Rchr
J-GLOBAL ID：200901026240318544
Update date: Dec. 11, 2024
Hanawa Toshihiro
ハナワ トシヒロ | Hanawa Toshihiro
Affiliation and department：
Other affiliations (2)：
Homepage URL (1)：
https://www.cspp.cc.u-tokyo.ac.jp/hanawa/
Research field (2)：
High-performance computing
, Computer systems
Research keywords (7)：
Accelerator computing
, High performance computing
, Computer architecture
, 大規模ディープラーニング
, Manycore system
, HPCシステム向け通信機構
, Interconnection Networks for High Performance Computing Systems
Research theme for competitive and other funds (16)：
- 2023 - 2027 Next-generation high-performance linear solver for future computational science and engineering
- 2021 - 2024 Construction of numerical linear algebra based on lattice H-matrices and its high-performance implementation on modern architectures
- 2020 - 2023 余剰コアを活用する高性能計算・データ解析支援
- 2019 - 2022 High performance linear solver for advanced computational electromagnetics
- 2018 - 2021 High performance computing platform by GPU and FPGA
- 2015 - 2019 Research on Integration of Communication and Computation by Tightly Coupled Accelerators
- 2011 - 2013 演算加速装置向け低遅延高バンド幅通信機構
- 2011 - 2013 Interconnection Network for Tightly Coupled Accelerators
- 2009 - 2011 ディペンダブルな並列・分散システムのテスト環境を提供するクラウドコンピューティングシステム
- 2009 - 2011 Cloud computing system offering a system testing environment for dependable parallel and distributed system
- 2007 - 2011 ディペンダブルシステムのためのベンチマーク
- 2007 - 2011 組込み向けマルチコアプロセッサ・小規模クラスタにおける並列プログラミング手法および省電力化手法
- 2007 - 2011 省電力耐故障高性能通信機構
- 2007 - 2011 Benchmark for Dependable System
- 2007 - 2011 Parallel Programing and Power awareness using multicore processor for embedded system and small scale cluster
- 2007 - 2011 Low-power, high-performance and dependable communication mechanism
Show all
Papers (356)：
-
Yohei Miki, Toshihiro Hanawa. Unified Schemes for Directive-Based GPU Offloading. IEEE Access. 2024
-
Toshihiro Hanawa, Kengo Nakajima, Yohei Miki 0001, Takashi Shimokawabe, Kazuya Yamazaki, Shinji Sumimoto, Osamu Tatebe, Taisuke Boku, Daisuke Takahashi, Akira Nukada, et al. Preliminary Performance Evaluation of Grace-Hopper GH200. CLUSTER Workshops. 2024. 184-185
-
Shinji Sumimoto, Toshihiro Hanawa, Kengo Nakajima. MPI-Adapter2: An Automatic ABI Translation Library Builder for MPI Application Binary Portability. HPC Asia Workshops. 2024. 63-68
-
Masatoshi Kawai, Akihiro Ida, Toshihiro Hanawa, Tetsuya Hoshino. Optimize Efficiency of Utilizing Systems by Dynamic Core Binding. HPC Asia Workshops. 2024. 77-82
-
Shinji Sumimoto, Takashi Arakawa, Yoshio Sakaguchi, Hiroya Matsuba, Hisashi Yashiro, Toshihiro Hanawa, Kengo Nakajima. A System-Wide Communication to Couple Multiple MPI Programs for Heterogeneous Computing. Parallel and Distributed Computing, Applications and Technologies. 2023. 314-327
ｍore...
MISC (28)：
-
住元真司, 荒川隆, 坂口吉生, 松葉浩也, 松葉浩也, 八代尚, 大島聡史, 塙敏博, 中島研吾, 中島研吾. WaitIOのRDMAによる通信高速化. 情報処理学会研究報告(Web). 2024. 2024. HPC-194
-
塙敏博, 塙敏博, 塙敏博, 建部修見, 建部修見, 中島研吾, 中島研吾, 朴泰祐, 朴泰祐, 三木洋平, et al. GH200の予備性能評価. 情報処理学会研究報告(Web). 2024. 2024. HPC-195
-
星野哲也, 河合直聡, 伊田明弘, 塙敏博, 片桐孝洋. HPCカーネルベンチマークによるSapphire Rapids HBMの性能評価. 情報処理学会研究報告(Web). 2024. 2024. HPC-193
-
住元真司, 塙敏博, 中島研吾, 中島研吾. MPI-Adapter2:異なるMPIライブラリ間でのアプリケーション実行を実現するABI変換ライブラリ. 情報処理学会研究報告(Web). 2023. 2023. HPC-188
-
住元真司, 塙敏博, 中島研吾, 中島研吾. コンテナによるジョブ可搬性実現とファイルアクセス高速化. 情報処理学会研究報告(Web). 2023. 2023. HPC-190
ｍore...
Patents (3)：
Books (4)：
-
Advanced Software Technologies for Post-Peta Scale Computing: The Japanese Post-Peta CREST Research Project
Springer 2018
-
ソフトウェアデザイン2月号
技術評論社 2010
-
Beyond Loop Level Parallelism in OpenMP: Accelerators, Tasking and More
Lecture Notes in Computer Science 6132, Springer Verlag 2010
-
Beyond Loop Level Parallelism in OpenMP: Accelerators, Tasking and More
Lecture Notes in Computer Science 6132, Springer Verlag 2010
Lectures and oral presentations (4)：
-
An Optimization of H-matrix-vector Multiplication by Using Un-used Cores
(HPC Asia 2020 2020)
-
Introduction of HPCI Shared Storage that has Achieved Year-Round Non-Stop Operation
(HPC Asia 2020)
-
Numerical Linear Algebra Based on Lattice H-Matrices
(HPC Asia 2020)
-
DNN Training Using Multiple GPUs for Medical Image Recognition
(HPC Asia 2020)
Education (3)：
- 1995 - 1998 Keio University Graduate School, Division of Science and Engineering Department of Computer Science
- 1993 - 1995 Keio University
- 1989 - 1993 Keio University Faculty of Science and Engineering Department of Electrical Engineering
Professional career (1)：
Work history (11)：
- 2021/11 - 現在 University of Tsukuba Center for Computational Sciences Guest Professor
- 2021/04 - 現在 The University of Tokyo Collaborative Research Organization for Intergrative Medical Genomics and Informatics Professor (Concurrent post)
- 2020/12 - 現在 The University of Tokyo The Graduate School of Engineering Department of Electrical Engineering and Information Systems Professor (Concurrent post)
- 2020/12 - 現在 The University of Tokyo Information Technology Center Professor
- 2015/04 - 2021/10 University of Tsukuba Center for Computational Sciences Guest Associate Professor
- 2016/02 - 2020/11 The University of Tokyo The Graduate School of Engineering Department of Electrical Engineering and Information Systems Associate Professor (Concurrent Post)
- 2015/12 - 2020/11 The University of Tokyo Information Technology Center Associate Professor
- 2013/12 - 2015/11 The University of Tokyo Information Technology Center Project Associate Professor
- 2011/10 - 2013/11 University of Tsukuba Faculty of Engineering, Information and Systems Associate Professor
- 2008/12 - 2011/09 University of Tsukuba Graduate School of Systems and Information Engineering Associate Professor
- 2007/04 - 2008/11 University of Tsukuba Center for Computational Sciences Research Fellow
Show all
Committee career (2)：
- 2019/04 - 現在 情報処理学会 ACS論文誌編集委員
- 2017/04 - 2021/03 情報処理学会 ハイパフォーマンスコンピューティング研究会運営委員
Awards (15)：
- 2024/08 - xSIG Best Master Student's Award GPU直接IOを用いたファイルIOの高速化
- 2022/12 - PDCAT2022 Best Paper Award A System-Wide Communication to Couple Multiple MPI Programs for Heterogeneous Computing
- 2022/07 - 産経新聞社 第35回(2022年度)独創性を拓く 先端技術大賞 経済産業大臣賞 大規模深層学習のための自動並列処理ソフトウェアRaNNC
- 2021/12 - Facebook 1st place, winner of PyTorch Developer Tools, PyTorch Annual Hackathon 2021 RaNNC (Rapid Neural Network Connector)
- 2021/07 - xSIG Best Master's Student Award Transprecision Calculation Platform Offloaded on FPGA
- 2021/05 - 情報処理学会 コンピュータサイエンス領域奨励賞 余剰コアの活用に向けた実行中プロファイリング手法の検討
- 2016 - 情報処理学会ハイパフォーマンスコンピューティングと計算科学シンポジウム 最優秀論文賞 密結合並列演算加速機構TCAによるGPU対応GASNetの実装と評価
- 2016 - Outstanding Research Award A proposal of GMPI: GPU self MPI for GPU clusters
- 2015 - Intel Heterogeneous Accelerator Research Platform (HARP) program
- 2014 - 情報処理学会 山下記念研究賞 Tightly Coupled Accelerators アーキテクチャ向け通信機構の予備評価
- 2014 - HPC in Asia workshop, International Supercomputing Conference Best Poster Award Proprietary Interconnect with Low Latency for HA-PACS/TCA
- 2014 - International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies (HEART 2014) Best Paper Award PEACH2: FPGA based PCIe network device for Tightly Coupled Accelerators
- 2011 - CoolChips XIV Best Feature Award PEACH: A Communication SoC for PCI Express Direct Link
- 1998/03 - 慶應義塾大学理工学部・大学院理工学研究科 藤原賞
- 1996 - 情報処理学会 平成7年度情報処理学会論文賞 多重出力可能なMINの性能評価
Show all
Association Membership(s) (2)：
IEEE Computer Society
, INFORMATION PROCESSING SOCIETY OF JAPAN
