Boku Taisuke

J-GLOBAL         Last updated: Sep 19, 2019 at 02:43
 
Avatar
Name
Boku Taisuke
E-mail
taisukecs.tsukuba.ac.jp
Affiliation
University of Tsukuba
Section
Center for Computational Sciences
Job title
Professor

Academic & Professional Experience

 
Apr 1988
 - 
Feb 1992
Assistant Professor, Department of Physics, Faculty of Science and Technology, Keio University
 
Feb 1992
 - 
Jul 1995
Lecturer, Institute of Information Systems and Engineering, University of Tsukuba
 
Aug 1995
 - 
Mar 2004
Associate Professor, Institute of Information Systems and Engineering, University of Tsukuba
 
Mar 2004
 - 
Feb 2005
Associate Professor, Graduate School of Systems and Information Engineering, University of Tsukuba
 
Mar 2005
   
 
Professor, Graduate School of Systems and Information Engineering, University of Tsukuba
 

Education

 
 
 - 
1984
Faculty of Engineering, Keio University
 
 
 - 
1990
Graduate School, Division of Science and Engineering, Keio University
 

Awards & Honors

 
Jun 2014
HEART2014 Best Paper Award, Program Committee of HEART2014
Winner: Yuetsu Kodama;Toshihiro Hanawa;Taisuke Boku;Mitsuhisa Sato
 
Using PEACH2 chip based on FPGA implementation to connect multiple GPUs on different computation node in GPU equipped PC clusters, we could reduce the communication time for GPU to GPU memory copy up to 1/3 of traditional software based technology.
Nov 2011
2011 ACM Gordon Bell Prize Best Performance Award, ACM
 
First-principles calculations of electron states of a silicon nanowire with 100,000 atoms on the K computer

Published Papers

 
Optimization on Astrophysical Radiative Transfer Code for FPGAs with OpenCL
藤田, 典久;小林, 諒平;山口, 佳樹;朴, 泰祐;吉川, 耕司;安部, 牧人;梅村, 雅之
IPSJ Transactions on Advanced Computing System   12(3) 64-75   Jul 2019   [Refereed]
One of the recent challenges faced by HPC is how to apply FPGA technology to accelerate a next-generation supercomputer as an efficient method of achieving high performance and low power consumption. GPU is the most commonly used accelerator for H...
GPU・FPGA複合演算加速による輻射流体シミュレーションコードARGOTの実装
中道, 安祐未;藤田, 典久;小林, 諒平;朴, 泰祐;吉川, 耕司;梅村, 雅之
研究報告ハイパフォーマンスコンピューティング(HPC)   2019-HPC-170(22) 1-5   Jul 2019
近年,高性能コンピューティング (HPC:High Performance Computing) の分野において,アクセラレータを搭載した大規模計算クラスタが主流の 1 つとなっている.アクセラレータには,主に Graphics Processing Unit (GPU) が用いられているが,HPC 分野では処理の柔軟性や電力効率の高さから Field Programmable Gate Array (FPGA) が注目されつつある.そこで,GPU が不得意な計算を FPGA に行わせる ...
OpenCL対応FPGA間通信機能によるGPU・FPGA複合型演算加速
小林, 諒平;藤田, 典久;山口, 佳樹;中道, 安祐未;朴, 泰祐
研究報告ハイパフォーマンスコンピューティング(HPC)   2019-HPC-170(5) 1-9   Jul 2019
我々は,高い演算性能とメモリバンド幅を有する GPU(Graphics Processing Unit)に演算通信性能に優れている FPGA(Field Programmable Gate Array)を連携させ,双方を相補的に利用する GPU-FPGA 複合システムに関する研究を進めている.GPU,FPGA といった異なるハードウェアを搭載するシステム上では,各デバイスで実行される演算をどのようにプログラミングし,全デバイスを協調動作させるかが重要な課題となる.そこで本稿では,OpenC...
Fujita, Norihisa;Kobayashi, Ryohei;Yamaguchi, Yoshiki;Boku, Taisuke
2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)   479-488   Jul 2019   [Refereed]
In recent years, Field Programmable Gate Array (FPGA) has been a topic of interest in High Performance Computing (HPC) research. Although the biggest problem in utilizing FPGAs for HPC applications is in the difficulty of developing FPGAs, this pr...
Kobayashi, Ryohei;Fujita, Norihisa;Yamaguchi, Yoshiki;Nakamichi, Ayumi;Boku, Taisuke
2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)   489-498   Jul 2019   [Refereed]
Field-programmable gate arrays (FPGAs) have garnered significant interest in research on high-performance computing because their computation and communication capabilities have drastically improved in recent years due to advances in semiconductor...

Books etc

 
Advanced Software Technologies for Post-Peta Scale Computing
Boku,Taisuke (Part:Contributor, GPU-Accelerated Language and Communication Support by FPGA)
Springer   May 2018   ISBN:9789811319242
Although the GPU is one of the most successfully used accelerating devices for HPC, there are several issues when it is used for large-scale parallel systems. To describe real applications on GPU-ready parallel systems, we need to combine differen...
OpenMP: Memory, Devices, and Tasks
Tabuchi, Akihiro; Kimura, Yasuyuki; Torii, Sunao; Matsufuru, Hideo; Ishikawa, Tadashi; Boku, Taisuke; Sato, Mitsuhisa (Part:Contributor, Design and Preliminary Evaluation of Omni OpenACC Compiler for Massive MIMD Processor PEZY-SC)
SPRINGER INT PUBLISHING AG   2016   ISBN:9783319455495
2013 IEEE 21ST ANNUAL SYMPOSIUM ON HIGH-PERFORMANCE INTERCONNECTS (HOTI)
Hanawa, Toshihiro; Kodama, Yuetsu; Boku, Taisuke; Sato, Mitsuhisa (Part:Contributor, Interconnection Network for Tightly Coupled Accelerators Architecture)
IEEE   2013   ISBN:9780769551036
PRACTICAL PROGRAMMING MODEL FOR THE MULTI-CORE ERA, PROCEEDINGS
Lee, Jinpil;Sato, Mitsuhisa;Boku, Taisuke (Part:Contributor, Design and implementation of OpenMPD: An OpenMP-like programming language for distributed memory systems)
SPRINGER-VERLAG BERLIN   Jan 2008   ISBN:9783540693024
2008 IEEE INTERNATIONAL SYMPOSIUM ON PARALLEL & DISTRIBUTED PROCESSING, VOLS 1-8
Miura, Shin'ichi;Boku, Taisuke;Okamoto, Takayuki;Hanawal, Toshihiro (Part:Contributor, A dynamic routing control system for high-performance PC cluster with multi-path Ethernet connection)
IEEE   Jan 2008   ISBN:9781424416936

Conference Activities & Talks

 
Cygnus: GPU + FPGA accelerated supercomputing platform [Invited]
Kobayashi, Ryohei;Fujita, Norihisa;Yamaguchi, Yoshiki;Boku, Taisuke;Yoshikawa, Kohji;Umemura, Masayuki
1st International Workshop on Reconfigurable High Performance Computing (ReHPC'2019)   13 Sep 2019   
Graphics processing units (GPUs) have been widely used in high-performance computing (HPC) systems as accelerators because they can offer good peak performance and high memory bandwidth. However, the GPU is not almighty as an accelerator because i...
スーパーコンピュータにおける演算加速装置の現状と今後 [Invited]
朴,泰祐
神戸大学協定講座シンポジウム   21 Dec 2018   神戸大学
Hybrid Accelerated Parallel Computing, GPU + FPGA = ? [Invited]
Boku,Taisuke
CODESIGN 2018 Workshop in HPC China 2018   19 Oct 2018   China Computer Federation
Oakforest-PACS: World Largest KNL/OPA Cluster and Its Performance Optimization [Invited]
Boku,Taisuke
IPCC Asian Summit 2018   10 May 2018   Intel IPCC
GPU-FPGA Heterogeneous Computing with Unified Programming Framework [Invited]
Tsunashima, Ryuuta;Kobayashi, Ryohei;Fujita, Norihisa;Nakamichi, Ayumi;Boku, Taisuke
OpenACC Annual Meeting 2019   2 Sep 2019   
This talk shows how to use FPGA for HPC which enables on-the-fly offloading computation where CPUs/GPUs perform poorly to FPGAs while performing low-latency intra/inter-node communication and demonstrates the effectiveness of our proposed approach...

Research Grants & Projects

 
Study on interoperability of supercomputers on Grid environment
High performance computing on clusters
Performance evaluation of high performance computing on massively parallel processing systems