@article{CTT100845805,
  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 Transactions on Parallel & Distributed Systems (TPDS)},
  year = 2021,
}

@inproceedings{CTT100845807,
  author = {Jens Domke and Emil Vatai and Alexsandr Drozd and Peng Chen and Yosuke Oyama and Lingqi Zhang and Shweta Salaria and Daichi Mukunoki and Artur Podobas and Mohamed Wahib and Satoshi Matsuoka},
  title = {Matrix Engines for High Performance Computing: A Paragon of Performance or Grasping at Straws?},
  booktitle = {},
  year = 2021,
}

@inproceedings{CTT100802961,
  author = {Yosuke Oyama and Naoya Maruyama and Nikoli Dryden and Peter Harrington and Jan Balewski and Satoshi Matsuoka and Marc Snir and Peter Nugent and Brian Van Essen},
  title = {Toward Training a Large 3D Cosmological CNN with Hybrid Parallelization},
  booktitle = {},
  year = 2019,
}

@inproceedings{CTT100802588,
  author = {Yosuke Oyama and Naoya Maruyama and Nikoli Dryden and Peter Harrington and Jan Balewski and Satoshi Matsuoka and Marc Snir and Peter Nugent and Brian Van Essen},
  title = {Toward Training a Large 3D Cosmological CNN with Hybrid Parallelization},
  booktitle = {},
  year = 2019,
}

@inproceedings{CTT100800873,
  author = {Yosuke Oyama and Naoya Maruyama and Nikoli Dryden and Peter Harrington and Jan Balewski and Satoshi Matsuoka and Marc Snir and Peter Nugent and Brian Van Essen},
  title = {Toward Training a Large 3D Cosmological CNN with Hybrid Parallelization},
  booktitle = {},
  year = 2019,
}

@inproceedings{CTT100802673,
  author = {Toshiki Tsuchikawa and Toshio Endo and Akihiro Nomura and Masaaki Kondo and Yosuke Oyama and SATOSHI MATSUOKA},
  title = {メモリアクセスデータを用いた機械学習によるアプリケーションの類型化},
  booktitle = {},
  year = 2019,
}

@inproceedings{CTT100793973,
  author = {Yosuke Oyama and Tal Ben-Nun and Torsten Hoefler and Satoshi Matsuoka},
  title = {u-cuDNN: Accelerating Deep Learning Frameworks with Micro-Batches},
  booktitle = {},
  year = 2019,
}

@inproceedings{CTT100771394,
  author = {Yosuke Oyama and Tal Ben-Nun and Torsten Hoefler and Satoshi Matsuoka},
  title = {Accelerating Deep Learning Frameworks with Micro-batches},
  booktitle = {},
  year = 2018,
}

@inproceedings{CTT100802677,
  author = {Toshiki Tsuchikawa and Yosuke Oyama and Akihiro Nomura and SATOSHI MATSUOKA},
  title = {機械学習による計算機トレースの自動生成},
  booktitle = {},
  year = 2018,
}

@inproceedings{CTT100802679,
  author = {Keita Yashima and Yosuke Oyama and SATOSHI MATSUOKA},
  title = {深層学習におけるBatchNormalization使用時の計算時間と精度の関係性},
  booktitle = {},
  year = 2018,
}

@inproceedings{CTT100758523,
  author = {Yosuke Oyama and Tal Ben-Nun and Torsten Hoefler and Satoshi Matsuoka},
  title = {Less is More: Accelerating Deep Neural Networks with Micro-Batching},
  booktitle = {},
  year = 2017,
}

@inproceedings{CTT100829961,
  author = {Ikuro Sato and Ryo Fujisaki and Yosuke Oyama and Akihiro Nomura and Satoshi Matsuoka},
  title = {Asynchronous, data-parallel deep convolutional neural network training with linear prediction model for parameter transition},
  booktitle = {International Conference on Neural Information Processing},
  year = 2017,
}

@inproceedings{CTT100741817,
  author = {Yosuke Oyama and Akihiro Nomura and Ikuro Sato and Hiroki Nishimura and Yukimasa Tamatsu and Satoshi Matsuoka},
  title = {Predicting Probabilistic Parameters of a Large-Scale Asynchronous SGD Deep Learning System},
  booktitle = {},
  year = 2017,
}

@inproceedings{CTT100737165,
  author = {Yosuke Oyama and Akihiro Nomura and 佐藤育郎 and SATOSHI MATSUOKA},
  title = {ディープラーニングのデータ並列学習における少精度浮動小数点数を用いた通信量の削減},
  booktitle = {},
  year = 2017,
}

@inproceedings{CTT100734705,
  author = {Yosuke Oyama and Akihiro Nomura and Ikuro Sato and Hiroki Nishimura and Yukimasa Tamatsu and Satoshi Matsuoka},
  title = {Predicting Statistics of Asynchronous SGD Parameters for a Large-Scale Distributed Deep Learning System on GPU Supercomputers},
  booktitle = {},
  year = 2016,
}

@inproceedings{CTT100734459,
  author = {Yosuke Oyama and Hiroki Ohtsuji and Jun Kato and Kosuke Suzuki and Mitsuru Sato and Eiji Yoshida},
  title = {Partially-Decompressible Dictionary Based Compression Format for All Flash Array},
  booktitle = {},
  year = 2016,
}

@inproceedings{CTT100734458,
  author = {Yosuke Oyama and Akihiro Nomura and 佐藤育郎 and 西村裕紀 and 玉津幸政 and SATOSHI MATSUOKA},
  title = {学習条件を考慮した大規模非同期ディープラーニングシステムの性能モデリング},
  booktitle = {},
  year = 2016,
}

@inproceedings{CTT100704626,
  author = {Yosuke Oyama and Akihiro Nomura and Ikuro Sato and Hiroki Nishimura and Yukimasa Tamatsu and SATOSHI MATSUOKA},
  title = {Training Condition Conscious Performance Modeling of an Asynchronous Data-Parallel Deep Learning System},
  booktitle = {},
  year = 2016,
}

@misc{CTT100845804,
  author = {Jens Domke and Emil Vatai and Alexsandr Drozd and Peng Chen and Yosuke Oyama and Lingqi Zhang and Shweta Salaria and Daichi Mukunoki and Artur Podobas and Mohamed Wahib and Satoshi Matsuoka},
  title = {Matrix Engines for High Performance Computing: A Paragon of Performance or Grasping at Straws?},
  year = 2020,
}

@misc{CTT100845803,
  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},
  year = 2020,
}

@misc{CTT100771395,
  author = {Yosuke Oyama and Tal Ben-Nun and Torsten Hoefler and Satoshi Matsuoka},
  title = {μ-cuDNN},
  year = 2018,
}

@misc{CTT100764211,
  author = {Yosuke Oyama and Tal Ben-Nun and Torsten Hoefler and SATOSHI MATSUOKA},
  title = {μ-cuDNN: Accelerating Deep Learning Frameworks with Micro-Batching},
  year = 2018,
}

@misc{CTT100887766,
  author = {Yosuke Oyama},
  title = {Hierarchical Hybrid Parallel Training of Large-Scale Convolutional Neural Networks},
  year = 2021,
}

@misc{CTT100844426,
  author = {Yosuke Oyama},
  title = {Hierarchical Hybrid Parallel Training of Large-Scale Convolutional Neural Networks},
  year = 2021,
}

@misc{CTT100844427,
  author = {Yosuke Oyama},
  title = {Hierarchical Hybrid Parallel Training of Large-Scale Convolutional Neural Networks},
  year = 2021,
}

@misc{CTT100774295,
  author = {SATOSHI MATSUOKA and Akihiro Nomura and Yosuke Oyama},
  title = {学習システムおよび学習方法},
  howpublished = {RegisteredPatent},
  year = 2020,
  month  = {},
  note   = {特願2016-253169(2016/12/27), 特開2018-106489(2018/07/05), 特許第6704583号(2020/05/15)}
}


@misc{CTT100768968,
  author = {SATOSHI MATSUOKA and Akihiro Nomura and Yosuke Oyama},
  title = {予測装置、予測方法および予測プログラム},
  howpublished = {RegisteredPatent},
  year = 2019,
  month  = {},
  note   = {特願2016-150221(2016/07/29), 特開2018-018422(2018/02/01), 特許第6635265号(2019/12/27)}
}




@phdthesis{CTT100887766,
  author = {Yosuke Oyama},
  title = {Hierarchical Hybrid Parallel Training of Large-Scale Convolutional Neural Networks},
  school = {Tokyo Institute of Technology},
  year = 2021,
}

@phdthesis{CTT100844426,
  author = {Yosuke Oyama},
  title = {Hierarchical Hybrid Parallel Training of Large-Scale Convolutional Neural Networks},
  school = {Tokyo Institute of Technology},
  year = 2021,
}

@phdthesis{CTT100844427,
  author = {Yosuke Oyama},
  title = {Hierarchical Hybrid Parallel Training of Large-Scale Convolutional Neural Networks},
  school = {Tokyo Institute of Technology},
  year = 2021,
}