BibTeX records: Naoya Maruyama

download as .bib file

@article{DBLP:journals/ijhpca/AlexanderABBCCC21,
  author       = {Francis J. Alexander and
                  James A. Ang and
                  Jenna A. Bilbrey and
                  Jan Balewski and
                  Tiernan Casey and
                  Ryan Chard and
                  Jong Choi and
                  Sutanay Choudhury and
                  Bert J. Debusschere and
                  Anthony M. DeGennaro and
                  Nikoli Dryden and
                  J. Austin Ellis and
                  Ian T. Foster and
                  Cristina Garcia{-}Cardona and
                  Sayan Ghosh and
                  Peter Harrington and
                  Yunzhi Huang and
                  Shantenu Jha and
                  Travis Johnston and
                  Ai Kagawa and
                  Ramakrishnan Kannan and
                  Neeraj Kumar and
                  Zhengchun Liu and
                  Naoya Maruyama and
                  Satoshi Matsuoka and
                  Erin McCarthy and
                  Jamaludin Mohd{-}Yusof and
                  Peter Nugent and
                  Yosuke Oyama and
                  Thomas Proffen and
                  David Pugmire and
                  Sivasankaran Rajamanickam and
                  Vinay Ramakrishniah and
                  Malachi Schram and
                  Sudip K. Seal and
                  Ganesh Sivaraman and
                  Christine Sweeney and
                  Li Tan and
                  Rajeev Thakur and
                  Brian Van Essen and
                  Logan T. Ward and
                  Paul M. Welch and
                  Michael Wolf and
                  Sotiris S. Xantheas and
                  Kevin G. Yager and
                  Shinjae Yoo and
                  Byung{-}Jun Yoon},
  title        = {Co-design Center for Exascale Machine Learning Technologies (ExaLearn)},
  journal      = {Int. J. High Perform. Comput. Appl.},
  volume       = {35},
  number       = {6},
  pages        = {598--616},
  year         = {2021},
  url          = {https://doi.org/10.1177/10943420211029302},
  doi          = {10.1177/10943420211029302},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/ijhpca/AlexanderABBCCC21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tpds/OyamaMDMHBMNE21,
  author       = {Yosuke Oyama and
                  Naoya Maruyama and
                  Nikoli Dryden and
                  Erin McCarthy and
                  Peter Harrington and
                  Jan Balewski and
                  Satoshi Matsuoka and
                  Peter Nugent and
                  Brian Van Essen},
  title        = {The Case for Strong Scaling in Deep Learning: Training Large 3D CNNs
                  With Hybrid Parallelism},
  journal      = {{IEEE} Trans. Parallel Distributed Syst.},
  volume       = {32},
  number       = {7},
  pages        = {1641--1652},
  year         = {2021},
  url          = {https://doi.org/10.1109/TPDS.2020.3047974},
  doi          = {10.1109/TPDS.2020.3047974},
  timestamp    = {Tue, 02 Mar 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/tpds/OyamaMDMHBMNE21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:series/lncse/KunkelJN0YMWT20,
  author       = {Julian M. Kunkel and
                  Nabeeh Jumah and
                  Anastasiia Novikova and
                  Thomas Ludwig and
                  Hisashi Yashiro and
                  Naoya Maruyama and
                  Mohamed Wahib and
                  John Thuburn},
  editor       = {Hans{-}Joachim Bungartz and
                  Severin Reiz and
                  Benjamin Uekermann and
                  Philipp Neumann and
                  Wolfgang E. Nagel},
  title        = {{AIMES:} Advanced Computation and {I/O} Methods for Earth-System Simulations},
  booktitle    = {Software for Exascale Computing - {SPPEXA} 2016-2019},
  series       = {Lecture Notes in Computational Science and Engineering},
  volume       = {136},
  pages        = {61--102},
  publisher    = {Springer},
  year         = {2020},
  url          = {https://doi.org/10.1007/978-3-030-47956-5\_5},
  doi          = {10.1007/978-3-030-47956-5\_5},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/series/lncse/KunkelJN0YMWT20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-12856,
  author       = {Yosuke Oyama and
                  Naoya Maruyama and
                  Nikoli Dryden and
                  Erin McCarthy and
                  Peter Harrington and
                  Jan Balewski and
                  Satoshi Matsuoka and
                  Peter Nugent and
                  Brian Van Essen},
  title        = {The Case for Strong Scaling in Deep Learning: Training Large 3D CNNs
                  with Hybrid Parallelism},
  journal      = {CoRR},
  volume       = {abs/2007.12856},
  year         = {2020},
  url          = {https://arxiv.org/abs/2007.12856},
  eprinttype    = {arXiv},
  eprint       = {2007.12856},
  timestamp    = {Thu, 23 Jun 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2007-12856.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/DrydenMBMSE19,
  author       = {Nikoli Dryden and
                  Naoya Maruyama and
                  Tom Benson and
                  Tim Moon and
                  Marc Snir and
                  Brian Van Essen},
  title        = {Improving Strong-Scaling of {CNN} Training by Exploiting Finer-Grained
                  Parallelism},
  booktitle    = {2019 {IEEE} International Parallel and Distributed Processing Symposium,
                  {IPDPS} 2019, Rio de Janeiro, Brazil, May 20-24, 2019},
  pages        = {210--220},
  publisher    = {{IEEE}},
  year         = {2019},
  url          = {https://doi.org/10.1109/IPDPS.2019.00031},
  doi          = {10.1109/IPDPS.2019.00031},
  timestamp    = {Wed, 16 Oct 2019 14:14:51 +0200},
  biburl       = {https://dblp.org/rec/conf/ipps/DrydenMBMSE19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/DrydenMMBSE19,
  author       = {Nikoli Dryden and
                  Naoya Maruyama and
                  Tim Moon and
                  Tom Benson and
                  Marc Snir and
                  Brian Van Essen},
  editor       = {Michela Taufer and
                  Pavan Balaji and
                  Antonio J. Pe{\~{n}}a},
  title        = {Channel and filter parallelism for large-scale {CNN} training},
  booktitle    = {Proceedings of the International Conference for High Performance Computing,
                  Networking, Storage and Analysis, {SC} 2019, Denver, Colorado, USA,
                  November 17-19, 2019},
  pages        = {10:1--10:20},
  publisher    = {{ACM}},
  year         = {2019},
  url          = {https://doi.org/10.1145/3295500.3356207},
  doi          = {10.1145/3295500.3356207},
  timestamp    = {Sat, 09 Nov 2019 12:05:50 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/DrydenMMBSE19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/KarlinPSWSBBCCC19,
  author       = {Ian Karlin and
                  Yoonho Park and
                  Bronis R. de Supinski and
                  Peng Wang and
                  Bert Still and
                  David Beckingsale and
                  Robert Blake and
                  Tong Chen and
                  Guojing Cong and
                  Carlos H. A. Costa and
                  Johann Dahm and
                  Giacomo Domeniconi and
                  Thomas Epperly and
                  Aaron Fisher and
                  Sara Kokkila Schumacher and
                  Steven H. Langer and
                  Hai Le and
                  Eun Kyung Lee and
                  Naoya Maruyama and
                  Xinyu Que and
                  David F. Richards and
                  Bj{\"{o}}rn Sj{\"{o}}green and
                  Jonathan Wong and
                  Carol S. Woodward and
                  Ulrike Meier Yang and
                  Xiaohua Zhang and
                  Bob Anderson and
                  David Appelhans and
                  Levi Barnes and
                  Peter D. Barnes Jr. and
                  Sorin Bastea and
                  David B{\"{o}}hme and
                  Jamie A. Bramwell and
                  James M. Brase and
                  Jos{\'{e}} R. Brunheroto and
                  Barry Chen and
                  Charway R. Cooper and
                  Tony Degroot and
                  Robert D. Falgout and
                  Todd Gamblin and
                  David J. Gardner and
                  James N. Glosli and
                  John A. Gunnels and
                  Max P. Katz and
                  Tzanio V. Kolev and
                  I{-}Feng W. Kuo and
                  Matthew P. LeGendre and
                  Ruipeng Li and
                  Pei{-}Hung Lin and
                  Shelby Lockhart and
                  Kathleen McCandless and
                  Claudia Misale and
                  Jaime H. Moreno and
                  Rob Neely and
                  Jarom Nelson and
                  Rao Nimmakayala and
                  Kathryn M. O'Brien and
                  Kevin O'Brien and
                  Ramesh Pankajakshan and
                  Roger Pearce and
                  Slaven Peles and
                  Phil Regier and
                  Steven C. Rennich and
                  Martin Schulz and
                  Howard Scott and
                  James C. Sexton and
                  Kathleen Shoga and
                  Shiv Sundram and
                  Guillaume Thomas{-}Collignon and
                  Brian Van Essen and
                  Alexey Voronin and
                  Bob Walkup and
                  Lu Wang and
                  Chris Ward and
                  Hui{-}Fang Wen and
                  Daniel A. White and
                  Christopher Young and
                  Cyril Zeller and
                  Edward Zywicz},
  editor       = {Michela Taufer and
                  Pavan Balaji and
                  Antonio J. Pe{\~{n}}a},
  title        = {Preparation and optimization of a diverse workload for a large-scale
                  heterogeneous system},
  booktitle    = {Proceedings of the International Conference for High Performance Computing,
                  Networking, Storage and Analysis, {SC} 2019, Denver, Colorado, USA,
                  November 17-19, 2019},
  pages        = {32:1--32:17},
  publisher    = {{ACM}},
  year         = {2019},
  url          = {https://doi.org/10.1145/3295500.3356192},
  doi          = {10.1145/3295500.3356192},
  timestamp    = {Sat, 30 Sep 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/sc/KarlinPSWSBBCCC19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1903-06681,
  author       = {Nikoli Dryden and
                  Naoya Maruyama and
                  Tom Benson and
                  Tim Moon and
                  Marc Snir and
                  Brian Van Essen},
  title        = {Improving Strong-Scaling of {CNN} Training by Exploiting Finer-Grained
                  Parallelism},
  journal      = {CoRR},
  volume       = {abs/1903.06681},
  year         = {2019},
  url          = {http://arxiv.org/abs/1903.06681},
  eprinttype    = {arXiv},
  eprint       = {1903.06681},
  timestamp    = {Mon, 01 Apr 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1903-06681.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpcasia/MatsudaFM18,
  author       = {Motohiko Matsuda and
                  Keisuke Fukuda and
                  Naoya Maruyama},
  title        = {A Portability Layer of an All-pairs Operation for Hierarchical N-Body
                  Algorithm Framework Tapas},
  booktitle    = {Proceedings of the International Conference on High Performance Computing
                  in Asia-Pacific Region, {HPC} Asia 2018, Chiyoda, Tokyo, Japan, January
                  28-31, 2018},
  pages        = {241--250},
  publisher    = {{ACM}},
  year         = {2018},
  url          = {https://doi.org/10.1145/3149457.3149471},
  doi          = {10.1145/3149457.3149471},
  timestamp    = {Tue, 06 Nov 2018 16:59:01 +0100},
  biburl       = {https://dblp.org/rec/conf/hpcasia/MatsudaFM18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpcasia/TakizawaMMN18,
  author       = {Shin'ichiro Takizawa and
                  Motohiko Matsuda and
                  Naoya Maruyama and
                  Yoshifumi Nakamura},
  title        = {A Scalable Multi-Granular Data Model for Data Parallel Workflows},
  booktitle    = {Proceedings of the International Conference on High Performance Computing
                  in Asia-Pacific Region, {HPC} Asia 2018, Chiyoda, Tokyo, Japan, January
                  28-31, 2018},
  pages        = {251--260},
  publisher    = {{ACM}},
  year         = {2018},
  url          = {https://doi.org/10.1145/3149457.3154483},
  doi          = {10.1145/3149457.3154483},
  timestamp    = {Tue, 06 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hpcasia/TakizawaMMN18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/AlomMMET18,
  author       = {Md. Zahangir Alom and
                  Adam T. Moody and
                  Naoya Maruyama and
                  Brian C. Van Essen and
                  Tarek M. Taha},
  title        = {Effective Quantization Approaches for Recurrent Neural Networks},
  booktitle    = {2018 International Joint Conference on Neural Networks, {IJCNN} 2018,
                  Rio de Janeiro, Brazil, July 8-13, 2018},
  pages        = {1--8},
  publisher    = {{IEEE}},
  year         = {2018},
  url          = {https://doi.org/10.1109/IJCNN.2018.8489341},
  doi          = {10.1109/IJCNN.2018.8489341},
  timestamp    = {Wed, 16 Oct 2019 14:14:55 +0200},
  biburl       = {https://dblp.org/rec/conf/ijcnn/AlomMMET18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-02615,
  author       = {Md. Zahangir Alom and
                  Adam T. Moody and
                  Naoya Maruyama and
                  Brian C. Van Essen and
                  Tarek M. Taha},
  title        = {Effective Quantization Approaches for Recurrent Neural Networks},
  journal      = {CoRR},
  volume       = {abs/1802.02615},
  year         = {2018},
  url          = {http://arxiv.org/abs/1802.02615},
  eprinttype    = {arXiv},
  eprint       = {1802.02615},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1802-02615.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/dase/UenoSMFM17,
  author       = {Koji Ueno and
                  Toyotaro Suzumura and
                  Naoya Maruyama and
                  Katsuki Fujisawa and
                  Satoshi Matsuoka},
  title        = {Efficient Breadth-First Search on Massively Parallel and Distributed-Memory
                  Machines},
  journal      = {Data Sci. Eng.},
  volume       = {2},
  number       = {1},
  pages        = {22--35},
  year         = {2017},
  url          = {https://doi.org/10.1007/s41019-016-0024-y},
  doi          = {10.1007/S41019-016-0024-Y},
  timestamp    = {Tue, 01 Sep 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/dase/UenoSMFM17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tpds/UnatDHSABCCEFFH17,
  author       = {Didem Unat and
                  Anshu Dubey and
                  Torsten Hoefler and
                  John Shalf and
                  Mark James Abraham and
                  Mauro Bianco and
                  Bradford L. Chamberlain and
                  Romain Cledat and
                  H. Carter Edwards and
                  Hal Finkel and
                  Karl Fuerlinger and
                  Frank Hannig and
                  Emmanuel Jeannot and
                  Amir Kamil and
                  Jeff Keasler and
                  Paul H. J. Kelly and
                  Vitus J. Leung and
                  Hatem Ltaief and
                  Naoya Maruyama and
                  Chris J. Newburn and
                  Miquel Peric{\`{a}}s},
  title        = {Trends in Data Locality Abstractions for {HPC} Systems},
  journal      = {{IEEE} Trans. Parallel Distributed Syst.},
  volume       = {28},
  number       = {10},
  pages        = {3007--3020},
  year         = {2017},
  url          = {https://doi.org/10.1109/TPDS.2017.2703149},
  doi          = {10.1109/TPDS.2017.2703149},
  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/tpds/UnatDHSABCCEFFH17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/fpl/PodobasZMM17,
  author       = {Artur Podobas and
                  Hamid Reza Zohouri and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  editor       = {Marco D. Santambrogio and
                  Diana G{\"{o}}hringer and
                  Dirk Stroobandt and
                  Nele Mentens and
                  Jari Nurmi},
  title        = {Evaluating high-level design strategies on FPGAs for high-performance
                  computing},
  booktitle    = {27th International Conference on Field Programmable Logic and Applications,
                  {FPL} 2017, Ghent, Belgium, September 4-8, 2017},
  pages        = {1--4},
  publisher    = {{IEEE}},
  year         = {2017},
  url          = {https://doi.org/10.23919/FPL.2017.8056756},
  doi          = {10.23919/FPL.2017.8056756},
  timestamp    = {Wed, 16 Oct 2019 14:14:53 +0200},
  biburl       = {https://dblp.org/rec/conf/fpl/PodobasZMM17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/fpl/PodobasZMM17a,
  author       = {Artur Podobas and
                  Hamid Reza Zohouri and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  editor       = {Marco D. Santambrogio and
                  Diana G{\"{o}}hringer and
                  Dirk Stroobandt and
                  Nele Mentens and
                  Jari Nurmi},
  title        = {Evaluating high-level design strategies on FPGAs for high-performance
                  computing},
  booktitle    = {27th International Conference on Field Programmable Logic and Applications,
                  {FPL} 2017, Ghent, Belgium, September 4-8, 2017},
  pages        = {1--4},
  publisher    = {{IEEE}},
  year         = {2017},
  url          = {https://doi.org/10.23919/FPL.2017.8056760},
  doi          = {10.23919/FPL.2017.8056760},
  timestamp    = {Wed, 11 Oct 2017 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/fpl/PodobasZMM17a.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpp/LinXNMM17,
  author       = {James Lin and
                  Zhigeng Xu and
                  Akira Nukada and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  title        = {Optimizations of Two Compute-Bound Scientific Kernels on the {SW26010}
                  Many-Core Processor},
  booktitle    = {46th International Conference on Parallel Processing, {ICPP} 2017,
                  Bristol, United Kingdom, August 14-17, 2017},
  pages        = {432--441},
  publisher    = {{IEEE} Computer Society},
  year         = {2017},
  url          = {https://doi.org/10.1109/ICPP.2017.52},
  doi          = {10.1109/ICPP.2017.52},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icpp/LinXNMM17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpca/KumahataMM16,
  author       = {Kiyoshi Kumahata and
                  Kazuo Minami and
                  Naoya Maruyama},
  title        = {High-performance conjugate gradient performance improvement on the
                  {K} computer},
  journal      = {Int. J. High Perform. Comput. Appl.},
  volume       = {30},
  number       = {1},
  pages        = {55--70},
  year         = {2016},
  url          = {https://doi.org/10.1177/1094342015607950},
  doi          = {10.1177/1094342015607950},
  timestamp    = {Thu, 12 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ijhpca/KumahataMM16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/bigdataconf/UenoSMFM16,
  author       = {Koji Ueno and
                  Toyotaro Suzumura and
                  Naoya Maruyama and
                  Katsuki Fujisawa and
                  Satoshi Matsuoka},
  editor       = {James Joshi and
                  George Karypis and
                  Ling Liu and
                  Xiaohua Hu and
                  Ronay Ak and
                  Yinglong Xia and
                  Weijia Xu and
                  Aki{-}Hiro Sato and
                  Sudarsan Rachuri and
                  Lyle H. Ungar and
                  Philip S. Yu and
                  Rama Govindaraju and
                  Toyotaro Suzumura},
  title        = {Extreme scale breadth-first search on supercomputers},
  booktitle    = {2016 {IEEE} International Conference on Big Data {(IEEE} BigData 2016),
                  Washington DC, USA, December 5-8, 2016},
  pages        = {1040--1047},
  publisher    = {{IEEE} Computer Society},
  year         = {2016},
  url          = {https://doi.org/10.1109/BigData.2016.7840705},
  doi          = {10.1109/BIGDATA.2016.7840705},
  timestamp    = {Fri, 19 Nov 2021 16:08:20 +0100},
  biburl       = {https://dblp.org/rec/conf/bigdataconf/UenoSMFM16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cd/MatsuokaANIKMTI16,
  author       = {Satoshi Matsuoka and
                  Hideharu Amano and
                  Kengo Nakajima and
                  Koji Inoue and
                  Tomohiro Kudoh and
                  Naoya Maruyama and
                  Kenjiro Taura and
                  Takeshi Iwashita and
                  Takahiro Katagiri and
                  Toshihiro Hanawa and
                  Toshio Endo},
  editor       = {Gianluca Palermo and
                  John Feo},
  title        = {From {FLOPS} to {BYTES:} disruptive change in high-performance computing
                  towards the post-moore era},
  booktitle    = {Proceedings of the {ACM} International Conference on Computing Frontiers,
                  CF'16, Como, Italy, May 16-19, 2016},
  pages        = {274--281},
  publisher    = {{ACM}},
  year         = {2016},
  url          = {https://doi.org/10.1145/2903150.2906830},
  doi          = {10.1145/2903150.2906830},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/cd/MatsuokaANIKMTI16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpcc/HoshinoMM16,
  author       = {Tetsuya Hoshino and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  editor       = {Jinjun Chen and
                  Laurence T. Yang},
  title        = {A Directive-Based Data Layout Abstraction for Performance Portability
                  of OpenACC Applications},
  booktitle    = {18th {IEEE} International Conference on High Performance Computing
                  and Communications; 14th {IEEE} International Conference on Smart
                  City; 2nd {IEEE} International Conference on Data Science and Systems,
                  HPCC/SmartCity/DSS 2016, Sydney, Australia, December 12-14, 2016},
  pages        = {1147--1154},
  publisher    = {{IEEE} Computer Society},
  year         = {2016},
  url          = {https://doi.org/10.1109/HPCC-SmartCity-DSS.2016.0161},
  doi          = {10.1109/HPCC-SMARTCITY-DSS.2016.0161},
  timestamp    = {Wed, 16 Oct 2019 14:14:52 +0200},
  biburl       = {https://dblp.org/rec/conf/hpcc/HoshinoMM16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpads/FukudaMMYTM16,
  author       = {Keisuke Fukuda and
                  Motohiko Matsuda and
                  Naoya Maruyama and
                  Rio Yokota and
                  Kenjiro Taura and
                  Satoshi Matsuoka},
  title        = {Tapas: An Implicitly Parallel Programming Framework for Hierarchical
                  N-Body Algorithms},
  booktitle    = {22nd {IEEE} International Conference on Parallel and Distributed Systems,
                  {ICPADS} 2016, Wuhan, China, December 13-16, 2016},
  pages        = {1100--1109},
  publisher    = {{IEEE} Computer Society},
  year         = {2016},
  url          = {https://doi.org/10.1109/ICPADS.2016.0145},
  doi          = {10.1109/ICPADS.2016.0145},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icpads/FukudaMMYTM16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwomp/AmerMPMTYB16,
  author       = {Abdelhalim Amer and
                  Satoshi Matsuoka and
                  Miquel Peric{\`{a}}s and
                  Naoya Maruyama and
                  Kenjiro Taura and
                  Rio Yokota and
                  Pavan Balaji},
  editor       = {Naoya Maruyama and
                  Bronis R. de Supinski and
                  Mohamed Wahib},
  title        = {Scaling {FMM} with Data-Driven OpenMP Tasks on Multicore Architectures},
  booktitle    = {OpenMP: Memory, Devices, and Tasks - 12th International Workshop on
                  OpenMP, {IWOMP} 2016, Nara, Japan, October 5-7, 2016, Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {9903},
  pages        = {156--170},
  year         = {2016},
  url          = {https://doi.org/10.1007/978-3-319-45550-1\_12},
  doi          = {10.1007/978-3-319-45550-1\_12},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/iwomp/AmerMPMTYB16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/ZohouriMSMM16,
  author       = {Hamid Reza Zohouri and
                  Naoya Maruyama and
                  Aaron Smith and
                  Motohiko Matsuda and
                  Satoshi Matsuoka},
  editor       = {John West and
                  Cherri M. Pancake},
  title        = {Evaluating and optimizing OpenCL kernels for high performance computing
                  with FPGAs},
  booktitle    = {Proceedings of the International Conference for High Performance Computing,
                  Networking, Storage and Analysis, {SC} 2016, Salt Lake City, UT, USA,
                  November 13-18, 2016},
  pages        = {409--420},
  publisher    = {{IEEE} Computer Society},
  year         = {2016},
  url          = {https://doi.org/10.1109/SC.2016.34},
  doi          = {10.1109/SC.2016.34},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/ZohouriMSMM16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/WahibMA16,
  author       = {Mohamed Wahib and
                  Naoya Maruyama and
                  Takayuki Aoki},
  editor       = {John West and
                  Cherri M. Pancake},
  title        = {Daino: a high-level framework for parallel and efficient {AMR} on
                  GPUs},
  booktitle    = {Proceedings of the International Conference for High Performance Computing,
                  Networking, Storage and Analysis, {SC} 2016, Salt Lake City, UT, USA,
                  November 13-18, 2016},
  pages        = {621--632},
  publisher    = {{IEEE} Computer Society},
  year         = {2016},
  url          = {https://doi.org/10.1109/SC.2016.52},
  doi          = {10.1109/SC.2016.52},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/WahibMA16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/iwomp/2016,
  editor       = {Naoya Maruyama and
                  Bronis R. de Supinski and
                  Mohamed Wahib},
  title        = {OpenMP: Memory, Devices, and Tasks - 12th International Workshop on
                  OpenMP, {IWOMP} 2016, Nara, Japan, October 5-7, 2016, Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {9903},
  year         = {2016},
  url          = {https://doi.org/10.1007/978-3-319-45550-1},
  doi          = {10.1007/978-3-319-45550-1},
  isbn         = {978-3-319-45549-5},
  timestamp    = {Tue, 14 May 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/iwomp/2016.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/WahibM15,
  author       = {Mohamed Wahib and
                  Naoya Maruyama},
  editor       = {Thilo Kielmann and
                  Dean Hildebrand and
                  Michela Taufer},
  title        = {Automated {GPU} Kernel Transformations in Large-Scale Production Stencil
                  Applications},
  booktitle    = {Proceedings of the 24th International Symposium on High-Performance
                  Parallel and Distributed Computing, {HPDC} 2015, Portland, OR, USA,
                  June 15-19, 2015},
  pages        = {259--270},
  publisher    = {{ACM}},
  year         = {2015},
  url          = {https://doi.org/10.1145/2749246.2749255},
  doi          = {10.1145/2749246.2749255},
  timestamp    = {Tue, 06 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hpdc/WahibM15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/Maruyama15,
  author       = {Naoya Maruyama},
  title        = {{PDSEC} Keynote},
  booktitle    = {2015 {IEEE} International Parallel and Distributed Processing Symposium
                  Workshop, {IPDPS} 2015, Hyderabad, India, May 25-29, 2015},
  pages        = {921},
  publisher    = {{IEEE} Computer Society},
  year         = {2015},
  url          = {https://doi.org/10.1109/IPDPSW.2015.185},
  doi          = {10.1109/IPDPSW.2015.185},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/Maruyama15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/WahibM15,
  author       = {Mohamed Wahib and
                  Naoya Maruyama},
  editor       = {Antonino Tumeo and
                  John Feo and
                  Oreste Villa},
  title        = {Data-centric GPU-based adaptive mesh refinement},
  booktitle    = {Proceedings of the 5th Workshop on Irregular Applications - Architectures
                  and Algorithms, {IA3} 2015, Austin, Texas, USA, November 15, 2015},
  pages        = {3:1--3:7},
  publisher    = {{ACM}},
  year         = {2015},
  url          = {https://doi.org/10.1145/2833179.2833181},
  doi          = {10.1145/2833179.2833181},
  timestamp    = {Tue, 06 Nov 2018 16:59:28 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/WahibM15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/SatoMMGSMM14,
  author       = {Kento Sato and
                  Kathryn M. Mohror and
                  Adam Moody and
                  Todd Gamblin and
                  Bronis R. de Supinski and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  title        = {A User-Level InfiniBand-Based File System and Checkpoint Strategy
                  for Burst Buffers},
  booktitle    = {14th {IEEE/ACM} International Symposium on Cluster, Cloud and Grid
                  Computing, CCGrid 2014, Chicago, IL, USA, May 26-29, 2014},
  pages        = {21--30},
  publisher    = {{IEEE} Computer Society},
  year         = {2014},
  url          = {https://doi.org/10.1109/CCGrid.2014.24},
  doi          = {10.1109/CCGRID.2014.24},
  timestamp    = {Tue, 25 Jul 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ccgrid/SatoMMGSMM14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/SatoMMGSMM14,
  author       = {Kento Sato and
                  Adam Moody and
                  Kathryn M. Mohror and
                  Todd Gamblin and
                  Bronis R. de Supinski and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  title        = {{FMI:} Fault Tolerant Messaging Interface for Fast and Transparent
                  Recovery},
  booktitle    = {2014 {IEEE} 28th International Parallel and Distributed Processing
                  Symposium, Phoenix, AZ, USA, May 19-23, 2014},
  pages        = {1225--1234},
  publisher    = {{IEEE} Computer Society},
  year         = {2014},
  url          = {https://doi.org/10.1109/IPDPS.2014.126},
  doi          = {10.1109/IPDPS.2014.126},
  timestamp    = {Tue, 25 Jul 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ipps/SatoMMGSMM14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/MatsudaTM14,
  author       = {Motohiko Matsuda and
                  Shin'ichiro Takizawa and
                  Naoya Maruyama},
  editor       = {Jack J. Dongarra and
                  Yutaka Ishikawa and
                  Atsushi Hori},
  title        = {Evaluation of Asynchronous {MPI} Communication in Map-Reduce System
                  on the {K} Computer},
  booktitle    = {21st European {MPI} Users' Group Meeting, EuroMPI/ASIA '14, Kyoto,
                  Japan - September 09 - 12, 2014},
  pages        = {163},
  publisher    = {{ACM}},
  year         = {2014},
  url          = {https://doi.org/10.1145/2642769.2642800},
  doi          = {10.1145/2642769.2642800},
  timestamp    = {Tue, 06 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/pvm/MatsudaTM14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/HoshinoMM14,
  author       = {Tetsuya Hoshino and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  editor       = {Sunita Chandrasekaran and
                  Fernanda S. Foertter and
                  Oscar R. Hernandez},
  title        = {An OpenACC extension for data layout transformation},
  booktitle    = {Proceedings of the First Workshop on Accelerator Programming using
                  Directives, {WACCPD} '14, New Orleans, Louisiana, USA, November 16-21,
                  2014},
  pages        = {12--18},
  publisher    = {{IEEE} Computer Society},
  year         = {2014},
  url          = {https://doi.org/10.1109/WACCPD.2014.12},
  doi          = {10.1109/WACCPD.2014.12},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/HoshinoMM14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/WahibM14,
  author       = {Mohamed Wahib and
                  Naoya Maruyama},
  editor       = {Trish Damkroger and
                  Jack J. Dongarra},
  title        = {Scalable Kernel Fusion for Memory-Bound {GPU} Applications},
  booktitle    = {International Conference for High Performance Computing, Networking,
                  Storage and Analysis, {SC} 2014, New Orleans, LA, USA, November 16-21,
                  2014},
  pages        = {191--202},
  publisher    = {{IEEE} Computer Society},
  year         = {2014},
  url          = {https://doi.org/10.1109/SC.2014.21},
  doi          = {10.1109/SC.2014.21},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/WahibM14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/HoshinoMMT13,
  author       = {Tetsuya Hoshino and
                  Naoya Maruyama and
                  Satoshi Matsuoka and
                  Ryoji Takaki},
  title        = {{CUDA} vs OpenACC: Performance Case Studies with Kernel Benchmarks
                  and a Memory-Bound {CFD} Application},
  booktitle    = {13th {IEEE/ACM} International Symposium on Cluster, Cloud, and Grid
                  Computing, CCGrid 2013, Delft, Netherlands, May 13-16, 2013},
  pages        = {136--143},
  publisher    = {{IEEE} Computer Society},
  year         = {2013},
  url          = {https://doi.org/10.1109/CCGrid.2013.12},
  doi          = {10.1109/CCGRID.2013.12},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ccgrid/HoshinoMMT13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/MatsudaMT13,
  author       = {Motohiko Matsuda and
                  Naoya Maruyama and
                  Shin'ichiro Takizawa},
  title        = {K MapReduce: {A} scalable tool for data-processing and search/ensemble
                  applications on large-scale supercomputers},
  booktitle    = {2013 {IEEE} International Conference on Cluster Computing, {CLUSTER}
                  2013, Indianapolis, IN, USA, September 23-27, 2013},
  pages        = {1--8},
  publisher    = {{IEEE} Computer Society},
  year         = {2013},
  url          = {https://doi.org/10.1109/CLUSTER.2013.6702663},
  doi          = {10.1109/CLUSTER.2013.6702663},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/MatsudaMT13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/WahibM13,
  author       = {Mohamed Wahib and
                  Naoya Maruyama},
  title        = {Highly optimized full GPU-acceleration of non-hydrostatic weather
                  model {SCALE-LES}},
  booktitle    = {2013 {IEEE} International Conference on Cluster Computing, {CLUSTER}
                  2013, Indianapolis, IN, USA, September 23-27, 2013},
  pages        = {1--8},
  publisher    = {{IEEE} Computer Society},
  year         = {2013},
  url          = {https://doi.org/10.1109/CLUSTER.2013.6702667},
  doi          = {10.1109/CLUSTER.2013.6702667},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/WahibM13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/MaruyamaKBPTZ13,
  author       = {Naoya Maruyama and
                  Leif Kobbelt and
                  Pavan Balaji and
                  Nikola Puzovic and
                  Samuel Thibault and
                  Kun Zhou},
  editor       = {Felix Wolf and
                  Bernd Mohr and
                  Dieter an Mey},
  title        = {Topic 15: {GPU} and Accelerator Computing - (Introduction)},
  booktitle    = {Euro-Par 2013 Parallel Processing - 19th International Conference,
                  Aachen, Germany, August 26-30, 2013. Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {8097},
  pages        = {800},
  publisher    = {Springer},
  year         = {2013},
  url          = {https://doi.org/10.1007/978-3-642-40047-6\_79},
  doi          = {10.1007/978-3-642-40047-6\_79},
  timestamp    = {Tue, 14 May 2019 10:00:46 +0200},
  biburl       = {https://dblp.org/rec/conf/europar/MaruyamaKBPTZ13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpp/KomodaMNM13,
  author       = {Toshiya Komoda and
                  Shinobu Miwa and
                  Hiroshi Nakamura and
                  Naoya Maruyama},
  title        = {Integrating Multi-GPU Execution in an OpenACC Compiler},
  booktitle    = {42nd International Conference on Parallel Processing, {ICPP} 2013,
                  Lyon, France, October 1-4, 2013},
  pages        = {260--269},
  publisher    = {{IEEE} Computer Society},
  year         = {2013},
  url          = {https://doi.org/10.1109/ICPP.2013.35},
  doi          = {10.1109/ICPP.2013.35},
  timestamp    = {Fri, 22 Mar 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icpp/KomodaMNM13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/BouguerraGBCMM13,
  author       = {Mohamed{-}Slim Bouguerra and
                  Ana Gainaru and
                  Leonardo Arturo Bautista{-}Gomez and
                  Franck Cappello and
                  Satoshi Matsuoka and
                  Naoya Maruyama},
  title        = {Improving the Computing Efficiency of {HPC} Systems Using a Combination
                  of Proactive and Preventive Checkpointing},
  booktitle    = {27th {IEEE} International Symposium on Parallel and Distributed Processing,
                  {IPDPS} 2013, Cambridge, MA, USA, May 20-24, 2013},
  pages        = {501--512},
  publisher    = {{IEEE} Computer Society},
  year         = {2013},
  url          = {https://doi.org/10.1109/IPDPS.2013.74},
  doi          = {10.1109/IPDPS.2013.74},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/BouguerraGBCMM13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/supercomputer/AmerMPTYM13,
  author       = {Abdelhalim Amer and
                  Naoya Maruyama and
                  Miquel Peric{\`{a}}s and
                  Kenjiro Taura and
                  Rio Yokota and
                  Satoshi Matsuoka},
  editor       = {Julian M. Kunkel and
                  Thomas Ludwig and
                  Hans Werner Meuer},
  title        = {Fork-Join and Data-Driven Execution Models on Multi-core Architectures:
                  Case Study of the {FMM}},
  booktitle    = {Supercomputing - 28th International Supercomputing Conference, {ISC}
                  2013, Leipzig, Germany, June 16-20, 2013. Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {7905},
  pages        = {255--266},
  publisher    = {Springer},
  year         = {2013},
  url          = {https://doi.org/10.1007/978-3-642-38750-0\_19},
  doi          = {10.1007/978-3-642-38750-0\_19},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/supercomputer/AmerMPTYM13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/NomuraIMM12,
  author       = {Akihiro Nomura and
                  Yutaka Ishikawa and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  title        = {Design and Implementation of Portable and Efficient Non-blocking Collective
                  Communication},
  booktitle    = {12th {IEEE/ACM} International Symposium on Cluster, Cloud and Grid
                  Computing, CCGrid 2012, Ottawa, Canada, May 13-16, 2012},
  pages        = {1--8},
  publisher    = {{IEEE} Computer Society},
  year         = {2012},
  url          = {https://doi.org/10.1109/CCGrid.2012.96},
  doi          = {10.1109/CCGRID.2012.96},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ccgrid/NomuraIMM12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/Bautista-GomezRMCM12,
  author       = {Leonardo Arturo Bautista{-}Gomez and
                  Thomas Ropars and
                  Naoya Maruyama and
                  Franck Cappello and
                  Satoshi Matsuoka},
  title        = {Hierarchical Clustering Strategies for Fault Tolerance in Large Scale
                  {HPC} Systems},
  booktitle    = {2012 {IEEE} International Conference on Cluster Computing, {CLUSTER}
                  2012, Beijing, China, September 24-28, 2012},
  pages        = {355--363},
  publisher    = {{IEEE} Computer Society},
  year         = {2012},
  url          = {https://doi.org/10.1109/CLUSTER.2012.71},
  doi          = {10.1109/CLUSTER.2012.71},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/Bautista-GomezRMCM12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/DemeshkoMTM12,
  author       = {Irina Demeshko and
                  Naoya Maruyama and
                  Hirofumi Tomita and
                  Satoshi Matsuoka},
  editor       = {Ioannis Caragiannis and
                  Michael Alexander and
                  Rosa M. Badia and
                  Mario Cannataro and
                  Alexandru Costan and
                  Marco Danelutto and
                  Fr{\'{e}}d{\'{e}}ric Desprez and
                  Bettina Krammer and
                  Julio Sahuquillo and
                  Stephen L. Scott and
                  Josef Weidendorfer},
  title        = {Multi-GPU Implementation of the {NICAM} Atmospheric Model},
  booktitle    = {Euro-Par 2012: Parallel Processing Workshops - BDMC, CGWS, HeteroPar,
                  HiBB, OMHI, Paraphrase, PROPER, Resilience, UCHPC, VHPC, Rhodes Islands,
                  Greece, August 27-31, 2012. Revised Selected Papers},
  series       = {Lecture Notes in Computer Science},
  volume       = {7640},
  pages        = {175--184},
  publisher    = {Springer},
  year         = {2012},
  url          = {https://doi.org/10.1007/978-3-642-36949-0\_20},
  doi          = {10.1007/978-3-642-36949-0\_20},
  timestamp    = {Wed, 19 Feb 2020 14:52:57 +0100},
  biburl       = {https://dblp.org/rec/conf/europar/DemeshkoMTM12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/Bautista-GomezNMCM12,
  author       = {Leonardo Arturo Bautista{-}Gomez and
                  Bogdan Nicolae and
                  Naoya Maruyama and
                  Franck Cappello and
                  Satoshi Matsuoka},
  editor       = {Christos Kaklamanis and
                  Theodore S. Papatheodorou and
                  Paul G. Spirakis},
  title        = {Scalable Reed-Solomon-Based Reliable Local Storage for {HPC} Applications
                  on IaaS Clouds},
  booktitle    = {Euro-Par 2012 Parallel Processing - 18th International Conference,
                  Euro-Par 2012, Rhodes Island, Greece, August 27-31, 2012. Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {7484},
  pages        = {313--324},
  publisher    = {Springer},
  year         = {2012},
  url          = {https://doi.org/10.1007/978-3-642-32820-6\_32},
  doi          = {10.1007/978-3-642-32820-6\_32},
  timestamp    = {Fri, 27 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/europar/Bautista-GomezNMCM12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/DrozdMM12,
  author       = {Aleksandr Drozd and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  title        = {Sequence Alignment on Massively Parallel Heterogeneous Systems},
  booktitle    = {26th {IEEE} International Parallel and Distributed Processing Symposium
                  Workshops {\&} PhD Forum, {IPDPS} 2012, Shanghai, China, May 21-25,
                  2012},
  pages        = {2498--2501},
  publisher    = {{IEEE} Computer Society},
  year         = {2012},
  url          = {https://doi.org/10.1109/IPDPSW.2012.311},
  doi          = {10.1109/IPDPSW.2012.311},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/DrozdMM12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/SatoMMMGSM12,
  author       = {Kento Sato and
                  Naoya Maruyama and
                  Kathryn M. Mohror and
                  Adam Moody and
                  Todd Gamblin and
                  Bronis R. de Supinski and
                  Satoshi Matsuoka},
  editor       = {Jeffrey K. Hollingsworth},
  title        = {Design and modeling of a non-blocking checkpointing system},
  booktitle    = {{SC} Conference on High Performance Computing Networking, Storage
                  and Analysis, {SC} '12, Salt Lake City, UT, {USA} - November 11 -
                  15, 2012},
  pages        = {19},
  publisher    = {{IEEE/ACM}},
  year         = {2012},
  url          = {https://doi.org/10.1109/SC.2012.46},
  doi          = {10.1109/SC.2012.46},
  timestamp    = {Tue, 25 Jul 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/sc/SatoMMMGSM12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/TauraNYM12,
  author       = {Kenjiro Taura and
                  Jun Nakashima and
                  Rio Yokota and
                  Naoya Maruyama},
  title        = {A Task Parallel Implementation of Fast Multipole Methods},
  booktitle    = {2012 {SC} Companion: High Performance Computing, Networking Storage
                  and Analysis, Salt Lake City, UT, USA, November 10-16, 2012},
  pages        = {617--625},
  publisher    = {{IEEE} Computer Society},
  year         = {2012},
  url          = {https://doi.org/10.1109/SC.Companion.2012.86},
  doi          = {10.1109/SC.COMPANION.2012.86},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/sc/TauraNYM12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/vecpar/DrozdMM12,
  author       = {Aleksandr Drozd and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  editor       = {Michel J. Dayd{\'{e}} and
                  Osni Marques and
                  Kengo Nakajima},
  title        = {A Multi {GPU} Read Alignment Algorithm with Model-Based Performance
                  Optimization},
  booktitle    = {High Performance Computing for Computational Science - {VECPAR} 2012,
                  10th International Conference, Kobe, Japan, July 17-20, 2012, Revised
                  Selected Papers},
  series       = {Lecture Notes in Computer Science},
  volume       = {7851},
  pages        = {270--277},
  publisher    = {Springer},
  year         = {2012},
  url          = {https://doi.org/10.1007/978-3-642-38718-0\_27},
  doi          = {10.1007/978-3-642-38718-0\_27},
  timestamp    = {Tue, 14 May 2019 10:00:36 +0200},
  biburl       = {https://dblp.org/rec/conf/vecpar/DrozdMM12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/ShimokawabeATEYMNM11,
  author       = {Takashi Shimokawabe and
                  Takayuki Aoki and
                  Tomohiro Takaki and
                  Toshio Endo and
                  Akinori Yamanaka and
                  Naoya Maruyama and
                  Akira Nukada and
                  Satoshi Matsuoka},
  editor       = {Scott A. Lathrop and
                  Jim Costa and
                  William Kramer},
  title        = {Peta-scale phase-field simulation for dendritic solidification on
                  the {TSUBAME} 2.0 supercomputer},
  booktitle    = {Conference on High Performance Computing Networking, Storage and Analysis,
                  {SC} 2011, Seattle, WA, USA, November 12-18, 2011},
  pages        = {3:1--3:11},
  publisher    = {{ACM}},
  year         = {2011},
  url          = {https://doi.org/10.1145/2063384.2063388},
  doi          = {10.1145/2063384.2063388},
  timestamp    = {Sun, 25 Oct 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/sc/ShimokawabeATEYMNM11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/MaruyamaNSM11,
  author       = {Naoya Maruyama and
                  Tatsuo Nomura and
                  Kento Sato and
                  Satoshi Matsuoka},
  editor       = {Scott A. Lathrop and
                  Jim Costa and
                  William Kramer},
  title        = {Physis: an implicitly parallel programming model for stencil computations
                  on large-scale GPU-accelerated supercomputers},
  booktitle    = {Conference on High Performance Computing Networking, Storage and Analysis,
                  {SC} 2011, Seattle, WA, USA, November 12-18, 2011},
  pages        = {11:1--11:12},
  publisher    = {{ACM}},
  year         = {2011},
  url          = {https://doi.org/10.1145/2063384.2063398},
  doi          = {10.1145/2063384.2063398},
  timestamp    = {Tue, 06 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/MaruyamaNSM11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/DrozdMM11,
  author       = {Aleksandr Drozd and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  editor       = {Scott A. Lathrop and
                  Jim Costa and
                  William Kramer},
  title        = {Poster: fast {GPU} read alignment with burrows wheeler transform based
                  index},
  booktitle    = {Conference on High Performance Computing Networking, Storage and Analysis
                  - Companion Volume, {SC} 2011, Seattle, WA, USA, November 12-18, 2011},
  pages        = {21--22},
  publisher    = {{ACM}},
  year         = {2011},
  url          = {https://doi.org/10.1145/2148600.2148612},
  doi          = {10.1145/2148600.2148612},
  timestamp    = {Fri, 03 Jul 2020 08:57:24 +0200},
  biburl       = {https://dblp.org/rec/conf/sc/DrozdMM11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/Bautista-GomezTKCMM11,
  author       = {Leonardo Arturo Bautista{-}Gomez and
                  Seiji Tsuboi and
                  Dimitri Komatitsch and
                  Franck Cappello and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  editor       = {Scott A. Lathrop and
                  Jim Costa and
                  William Kramer},
  title        = {{FTI:} high performance fault tolerance interface for hybrid systems},
  booktitle    = {Conference on High Performance Computing Networking, Storage and Analysis,
                  {SC} 2011, Seattle, WA, USA, November 12-18, 2011},
  pages        = {32:1--32:32},
  publisher    = {{ACM}},
  year         = {2011},
  url          = {https://doi.org/10.1145/2063384.2063427},
  doi          = {10.1145/2063384.2063427},
  timestamp    = {Sun, 02 Jun 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/sc/Bautista-GomezTKCMM11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/systor/SilbersteinM11,
  author       = {Mark Silberstein and
                  Naoya Maruyama},
  editor       = {Paula Ta{-}Shma and
                  Jos{\'{e}} Moreira and
                  Liuba Shrira},
  title        = {An exact algorithm for energy-efficient acceleration of task trees
                  on {CPU/GPU} architectures},
  booktitle    = {Proceedings of of {SYSTOR} 2011: The 4th Annual Haifa Experimental
                  Systems Conference, Haifa, Israel, May 30 - June 1, 2011},
  pages        = {7},
  publisher    = {{ACM}},
  year         = {2011},
  url          = {https://doi.org/10.1145/1987816.1987826},
  doi          = {10.1145/1987816.1987826},
  timestamp    = {Tue, 06 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/systor/SilbersteinM11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ngc/MaruyamaM10,
  author       = {Naoya Maruyama and
                  Satoshi Matsuoka},
  title        = {Model-based Fault Localization: Finding Behavioral Outliers in Large-scale
                  Computing Systems},
  journal      = {New Gener. Comput.},
  volume       = {28},
  number       = {3},
  pages        = {237--255},
  year         = {2010},
  url          = {https://doi.org/10.1007/s00354-009-0088-6},
  doi          = {10.1007/S00354-009-0088-6},
  timestamp    = {Thu, 14 May 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/ngc/MaruyamaM10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/GomezMCM10,
  author       = {Leonardo Arturo Bautista{-}Gomez and
                  Naoya Maruyama and
                  Franck Cappello and
                  Satoshi Matsuoka},
  title        = {Distributed Diskless Checkpoint for Large Scale Systems},
  booktitle    = {10th {IEEE/ACM} International Conference on Cluster, Cloud and Grid
                  Computing, CCGrid 2010, 17-20 May 2010, Melbourne, Victoria, Australia},
  pages        = {63--72},
  publisher    = {{IEEE} Computer Society},
  year         = {2010},
  url          = {https://doi.org/10.1109/CCGRID.2010.40},
  doi          = {10.1109/CCGRID.2010.40},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ccgrid/GomezMCM10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/green/NagasakaMNEM10,
  author       = {Hitoshi Nagasaka and
                  Naoya Maruyama and
                  Akira Nukada and
                  Toshio Endo and
                  Satoshi Matsuoka},
  title        = {Statistical power modeling of {GPU} kernels using performance counters},
  booktitle    = {International Green Computing Conference 2010, Chicago, IL, USA, 15-18
                  August 2010},
  pages        = {115--122},
  publisher    = {{IEEE} Computer Society},
  year         = {2010},
  url          = {https://doi.org/10.1109/GREENCOMP.2010.5598315},
  doi          = {10.1109/GREENCOMP.2010.5598315},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/green/NagasakaMNEM10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hipc/Bautista-GomezNMCM10,
  author       = {Leonardo Arturo Bautista{-}Gomez and
                  Akira Nukada and
                  Naoya Maruyama and
                  Franck Cappello and
                  Satoshi Matsuoka},
  title        = {Low-overhead diskless checkpoint for hybrid computing systems},
  booktitle    = {2010 International Conference on High Performance Computing, HiPC
                  2010, Dona Paula, Goa, India, December 19-22, 2010},
  pages        = {1--10},
  publisher    = {{IEEE} Computer Society},
  year         = {2010},
  url          = {https://doi.org/10.1109/HIPC.2010.5713163},
  doi          = {10.1109/HIPC.2010.5713163},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hipc/Bautista-GomezNMCM10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/EndoNMM10,
  author       = {Toshio Endo and
                  Akira Nukada and
                  Satoshi Matsuoka and
                  Naoya Maruyama},
  title        = {Linpack evaluation on a supercomputer with heterogeneous accelerators},
  booktitle    = {24th {IEEE} International Symposium on Parallel and Distributed Processing,
                  {IPDPS} 2010, Atlanta, Georgia, USA, 19-23 April 2010 - Conference
                  Proceedings},
  pages        = {1--8},
  publisher    = {{IEEE}},
  year         = {2010},
  url          = {https://doi.org/10.1109/IPDPS.2010.5470353},
  doi          = {10.1109/IPDPS.2010.5470353},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/EndoNMM10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/MaruyamaNM10,
  author       = {Naoya Maruyama and
                  Akira Nukada and
                  Satoshi Matsuoka},
  title        = {A high-performance fault-tolerant software framework for memory on
                  commodity GPUs},
  booktitle    = {24th {IEEE} International Symposium on Parallel and Distributed Processing,
                  {IPDPS} 2010, Atlanta, Georgia, USA, 19-23 April 2010 - Conference
                  Proceedings},
  pages        = {1--12},
  publisher    = {{IEEE}},
  year         = {2010},
  url          = {https://doi.org/10.1109/IPDPS.2010.5470473},
  doi          = {10.1109/IPDPS.2010.5470473},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/MaruyamaNM10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/ShimokawabeAMIKENMM10,
  author       = {Takashi Shimokawabe and
                  Takayuki Aoki and
                  Chiashi Muroi and
                  Junichi Ishida and
                  Kohei Kawano and
                  Toshio Endo and
                  Akira Nukada and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  title        = {An 80-Fold Speedup, 15.0 TFlops Full {GPU} Acceleration of Non-Hydrostatic
                  Weather Model {ASUCA} Production Code},
  booktitle    = {Conference on High Performance Computing Networking, Storage and Analysis,
                  {SC} 2010, New Orleans, LA, USA, November 13-19, 2010},
  pages        = {1--11},
  publisher    = {{IEEE}},
  year         = {2010},
  url          = {https://doi.org/10.1109/SC.2010.9},
  doi          = {10.1109/SC.2010.9},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/ShimokawabeAMIKENMM10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/LerthirunwongMM09,
  author       = {Sumeth Lerthirunwong and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  editor       = {Franck Cappello and
                  Cho{-}Li Wang and
                  Rajkumar Buyya},
  title        = {Adaptive Resource Indexing Technique for Unstructured Peer-to-Peer
                  Networks},
  booktitle    = {9th {IEEE/ACM} International Symposium on Cluster Computing and the
                  Grid, CCGrid 2009, Shanghai, China, 18-21 May 2009},
  pages        = {172--179},
  publisher    = {{IEEE} Computer Society},
  year         = {2009},
  url          = {https://doi.org/10.1109/CCGRID.2009.41},
  doi          = {10.1109/CCGRID.2009.41},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ccgrid/LerthirunwongMM09.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/grid/SatoMEM08,
  author       = {Hitoshi Sato and
                  Satoshi Matsuoka and
                  Toshio Endo and
                  Naoya Maruyama},
  title        = {Access-pattern and bandwidth aware file replication algorithm in a
                  grid environment},
  booktitle    = {9th {IEEE/ACM} International Conference on Grid Computing (Grid 2008),
                  Tsukuba, Japan, September 29 - October 1, 2008},
  pages        = {250--257},
  publisher    = {{IEEE} Computer Society},
  year         = {2008},
  url          = {https://doi.org/10.1109/GRID.2008.4662806},
  doi          = {10.1109/GRID.2008.4662806},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/grid/SatoMEM08.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/MaruyamaM08,
  author       = {Naoya Maruyama and
                  Satoshi Matsuoka},
  title        = {Model-based fault localization in large-scale computing systems},
  booktitle    = {22nd {IEEE} International Symposium on Parallel and Distributed Processing,
                  {IPDPS} 2008, Miami, Florida USA, April 14-18, 2008},
  pages        = {1--12},
  publisher    = {{IEEE}},
  year         = {2008},
  url          = {https://doi.org/10.1109/IPDPS.2008.4536310},
  doi          = {10.1109/IPDPS.2008.4536310},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/MaruyamaM08.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/OgataEMM08,
  author       = {Yasuhiko Ogata and
                  Toshio Endo and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  title        = {An efficient, model-based {CPU-GPU} heterogeneous {FFT} library},
  booktitle    = {22nd {IEEE} International Symposium on Parallel and Distributed Processing,
                  {IPDPS} 2008, Miami, Florida USA, April 14-18, 2008},
  pages        = {1--10},
  publisher    = {{IEEE}},
  year         = {2008},
  url          = {https://doi.org/10.1109/IPDPS.2008.4536163},
  doi          = {10.1109/IPDPS.2008.4536163},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/OgataEMM08.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/NishimuraMM07,
  author       = {Hideo Nishimura and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  title        = {Virtual Clusters on the Fly - Fast, Scalable, and Flexible Installation},
  booktitle    = {Seventh {IEEE} International Symposium on Cluster Computing and the
                  Grid (CCGrid 2007), 14-17 May 2007, Rio de Janeiro, Brazil},
  pages        = {549--556},
  publisher    = {{IEEE} Computer Society},
  year         = {2007},
  url          = {https://doi.org/10.1109/CCGRID.2007.121},
  doi          = {10.1109/CCGRID.2007.121},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ccgrid/NishimuraMM07.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/YamasakiMM07,
  author       = {Shohei Yamasaki and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  title        = {Model-based resource selection for efficient virtual cluster deployment},
  booktitle    = {Proceedings of the 2nd International Workshop on Virtualization Technology
                  in Distributed Computing, VTDC@SC 2007, Reno, Nevada, USA, November
                  2007},
  pages        = {6:1--6:7},
  publisher    = {{ACM}},
  year         = {2007},
  url          = {https://doi.org/10.1145/1408654.1408660},
  doi          = {10.1145/1408654.1408660},
  timestamp    = {Wed, 16 Oct 2019 14:14:57 +0200},
  biburl       = {https://dblp.org/rec/conf/sc/YamasakiMM07.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ispa/TatezonoMM06,
  author       = {Masaki Tatezono and
                  Naoya Maruyama and
                  Satoshi Matsuoka},
  editor       = {Geyong Min and
                  Beniamino Di Martino and
                  Laurence Tianruo Yang and
                  Minyi Guo and
                  Gudula R{\"{u}}nger},
  title        = {Making Wide-Area, Multi-site {MPI} Feasible Using Xen {VM}},
  booktitle    = {Frontiers of High Performance Computing and Networking - {ISPA} 2006
                  Workshops, {ISPA} 2006 International Workshops, FHPCN, XHPC, S-GRACE,
                  GridGIS, HPC-GTP, PDCE, ParDMCom, WOMP, ISDF, and UPWN, Sorrento,
                  Italy, December 4-7, 2006, Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {4331},
  pages        = {387--396},
  publisher    = {Springer},
  year         = {2006},
  url          = {https://doi.org/10.1007/11942634\_41},
  doi          = {10.1007/11942634\_41},
  timestamp    = {Tue, 14 May 2019 10:00:40 +0200},
  biburl       = {https://dblp.org/rec/conf/ispa/TatezonoMM06.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/MirgorodskiyMM06,
  author       = {Alexander V. Mirgorodskiy and
                  Naoya Maruyama and
                  Barton P. Miller},
  title        = {Scalable systems software - Problem diagnosis in large-scale computing
                  environments},
  booktitle    = {Proceedings of the {ACM/IEEE} {SC2006} Conference on High Performance
                  Networking and Computing, November 11-17, 2006, Tampa, FL, {USA}},
  pages        = {88},
  publisher    = {{ACM} Press},
  year         = {2006},
  url          = {https://doi.org/10.1145/1188455.1188548},
  doi          = {10.1145/1188455.1188548},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/MirgorodskiyMM06.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
a service of  Schloss Dagstuhl - Leibniz Center for Informatics