English Version



です.The 9th NCSS workshopでは,幅広く論文を募集しますので是非ご投稿ください.

  • 5月29日までに事前登録いただければ,参加費は無料です.会場での参加登録費は1,000円です.




  • Workshop on In Nonvolatile-memory Distributed Approximate Computing
  • 9:30-9:35 開会の挨拶 竹内 健(中大)
  • 9:35-9:40 来賓の挨拶 藤野 泰弘(NEDO)
  • 9:40-10:10 首藤 一幸(東工大)、ブロックチェーン「ネットワーク」の研究
  • 10:10-10:40 竹内 健(中大),Approximate不揮発性メモリ
  • 10:40-11:00 菅 真樹(リトルウィング),Approximate分散処理による深層学習処理の高速化に向けて
  • 11:00-11:20 平澤 将一(NII),Approximateネットワークと活用手法
  • 11:20-11:30 Closing


  • Workshop on Accelerator Cloud Computing
  • 12:30-13:00 工藤 知宏, Accelerator Cloud構想
  • 13:00-13:30 高野 了成,池上 努,アクセラレータクラウドを実現するシステムソフトウェア FlowOS
  • 13:30-13:50 Tomokazu Higuchi (U of Tokyo), ClPy: A NumPy-compatible Library accelerated with OpenCL
  • 13:50-14:20 天野 英晴,Virtual Large FPGA with a number of economical mid-range FPGAs
  • 14:20-14:40 大内 真一, CNN processor for training in edge devices using short-bit floating point format,「短ビット長浮動小数点データを用いたエッジデバイス用CNNプロセッサ」
  • 14:40-15:00 川口 博,データ並列深層学習の高速化手法

NCSS Oral Session

  • 12:30-15:00
  • Each presentation will be of 25 minutes duration, which includes 5-minute question and discussion time.
  • An asynchronous P system with branch and bound for solving Hamiltonian cycle problem, Akihiro Fujiwara, Kotaro Umetsu and Fumiya Nozato
  • Analysis of Supermarket Customer Behavior by Using RFM and Huff's Gravity Model, Yepeng Cheng and Yasuhiko Morimoto
  • Disk I/O Control Mechanism for Online and Batch Processing,Masanori Tanabe, Yoshinari Nomura, Kazutoshi Yokoyama, Takashi Nagao and Hiedo Taniguchi
  • Rule Generation for Signature Based Detection Systems of Cyber Attacks in IoT Environments, Yan Naung Soe, Yaokai Feng, Paulus Insap Santosa, Rudy Hartanto and Kouichi Sakurai
  • Siva - The IPFS Search Engine, Nawras Khudhur and Satoshi Fujita
  • A Framework of Moving Target Defenses for the Internet of Things, Wai Kyi Kyi Oo and Hiroshi Koide

NCSS Poster Session

  • 15:05-15:55
  • The size of a poster is up to A0 size.
  • Iterative Inference Technique for Image-to-image Translation of Tile Art Image Generation,Naoki Matsumura, Yasuaki Ito and Koji Nakano
  • An Efficient Convolutional Neural Network Computation using AVX-512 Instructions, Hiroki Kataoka, Koji Nakano and Yasuaki Ito
  • A GPU Implementation of Non-photorealistic Stained Glass Image Generation using Voronoi Diagrams, Hironobu Kobayashi, Yasuaki Ito and Koji Nakano
  • A strawberry optimization algorithm for the multi-objective knapsack problem, Yamato Mizobe and Akihiro Fujiwara
  • Design and Implementation of Circuit Switched Scheduling in Flow-in-Cloud Systems,Yao Hu and Michihiro Koibuchi
  • A Two-Opt Collective-Communication Method for Low-Latency Random Network Topologies, Ke Cui and Michihiro Koibuchi
  • Accelerating GPU implementation of All Pairs Shortest Path Algorithm, Daisuke Takafuji, Koji Nakano and Yasuaki Ito

Keynote Talks

  • 16:00-16:45 笠置明彦(富士通研究所),分散深層学習の高速化テクニック
  • 16:45-17:30 安戸僚汰(広島大学),スーパーコンピュータ向けネットワークトポロジのグラフ理論的展望