logical circuits on a VLSI chip operate in parallel essentially because sub-circuits on the chip execute their functions independently. Thus, ultra fine grade parallel processing can be achieved if operators in a software algorithm can be spread as parallel arithmetic circuits on these VLSI chips.In this research, a scheme is examined that extract operator level parallelism from a software algorithm, compile them to hardware description language, and implement the algorithm as parallel arithmetic units on hardware circuits directly.
- Hierarchical Interconnection Networks for Massively Parallel Computer Systems，M.M. Hafizur Rahman and Yasushi Inoguchi，LAMBERT，2011，212 pages
- Lecture Notes in Computer Science, Session 6A: Grid Scheduling and Algorithms II, Dynamic Task Scheduling Algorithm for Grid Computing System，Yuanyuan Zhang, Yasushi Inoguchi and Hong Shen，Springer，2005，578-583
- Reconfiguration and Yield of a Hierarchical Torus Network，M.M. Hafizur Rahman, Masaru Fukushi and Yasushi Inoguchi，IETE Technical Review，30，1， (accepted)
- Evaluating Reconfigurable Dataflow Computing Using the Himeno Benchmark，Yukinori Sato, Yasushi Inoguchi, Wayne Luk and Tadao Nakamura，Proceedings of International Conference on ReConFigurable Compuring and FPGAs， (accepted)
- Whole Program Data Dependence Profiling to Unveil Parallel Regions in the Dynamic Execution，Yukinori Sato, Yasushi Inoguchi and Tadao Nakamura，2012 IEEE International Symposium on Workload Characterization，(accepted)
◇Lectures and Presentations
- Evaluating Reconfigurable Dataflow Computing Using the Himeno Benchmark，Yukinori Sato, Yasushi Inoguchi, Wayne Luk and Tadao Nakamura，Proceedings of International Conference on ReConFigurable Compuring and FPGAs，Cancun, Mexico，(accepted)
- Whole Program Data Dependence Profiling to Unveil Parallel Regions in the Dynamic Execution，Yukinori Sato, Yasushi Inoguchi and Tadao Nakamura，2012 IEEE International Symposium on Workload Characterization，San Diego, USA，(accepted)
- Analysis of Sound Field Distibution for Room Acoustic: Ffom the Point of View of Hardware Implementation，Tan Yiyu, Yasushi Inoguchi, Yukinori Sato, Makoto Otani, Yukio Iwaya, Hiroshi Matsuoka and Takao Tsuchiya，Proceedings of 15th International Conference on Digital Audio Effects DAFx-12，York, U.K.，Sep., 2012
◇Academic Society Affiliations
- IEICE，Editor，IEICE TRANSACTIONS on Info. and Sys., E96-D, Special Section on Reconfigurable Systems，2012-2013
- IEICE Special Section on Parallel/Distributed Processing and Systems，Editor，2005-2006