このページでは本研究室のメンバーが関わった成果の一覧を示しています．

2021年度

学術論文誌

• Shunsuke Tsukada, Hikaru Takayasihki, Masayuki Sato, Kazuhiko Komatsu, Hiroaki Kobayashi, “A Metadata Prefetching Mechanism for Hybrid Memory Architectures,“ IEICE Transactions on Electronics, 2021. (Accepted)
• Bin Qi, Kazuhiko Komatsu, Masayuki Sato, Hiroyuki Kobayashi, “A Dynamic Parameter Tuning Method for SpMM Parallel Execution,“ Concurrency and Computation: Practice and Experience, e6755, 2021. [DOI: 10.1002/cpe.6755]
• Kazuhiko Komatsu, Hironori Miyazawa, Cheng Yiran, Masayuki Sato, Takashi Furusawa, Satoru Yamamoto, and Hiroaki Kobayashi, “Detection of Machinery Failure Signs From Big Time-Series Data Obtained by Flow Simulation of Intermediate-Pressure Steam Turbines,“ Journal of Engineering for Gas Turbines and Power, Vol. 144, No. 1, pp.1–9, Oct. 2021. [DOI: 10.1115/1.4052142]
• Komatsu, Kazuhiko, Akito Onodera, Erich Focht, Soya Fujimoto, Yoko Isobe, Shintaro Momose, Masayuki Sato, Hiroaki Kobayashi. “Performance and Power Analysis of a Vector Computing System.” Journal of Supercomputing Frontiers and Innovations, Vol. 8, No. 2, pp.75–94, 2021. [DOI: 10.14529/jsfi210205]
• Osamu Watanabe, Kazuhiko Komatsu, Masayuki Sato, Hiroaki Kobayashi, “Optimizing Load Balance in a Parallel CFD Code for a Large-Scale Turbine Simulation on a Vector Supercomputer,” Journal of Supercomputing Frontiers and Innovations, Vol. 8, No. 2, pp.114–130, 2021. [DOI: 10.14529/jsfi210207]
• Ilya V. Afanasyev, Vadim V. Voevodin, Kazuhiko Komatsu, Hiroaki Kobayashi, “Distributed Graph Algorithms for Multiple Vector Engines of NEC SX-Aurora TSUBASA Systems,”  Supercomputing Frontiers and Innovations, 8(2):95-113, September 2021. doi: 10.14529/jsfi210206
• Masahito Kumagai, Kazuhiko Komatsu, Fumiyo Takano, Takuya Araki, Masayuki Sato, Hiroaki Kobayashi, “An External Definition of the One-Hot Constraint and Fast QUBO Generation for High-Performance Combinatorial Clustering,” International Journal of Networking and Computing, Vol. 11, No. 2, pp.463–491, 2021. [DOI: 10.15803/ijnc.11.2_463]
• Hao Tang, Kazuhiko Komatsu, Masayuki Sato, Hiroaki Kobayashi, “Efficient Mixed-Precision Tall-and-Skinny Matrix-Matrix Multiplication for GPUs,” International Journal of Networking and Computing, 11(2):267-282, July 2021. doi: 10.15803/ijnc.11.2_267
• Ohno, K., Y. Ohta, S. Kawamoto, S. Abe, R. Hino, S. Koshimura, A. Musa, and H. Kobayashi (2021), Real ‑ time automatic uncertainty estimation of coseismic single rectangular fault model using GNSS data, Earth, Planets Space., 73(127), 1–18, 2021

国際会議

• Masahito Kumagai, Kazuhiko Komatsu, Masayuki Sato, Hiroaki Kobayashi, “Ising-based Combinatorial Clustering using the Kernel Method,” In Proceedings of 2021 IEEE 14th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC), pp.197–203, December 2021. [DOI: 10.1109/MCSoC51149.2021.00037]
• He Zhilin, Kazuhiko Komatsu, Masayuki Sato, Hiroaki Kobayashi, “Optimizations of a Linear Matrix Solver in a Composite Simulation for a Vector Computer,” In Proceedings of the 12th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP), December 2021.
• Kazuhiko Komatsu, Masahito Kumagai, Ji Qi, Masayuki Sato, Hiroaki Kobayashi, “An Externally-Constrained Ising Clustering Methodfor Material Informatics,” In Proceedings of 2021 Nineth International Symposium on Computing and Networking Workshops (CANDARW), pages 201-204, November 2021. doi: 10.1109/CANDARW53999.2021.00040
• Hikaru Takayashiki, Masayuki Sato, Kazuhiko Komatsu, Hiroaki Kobayashi, “Register Flush-free Runahead Execution for Modern Vector Processors” In Proceedings of IEEE 33rd International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), pp.114–125, October 2021. [DOI: 10.1109/SBAC-PAD53543.2021.00023]
• Kazuhiko Komatsu, Hironori Miyazawa, Cheng Yiran, Masayuki Sato, Takashi Furusawa, Satoru Yamamoto, Hiroaki Kobayashi, “Detection of Machinery Failure Signs From Big Time-Series Data Obtained by Flow Simulation of Intermediate-Pressure Steam Turbines,“ In Proceedings of ASME Turbo Expo, pp.1–11, June 2021. [DOI: 10.1115/GT2021-58698]
• Kou Murakami, Kazuhiko Komatsu, Masayuki Sato, Hiroaki Kobayashi, “A Processor Selection Method based on Execution Time Estimation for Machine Learning Programs,” In Proceedings of 2021 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pages 779-788, June 2021. doi: 10.1109/IPDPSW52791.2021.00116
• Shunsuke Tsukada, Hikaru Takayashiki, Masayuki Sato, Kazuhiko Komatsu, Hiroaki Kobayashi, “A Metadata Prefetching Mechanism for Hybrid Memory Architectures,” In Proceedings of IEEE Symposium in Low-Power and High-Speed Chips (COOL CHIPS), pp.1–3, April 2021. [DOI: 10.1109/COOLCHIPS52128.2021.9410321]
• Yuta Hougi, Kazuhiko Komatsu, Osamu Watanabe, Masayuki Sato, Hiroaki Kobayashi, “A hierarchical wavefront method for LU-SGS on modern multi-core vector processors,” In Proceedings of International Conference on Parallel Computational Fluid Dynamics 2020-2021, May 2021.
• Yujiro Takenaka, Mitsuo Yokokawa, Takashi Ishihara, Kazuhiko Komatsu, Hiroaki Kobayashi, “Performance Evaluation of Parallel DNS Codes on the Supercomputer SX-Aurora TSUBASA,” International Conference on Parallel Computational Fluid Dynamics 2020-2021, May 2021.

招待講演

• Hiroaki Kobayashi, The New Era of Hybrid-Computing:  Vector-Scalar to Vector-Digital Annealing,  to Vector-Quantum Annealing, Russian Supercomputing Days, September 27, 2021.
• Hiroaki Kobayashi, The New Era of Hybrid-Computing on and with SX-Aurora TSUBASA: Vector-Scalar to Vector-Digital Annealing, to Vector-Quantum Annealing, the 31st Workshop on Sustained Simulation Performance, March 16, 2021.
• 小林広明，”量子アニーリングが拓く新しいＨＰＣの世界”, 量子コンピューティングEXPO, 2021.4.5.

報道等

• NHKサイエンスゼロ (3月14日）, NHK 全国ニュース（3月14日, 午後3時，午後7時）
• 日経エレクトロニクス、”津波から避難経路を提示:D-Waveマシンなどが0.02秒で”，　2021年9月号．
• 日経新聞 “火力発電の損傷予測 東北大など、修繕時期把握 https://www.nikkei.com/nkd/industry/article/?DisplayType=1&n_m_code=012&ng=DGKKZO76631910U1A011C2TEC000”, 2021年10月15日

プレスリリース

• 東北大学とNEC、スーパーコンピュータを活用した 発電用ガスタービンの数値シミュレーション高速化技術を開発 ～高速かつ高精度なデジタルツインシミュレーションを実現し、 電力の安定供給と発電効率の向上に貢献～ http://www.tohoku.ac.jp/japanese/2021/10/press20211015-01-turbine.html, 2021年10月15日

特許

• 岡部朋永，小林広明，菊川豪太，小松一彦（以上，東北大），鍬守直樹，撫佐昭裕，風間悠加，瀧川陽平，佐藤佳彦（以上，NEC），物性マップ画像生成装置、制御方法、及びプログラム, 特願2021-044488, 出願日2021年3月18日.
• 岡部朋永，小林広明，菊川豪太，小松一彦（以上，東北大），鍬守直樹，撫佐昭裕，風間悠加，瀧川陽平，佐藤佳彦（以上，NEC），特異材料検出装置、制御方法、及びプログラム, 特願2021-044487, 出願日2021年3月18日.
• 岡部朋永，小林広明，菊川豪太，小松一彦（以上，東北大），鍬守直樹，撫佐昭裕，風間悠加，瀧川陽平，佐藤佳彦（以上，NEC），マップ画像生成装置、制御方法、及びプログラム，特願2021-044486, 2021年3月18日.
• 岡部朋永，小林広明，菊川豪太，小松一彦（以上，東北大），鍬守直樹，撫佐昭裕，風間悠加，瀧川陽平，佐藤佳彦（以上，NEC），推奨データ生成装置、制御方法、及びプログラム, 特願2021-044485, 2021年3月18日.

受賞・受章

• 深水一聖，情報処理学会全国大会優秀学生発表賞
• 深水一聖，情報処理学会東北支部学生奨励賞
• 熊谷政仁，情報科学研究科 機械系優秀学生賞
• 熊谷政仁，深水一聖，小野田誠，住友商事賞，東北大学 研究推進・支援機構 知の創出センター 量子アニーリングソリューションコンテスト．
• 佐藤 雅之，石田實記念財団研究奨励賞．
• 高屋敷 光，ベストプレゼンテーション賞，情報科学研究科後期博士課程発表会
• 越村 俊一，小林 広明，他　JST 大学発ベンチャー表彰　特別賞

2020年度

学術論文誌

• Takashi Soga, Kenta Yamaguchi, Raghunandan Mathur, Osamu Watanabe, Akihiro Musa, Ryusuke Egawa, and Hiroaki Kobayashi. “Effects of Using a Memory-Stalled Core for Handling MPI Communication Overlapping in the SOR Solver on SX-ACE and SX-Aurora TSUBASA,” Supercomputing Frontiers and Innovations (accepted).
• Kazuhiko Komatsu, Ayumu Gomi, Ryusuke Egawa, Daisuke Takahashi, Reiji Suda, Hiroyuki Takizawa, “Xevolver: A code transformation framework for separation of system‐awareness from application codes,”Concurrency and Computation: Practice and Experience, Vol. 32, No.7 2020年4月10日.

国際会議

• M. Yokokawa, A. Nakai, K. Komatsu, Y. Watanabe, Y. Masaoka, Y. Isobe, and H. Kobayashi, “I/O Performance of the SX-Aurora TSUBASA,” Proc. of 2020 IEEE International Parallel and Distributed Processing Symposium Workshop (IPDPSW), pp. 27-35 (2020), https://doi.org/10.1109/IPDPSW50202.2020.00014
• Yiran Cheng, Kazuhiko Komatsu, Masayuki Sato, Hiroaki Kobayashi, “A Deep Reinforcement Learning based Feature Selector,” In Proceedings of the 11th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP’20), December 2020.
• Bin Qi, Kazuhiko Komatsu, Masayuki Sato, Hiroaki Kobayashi, “A Dynamic Parameter Tuning Method for High Performance SpMM,” In Proceedings of the 11th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP’20), December 2020.
• Akito Onodera, Kazuhiko Komatsu, Soya Fujimoto, Yoko Isobe, Masayuki Sato, and Hiroaki Kobayashi, “Optimization of the Himeno Benchmark for SX-Aurora TSUBASA,” In Proceedings of International Symposium on Benchmarking, Measuring and Optimizing (Bench’20), November 2020.
• Masahito Kumagai, Kazuhiko Komatsu, Fumiyo Takano, Takuya Araki, Masayuki Sato, and Hiroaki Kobayashi, “Combinatorial Clustering based on an Externally-defined One-hot Constraint,” In Proceedings of The Eighth International Symposium on Computing and Networking, November 2020.
• Hao Tang, Kazuhiko Komatsu, Masayuki Sato, and Hiroaki Kobayashi, “An Efficient Skinny Matrix-Matrix Multiplication Method by Folding Input Matrices into Tensor Core Operations,” In Proceedings of The Eighth International Symposium on Computing and Networking, November 2020.
• Takumi Kishitani, Kazuhiko Komatsu, Masayuki Sato, Akihiro Musa, Hiroaki Kobayashi, “Importance of Selecting Data Layouts in the Tsunami Simulation Code,” In Proceedings of International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp.830–837, May 2020.
• Yuta Hougi, Kazuhiko Komatsu, Osamu Watanabe, Masayuki Sato, Hiroaki Kobayashi, “A hierarchical wavefront method for LU-SGS on modern multi-core vector processors,” 32nd International conference on Parallel Computational Fluid Dynamics (ParCFD 2020), 2020. (Accepted)
• Yujiro Takenaka, Mitsuo Yokokawa, Takashi Ishihara, Kazuhiko Komatsu, Hiroaki Kobayashi, “PERFORMANCE EVALUATION OF PARALLEL DNS CODES ON THE SUPERCOMPUTER SX-AURORA TSUBASA,” 32nd International conference on Parallel Computational Fluid Dynamics (ParCFD 2020), 2020. (Accepted)
• Masayuki Sato, Xue Hao, Kazuhiko Komatsu, Hiroaki Kobayashi, “Energy-Efficient Design of an STT-RAM-based Hybrid Cache Architecture,” In Proceedings of IEEE Symposium on High-Performance and Low-Power Chips and Systems (COOL Chips 23), April 2020.
• Akihiro Musa, Takashi Soga, Takashi Abe, Masa Sato, Kazuhiko Komatsu, Shinichi Koshimura, Hiroaki Kobayashi, “Evaluation of Tsunami Inundation Simulation using Vector-Scalar Hybrid MPI on SX-Aurora TSUBASA,” The poster presentation at The International Conference for High Performance Computing, Networking, Storage and Analysis (SC20), November 2020.
• Akito Onodera, Kazuhiko Komatsu, Takumi Kishitani, Masayuki Sato, Yoko Isobe, Hiroaki Kobayashi, “Optimizations for the Himeno Benchmark on Vector Computing System SX-Aurora TSUBASA,” Research Poster in ISC High Performance, June 2020.
• Masahito Kumagai, Kazuhiko Komatsu, Masayuki Sato, Hiroaki Kobayashi, “An Evaluation of a Hierarchical Clustering Method Using Quantum Annealing,” Research Poster in ISC High Performance, June 2020.
• Shunsuke Tsukada, Masayuki Sato, Kazuhiko Komatsu, Hiroaki Kobayashi, “Metadata Management for Large-Scale Hybrid Memory Architectures,” Research Poster in ISC High Performance, June 2020.
• Ilya. V. Afanasyev, Vladimir V. Voevodin, Kazuhiko Komatsu, and Hiroaki Kobayashi, “Developing an Ecient Vector-Friendly Implementation of the Breadth- first Search Algorithm for NEC SX-Aurora TSUBASA,” In Proceedings of 16th International Conference on Parallel Computing Technologies, April 2020.

学術講演・口頭発表

• 撫佐昭裕，“大規模津波浸水被害推計シミュレーションのマルチプラットフォーム向け最適化手法の研究”， 学際大規模情報基盤共同利用・共同研究拠点　第12回シンポジウム，東京，7月，2020．
• 塚田 竣介, 佐藤 雅之, 高屋敷 光, 小松 一彦, 小林 広明, “複合型メインメモリのメタデータ管理のためのデータアクセス解析,” In 並列/分散/協調処理に関する「福井」サマー・ワークショップ(SWoPP2020), July 2020.
• 後藤啓，横川三津夫，坂敏秀，小松一彦，小林広明，建物・地盤地震動応答シミュレーションのベクトル計算機向け最適化，技術報告，Vol. 2020-HPC-173，No. 3, pp.1-8 (2020)

編著書

• Resch, M., Kovalenko, Y., Bez, W., Focht, E., Kobayashi, H. (Eds.), Sustained Simulation Performance 2018 and 2019, Reading, 234 pages, ISBN 978-3-030-39180-5, Springer Nature Switzerland AG, May, 2020. DOI 10.1007/978-3-030-39181-2
• Hiroaki Kobayashi, R&D of a Quantum-Annealing Assisted Next Generation HPC Infrastructure and Its Killer Applications, Sustained Simulation Performance 2018 and 2019, pp.3-12, Reading, Springer Nature Switzerland AG, May, 2020.
• Kazuhiko Komatsu and Hiroaki Kobayashi, “Performance Evaluation of SX-Aurora TSUBASA by Using Benchmark Programs,” Sustained Simulation Performance 2018 and 2019, pp.69-77 Reading, Springer Nature Switzerland AG, May, 2020.

解説・総説・報告

• 撫佐昭裕，岸谷拓海，阿部孝志，佐藤佳彦，田野邊睦，鈴木崇之，村嶋陽一，佐藤雅之，小松一彦，伊達　進，越村俊一，小林広明, “リアルタイム津波浸水被害推計シミュレーションの性能評価,” SENAC Vol. 53, No. 2 (2020.4)．

報道等

• 東北大学，NECプレスリリース，” 東北大学とNEC、スーパーコンピュータを活用して航空機用複合材料開発を加速する マテリアルズインテグレーションシステムの研究開発を開始”(2020年7月1日)

受賞・受章

• Eighth International Symposium on Computing and Networking (CANDAR’20) Best Paper Award, “Combinatorial Clustering based on an Externally-defined One-hot Constraint,” Masahito Kumagai, Kazuhiko Komatsu, Fumiyo Takano, Takuya Araki, Masayuki Sato, Hiroaki Kobayashi
• 情報処理学会東北支部野口研究奨励賞，佐藤雅之

2019年度

学術論文誌

• Masayuki Sato, Takuya Toyoshima, Hikaru Takayashiki, Ryusuke Egawa, Hiroaki Kobayashi, “An Energy-aware Dynamic Data Allocation Mechanism for Many-Channel Memory Systems,” Journal of Supercomputing Frontiers and Innovations, Vol. 6, No. 4, pp.4–19, 2019.
• Hikaru Takayashiki, Masayuki Sato, Kazuhiko Komatsu, Hiroaki Kobayashi, “A Skewed Multi-banked Cache for Many-core Vector Processors,” Journal of Supercomputing Frontiers and Innovations, Vol6, No.3, pp.86–101, 2019. [DOI: 10.14529/jsfi190305]

国際会議

• Kou Murakami, Kazuhiko Komatsu, Masayuki Sato, Hiroaki Kobayashi, “Performance evaluation of a clustering approach based on thermophysical properties by using multiple platform,” In Poster Proceedings of International Conference on High Performance Computing in Asia-Pacific Region (HPCAsia), Jan 2020.
• Yuta Hougi, Kazuhiko Komatsu, Masayuki Sato, Hiroaki Kobayashi, “Acceleration of Numerical Turbine using the Red-Black Method,” In Poster Proceedings of International Conference on High Performance Computing in Asia-Pacific Region (HPCAsia), Jan 2020.
• Osamu Watanabe, Yuta Hougi, Kazuhiko Komatsu, Masayuki Sato, Akihiro Musa, Hiroaki Kobayashi, “Optimizing Memory Layout of Hyperplane Ordering for Vector Supercomputer SX-Aurora TSUBASA,” Workshop on Memory Centric High Performance Computing, pp.1–8, November 2019.
• Hikaru Takayashiki, Masayuki Sato, Kazuhiko Komatsu, Hiroaki Kobayashi, “A Hardware Prefetching Mechanism for Vector Gather Instructions,” 9th Workshop on Irregular Applications: Architectures and Algorithms, pp.1–8, November 2019.
• Ilya Afanaasyev, Vadim Voevodin, Vladimir Voevodin, Kazuhiko Komatsu, Hiroaki Kobayashi, Developing Efficient Implementations of Shortest Paths and Page Rank algorithms for NEC SX-Aurora TSUBASA Architecture, Russian Supercomputing Days, September 2019.
• Ilya Afanaasyev, Vadim Voevodin, Vladimir Voevodin, Kazuhiko Komatsu, Hiroaki Kobayashi, Analysis of relationship between SIMD-processing features used in NVIDIA GPUs and NEC SX-Aurora TSUBASA vector processors, In Proceedings of 15th International Conference on Parallel Computing Technologies, August 2019.
• Akihiro Musa, Takashi Abe, Takumi Kishitani, Takuya Inoue, Masayuki Sato, Kazuhiko Komatsu, Yoishi Murashima, Shunichi Koshimura, Hiroaki Kobayashi, “Performance evaluation of tsunami inundation simulation on SX-Aurora TSUBASA,” In Proceedings of International Conference on Computational Science, pp.363–376, June 2019.
• Ryusuke Egawa, Masayuki Sato, Ryoma Saito, Hiroaki Kobayashi, “A Layer-Adaptable Cache Hierarchy by a Multiple-layer Bypass Mechanism,” In Proceedings of International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies (HEART 2019), pp.1–6, June 2019.
• Kazuhiko Komatsu, Takumi Kishitani, Masayuki Sato, Hiroaki Kobayashi, “An Appropriate Computing System and its System Parameters Selection based on Bottleneck Prediction of Applications,” In Proceedings of The Fourteenth International Workshop on Automatic Performance Tuning, pp.1–10, May 2019.
• Hikaru Takayashiki, Masayuki Sato, Kazuhiko Komatsu, Hiroaki Kobayashi, “A Skewed Multi-bank Cache for Vector Processors,” Research Poster in ISC High Performance, RP23, June 2019.
• Takumi Kishitani, Kazuhiko Komatsu, Akihiro Musa, Masayuki Sato, Hiroaki Kobayashi, “An Application Parameter Search Method Based on the Binary Search Algorithm for Performance Tuning,” Research Poster in ISC High Performance, RP13, June 2019.
• Masayuki Sato, Yongcheng Chen, Haruya Kikuchi, Kazuhiko Komatsu, Hiroaki Kobayashi, “Perceptron-based Cache Bypassing for Way-Adaptable Caches,” In Proceedings of IEEE Symposium on High-Performance and Low-Power Chips and Systems (COOL Chips 22), April 2019.

招待講演

• Hiroaki Kobayashi, Quantum-Annealing Assisted Next-Generatioon HPC for Inductive and Deductive Computing Integrated Applications, Workshop on Sustained Simulation Performance 30, October 2019.
• Kazuhiko Komatsu, A System and its System Parameter Selection based on Bottleneck Prediction, Workshop on Sustained Simulation Performance 30, October 2019.
• Hiroaki Kobayashi, QA-Assisted Next Generation HPC Infrastructure for Computational Science, Data Science and their Integrated Applications. Invited Talk in Russian Supercomputing Days, September 2019.
• 小林広明，東日本大震災からの教訓：防災・減災に資するICT基盤の構築を目指して～IoT・AIを活用した安心・安全な人と自然の共生型サイバー社会実証実験の取り組み～,  NIKKEI AIサミット, April 2019.

学術講演

• 熊谷 政仁, 小松 一彦, 佐藤 雅之, 小林 広明, “量子アニーリングを用いたクラスタリング手法の評価”, 2020年電子情報通信学会総合大会, March 2020.
• 塚田 竣介, 佐藤 雅之, 小松 一彦, 小林 広明,  “複合型メインメモリのためのメタデータ管理手法に関する一考察”, 2020年電子情報通信学会総合大会, March 2020.
• 小野寺 明人, 小松 一彦, 磯部 洋子, 佐藤 雅之, 小林 広明, “姫野ベンチマークを用いたベクトル計算システムSX-Aurora TSUBASAの性能評価”, 2020年電子情報通信学会総合大会, March 2020.
• 中井 彩乃, 横川 三津夫(神戸大学), 小松 一彦(東北大学), 渡辺 裕太, 磯部 洋子(日本電気), 小林 広明(東北大学), “SX-Aurora TSUBASAの入出力性能の評価”, 第173回ハイパフォーマンスコンピューティング研究発表会, March 2020.
• Yiting Wang, Masayuki Sato, Kazuhiko Komatsu, Hiroaki Kobayashi, “A Refreshing Policy for eDRAM Last-Level Caches,” In Tohoku Section Joint Convention of Institutes of Electrical and Information Engineers, August 2019.
• Chen Zhenyu, Masayuki Sato, Kazuhiko Komatsu, Hiroaki Kobayashi, “A Virtual Machine Allocation Algorithm Based on Reinforcement Learning for Cloud Computing Systems,” In Tohoku Section Joint Convention of Institutes of Electrical and Information Engineers, August 2019.
• Hao Xue, Masayuki Sato, Kazuhiko Komatsu, Hiroaki Kobayashi, “A Pure STT-RAM Hybrid Cache Architecture for Last-Level Caches,” In Tohoku Section Joint Convention of Institutes of Electrical and Information Engineers, August 2019.
• 法木 祐太, 佐藤 雅之, 小松 一彦, 小林 広明, “ベクトルコンピュータを用いた数値タービンの高速化に関する一検討,” In 電気関係学会東北支部連合大会, August 2019.
• 村上 洸, 佐藤 雅之, 小松 一彦, 小林 広明, “ベクトルコンピュータを用いた機械学習の高速化に関する研究,” In 電気関 係学会東北支部連合大会, August 2019.
• 高屋敷 光, 佐藤 雅之, 小松 一彦, 小林 広明, “ベクトル間接参照命令のためのプリフェッチに関する一検討,” In 並列/分散/協調処理に関する「北見」サマー・ワークショップ(SWoPP2019), pp.1–7, July 2019.

受賞

• Ilya Afanaasyev, Vadim Voevodin, Vladimir Voevodin, Kazuhiko Komatsu, Hiroaki Kobayashi, Analysis of relationship between SIMD-processing features used in NVIDIA GPUs and NEC SX-Aurora TSUBASA vector processors, Best Paper Award of PaCT, 2019.
• Hikaru Takayashiki, Masayuki Sato, Kazuhiko Komatsu, Hiroaki Kobayashi, Best Poster Winner HPC-in-Asia at ISC High Performance, 2019.

2018年度

学術論文誌

• Ilya V. Afanasyev, Alexander S. Antonov, Dmitry A. Nikitenko, Vadim V. Voevodin, Vladimir V. Voevodin, Kazuhiko Komatsu, Osamu Watanabe, Akihiro Musa, Hiroaki Kobayashi, “Developing Efficient Implementations of Bellman–Ford and Forward-Backward Graph Algorithms for NEC SX-ACE,” SUPERCOMPUTING FRONTIERS AND INNOVATIONS, VOL 5, NO 3, 2018, DOI: 10.14529/jsfi180311.
• Akihiro Musa, Takashi Abe, Takuya Inoue, Hiroaki Hokari, Yoichi Murashima, Yoshiyuki Kido, Susumu Date, Shinji Shimojo, Shunichi Koshimura, and Hiroaki Kobayashi, “A Real-Time Tsunami Inundation Forecast System Using Vector Supercomputer SX-ACE”, Journal of Disaster Research, Vol.13, No.2, pp.234-244, 2018, https://doi.org/10.20965/jdr.2018.
• Akihiro Musa, Osamu Watanabe, Hiroshi Matsuoka, Hiroaki Hokari, Takuya Inoue, Yoichi Murashima, Yusaku Ohta, Ryota Hine, Shunichi Koshimura, Hiroaki Kobayashi, “Real-time tsunami inundation forecast system for tsunami disaster prevention and mitigation”, Journal of Supercomputing, 2018, https://doi.org/10.1007/s11227-018-2363-0.
• Masayuki Sato, Y. Shoji, Zentaro Sakai, Ryusuke Egawa and Hiroaki Kobayashi, “An Adjacent-Line-Merging Writeback Scheme for STT-RAM-Based Last-Level Caches,” in IEEE Transactions on Multi-Scale Computing Systems, preprint, April 2018.

国際会議

• Kazuhiko Komatsu, Shintaro Momose, Yoko Isobe, Osamu Watanabe, Akihiro Musa, Mitsuo Yokokawa, Toshikazu Aoyama, Masayuki Sato, and Hiroaki Kobayashi, Performance Evaluation of a Vector Supercomputer SX-Aurora TSUBASA, In Proc. of the International Conference for High Performance Computing, Networking, Storage, and Analysis, Nov. 2018.
• Kazuhiko Komatsu, Takumi Kishitani, Masayuki Sato, Akihiro Musa and Hiroaki Kobayashi, “Search Space Reduction for Parameter Tuning of a Tsunami Simulation on a Many-core Processor,” In Auto-Tuning for Multicore and GPU 2018, Sep. 2018.
• Hiroyuki Takizawa, Thorsten Reimann, Kazuhiko Komatsu, Takashi Soga, Ryusuke Egawa, Akihiro Musa, and Hiroaki Kobayashi, “Expressing the Differences in Code Optimizations between Intel Knights Landing and NEC SX-ACE Processors,” In The 13th World Congress on Computational Mechanics / 2nd Pan American Congress on Computational Mechanics, Jul. 2018.
• Akihiro Musa, Takumi Kishitani, Takuya Inoue, Hiroaki Hokari, Masayuki Sato, Kazuhiko Komatsu, Yoichi Murashima, Shunichi Koshimura, Hiroaki Kobayashi, “Performance Evaluation of a Real-Time Tsunami Inundation Forecast System on Modern Supercomputers,” In Asia Oceania Geosciences Society 2018, Jun. 2018.
• Kazuhiko Komatsu, Shintaro Momose, Yoko Isobe, Masayuki Sato, Akihiro Musa, Hiroaki Kobayashi, “Early Evaluation of a New Vector Processor SX-Aurora TSUBASA,” In Poster Proceedings of International Supercomputing Conference, Jun. 2018.
• Hiroyuki Takizawa, Kenta Yamaguchi, Takashi Soga, Thorsten Reimann, Kazuhiko Komatsu, Ryusuke Egawa, Akihiro Musa, and Hiroaki Kobayashi, “Migrating an Old Vector Code to Modern Vector Machines,” In 30th International Conference on Parallel Computational Fluid Dynamics, May 2018.
• Yuki Kawarabatake, Mulya Agung, Kazuhiko Komatsu, Ryusuke Egawa and Hiroyuki Takizawa, “Use of Code Structural Features for Machine Learning to Predict Effective Optimizations,” In 33rd IEEE International Parallel & Distributed Processing Symposium Workshops(IPDPSW), International Workshop on Automatic Performance Tuning, pp. 1049-1055, May 2018.
• Masayuki Sato, Zehua Li, Ryusuke Egawa, and Hiroaki Kobayashi, “An Energy-aware Set-level Refreshing Mechanism for eDRAM Last-Level Caches,” In Proc. of COOL Chips 21, Apr. 2018.

学術講演・口頭発表

• 高屋敷 光, 佐藤 雅之, 小松 一彦, 江川 隆輔, 小林 広明, “マルチベクトルコアプロセッサの共有キャッシュ構成に関する一検討,” In 並列／分散／協調処理に関する『熊本』サマー・ワークショップ, Jul. 2018.
• 岸谷 拓海, 小松 一彦, 撫佐 昭裕, 佐藤 雅之, 小林 広明, “メニーコアプロセッサのためのパラメータチューニング時間削減手法,” In 並列／分散／協調処理に関する『熊本』サマー・ワークショップ, Jul. 2018.

招待講演

• Hiroaki Kobayashi, “A Real-Time Tsunami Inundation Forecasting System for Disaster Mitigation and Prevention ~Lessons learned from the 2011 East-Japan Great Earthquake ~,” In The 5th International Conference on Information and Communication Technologies for Disaster Management, Dec. 2018.
• Kazuhiko Komatsu, “Performance Evaluation of a Brand-New Vector Supercomputer SX-Aurora TSUBASA,” In Aurora Forum at SC18, Nov. 2018.
• 小松一彦, “新ベクトルプロセッサSX-Aurora TSUBASAの基本性能評価,” In SP研究会 at C&Cユーザーフォーラム&iEXPO2018ワークショップ , Nov. 2018.
• Hiroaki Kobayashi, “Experiences with SX-Aurora Tsubasa and its extension for the future,” In Workshop on Sustained Simulation Performance 28, Oct. 2018.
• Kazuhiko Komatsu, “Performance evaluation and analysis of SX-Aurora TSUBASA ,” In Workshop on Sustained Simulation Performance 28, Oct. 2018.
• Hiroaki Kobayashi, “Performance Evaluation of a Vector Supercomputer SX-Aurora TSUBASA,” In Russian Supercomputing Days, Sep. 2018.
• Hiroaki Kobayashi, “Early experiences with Aurora-TSUBASA,” In NEC User Group 30, May 2018.
• Hiroaki Kobayashi, “Early Experiences with SX-Aurora TSUBASA,” In NEC Aurora Forum, Jun. 2018.

特許

• 大森優也, 大西隆之, 岩崎裕江, 清水淳, 江川隆輔, 佐藤雅之, 小林広明, プロセッサ，多階層キャッシュメモリの制御方法，及び多階層キャッシュメモリの制御プログラム, 特願2018-156654, 2018. （出願中）

受賞

• 小林広明，小松一彦，2018年 全NUA ユーザー事例論文 技術貢献賞．
• 小林広明，撫佐昭裕，平成30年度 科学技術分野の文部科学大臣表彰 科学技術賞 開発部門．

2017年度

国際会議

• Masayuki Sato, Zentaro Sakai, Ryusuke Egawa, Hiroaki Kobayashi, “An Adjacent-Line-Merging Writeback Scheme for STT-RAM Last-Level Caches,” In Proceedings of IEEE International Symposium on High-Performance and Low-Power Chips (COOL Chips 20), Apr. 2017.
• Takuya Toyoshima, Masayuki Sato, Ryusuke Egawa, Hiroaki Kobayashi, “An Application-adaptive Data Allocation Method for Multi-channel Memory,” In Proceedings of IEEE International Symposium on High-Performance and Low-Power Chips (COOL Chips 20), Apr. 2017.

学術講演・口頭発表

• 佐藤涼祐, 佐藤雅之, 江川隆輔, 小林広明, Early Evaluation of a Heterogeneous Memory Architecture on a Vector Supercomputer, 平成29年度電気関係東北支部連合大会, 2017.

招待講演

• Kazuhiko Komatsu, Performance Analysis and Tuning of ExaFSA Codes, Society for Industrial and Applied Mathematics (SIAM PP2018), Mar. 2018
• Ryusuke Egawa, Masayuki Sato, Ryoma Saito, Hiroaki Kobayashi, A Multiple-layer Bypass Mechanism for Energy Efficient Computing, In 26th Workshop on Sustained Simulation Performance, Oct. 2017.
• Hiroaki Kobayashi, Two-Year Experiences with Vector Supercomputer SX-ACE and Design Space Exploration of the Next Generation Vector System, 26th Workshop on Sustained Simulation Performance, Oct. 2017.
• Hiroaki Kobayashi, Two-Year Experiences with Vector Supercomputer SX-ACE and Design Space Exploration of the Next Generation Vector System, Russian Supercomputing Days, Sep. 2017.

受賞

• 小林広明，平成29年度「情報化促進貢献個人等表彰」 文部科学大臣賞．
• 佐藤涼祐, 佐藤雅之, 江川隆輔, 小林広明, 平成29年度電気関係東北支部連合大会, IEEE Student Session Award (Encouragement Prize)．

学位論文

• 豊嶋 拓也， “メモリ省電力化のための動的データ配置に関する研究”
• 陳 勇丞， “機械学習に基づくデッドブロック予測を用いたウェイ適応型キャッシュの省電力化に関する研究”
• 李 沢華， “An Energy-aware LRU-based Refreshing Policy for eDRAM Last-Level Cache （eDRAMラストレベルキャッシュのための局所性に基づくエネルギを考慮したリフレッシュポリシに関する研究）”
• 岸谷 拓海，“リアルタイム津波シミュレーションに関する研究”
• 庄司 佳輝，“STT-RAMを用いたラストレベルキャッシュに関する研究”
• 鄒 子君， “熱中症シミュレーションの高速化に関する研究”
• 高屋敷 光， “マルチベクトルコアアーキテクチャのキャッシュ構造に関する研究”
• 森江 太一， “データ並列アプリケーションのメモリアクセス挙動に関する研究”

2016年度

国際会議

• Ryusuke Egawa, Wataru Uno, Masayuki Sato, Hiroaki Kobayashi, Jubee Tada, “A Power-Aware LLC Control Mechanism for 3D-Stacked Memory Subsystems,” In Proceedings of the IEEE International Conference on 3D System Integration (3DIC), Nov. 2016.
• Masayuki Sato, Shin Nishimura, Ryusuke Egawa, Hiroyuki Takizawa, Hiroaki Kobayashi, “A Cache Partitioning Mechanism to Protect Shared Data for CMPs,” In Proceedings of IEEE Symposium on Low-Power and High-Speed Chips, Apr. 2016.

国内会議

• 豊嶋 拓也, 佐藤 雅之, 江川 隆輔, 小林 広明, “高バンド幅メモリのための省電力データ配置手法に関する研究,” In 東北支部大会連合大会予稿集, August 2016.
• 佐藤 雅之, 高井 拓実, 江川 隆輔, 滝沢 寛之, 小林 広明, “アプリケーション適応型キャッシュリサイズのためのバイパス機構,” 電子情報通信学会論文誌, Vol. J99-D, No. 3, pp.337–347, Mar. 2016.

学位論文

• 坂井 然太郎, “STT-RAMキャッシュのためのライトマージ機構に関する研究”
• 高須 隼太, “性能と消費電力を考慮した性能最適化に関する研究”
• 菊地 陽哉, “メニーコアプロセッサを用いた津波浸水被害予測シミュレーションの高速化に関する研究”
• 佐藤 涼祐, “複合型メモリのためのデータ管理に関する研究”
• 斎藤 龍馬, “バイパス制御による積層型メモリシステムのエネルギー効率化に関する研究”