• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Research on architecture of optoelectronic integrated circuits and their design methodology

Research Project

Project/Area Number 20H04155
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 60040:Computer system-related
Research InstitutionNagoya University

Principal Investigator

Ishihara Tohru  名古屋大学, 情報学研究科, 教授 (30323471)

Co-Investigator(Kenkyū-buntansha) 塩見 準  大阪大学, 大学院情報科学研究科, 准教授 (40809795)
納富 雅也  東京工業大学, 理学院, 教授 (50393799)
増田 豊  名古屋大学, 情報学研究科, 准教授 (60845527)
Project Period (FY) 2020-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥17,550,000 (Direct Cost: ¥13,500,000、Indirect Cost: ¥4,050,000)
Fiscal Year 2022: ¥5,330,000 (Direct Cost: ¥4,100,000、Indirect Cost: ¥1,230,000)
Fiscal Year 2021: ¥6,110,000 (Direct Cost: ¥4,700,000、Indirect Cost: ¥1,410,000)
Fiscal Year 2020: ¥6,110,000 (Direct Cost: ¥4,700,000、Indirect Cost: ¥1,410,000)
Keywords計算機システム / 光電融合回路 / 光ニューラルネットワーク / 光コンピューティング / 光集積回路 / 低消費電力設計 / 設計最適化
Outline of Research at the Start

2000年以降のナノフォトニクス技術の急速な発展を背景に、光デバイスは数ミクロンのサイズまで超小型化され、光回路と電子回路を混載して集積することが可能となった。本課題は、光と電子が密に融合する光集積回路のアーキテクチャと設計技術を構築することにより、光集積回路における遅延-電力-面積のトレードオフ限界を明確にし、光集積回路の最適な構成を明らかにするものである。上記目的のために、下記の3項目に取り組む。1)回路設計段階で光集積回路の遅延、電力、面積を予測するモデルを構築する。2)光集積回路に対する設計最適化技術を構築する。3)光集積回路を非ノイマン型演算器に適用し最適化の効果を評価する。

Outline of Final Research Achievements

This research project aims to clarify the Pareto-optimal boundary for delay-power-area in optoelectronic integrated circuits by building architecture and design technology for optoelectronic integrated circuits in which photonic and electronic circuits are closely integrated. The purpose of this study is to clarify the optimal configuration of the optoelectronic integrated circuits. For this purpose, in the first year, we created a model for estimating circuit delay, power consumption, and circuit area of the optoelectronic integrated circuits. In FY2021, we developed a method to apply parallel computing technology based on Wavelength Division Multiplexing (WDM) and various low power consumption methods developed in past research to optical neural network circuits. Based on the results achieved up to the previous year, in the final year we devised and evaluated a optoelectronic recurrent neural network (RNN) architecture.

Academic Significance and Societal Importance of the Research Achievements

本研究課題は、世界に先駆けて光電融合集積回路に対する遅延、電力、面積のモデルを構築し、そのモデルに基づいて光電融合集積回路を最適設計する手法を構築した。また、光電融合集積回路を深層ニューラルネットワークに適用し、光ニューラルネットワークの最適なアーキテクチャを明らかにした。具体的には、光電融合集積回路に基づくリカレントニューラルネットワーク(RNN)アーキテクチャを開発した。光ニューラルネットワークの開発は、AI推論処理を超低遅延化し省エネルギー化する技術として学術的かつ社会的意義の高い先駆的な研究成果である。今後ますます大量のデータが超広帯域で流通する情報化社会に必要不可欠な研究成果である。

Report

(4 results)
  • 2023 Final Research Report ( PDF )
  • 2022 Annual Research Report
  • 2021 Annual Research Report
  • 2020 Annual Research Report
  • Research Products

    (13 results)

All 2024 2022 2021 2020

All Journal Article (5 results) (of which Peer Reviewed: 5 results) Presentation (8 results) (of which Int'l Joint Research: 6 results)

  • [Journal Article] A Synthesis Method Based on Multi-Stage Optimization for Power-Efficient Integrated Optical Logic Circuits2021

    • Author(s)
      MATSUO Ryosuke、SHIOMI Jun、ISHIHARA Tohru、ONODERA Hidetoshi、SHINYA Akihiko、NOTOMI Masaya
    • Journal Title

      IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

      Volume: E104.A Issue: 11 Pages: 1546-1554

    • DOI

      10.1587/transfun.2020KEP0018

    • NAID

      130008109844

    • ISSN
      0916-8508, 1745-1337
    • Year and Date
      2021-11-01
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Neural Network Calculations at the Speed of Light Using Optical Vector-Matrix Multiplication and Optoelectronic Activation2021

    • Author(s)
      HATTORI Naoki、SHIOMI Jun、MASUDA Yutaka、ISHIHARA Tohru、SHINYA Akihiko、NOTOMI Masaya
    • Journal Title

      IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

      Volume: E104.A Issue: 11 Pages: 1477-1487

    • DOI

      10.1587/transfun.2020KEP0016

    • NAID

      130008109846

    • ISSN
      0916-8508, 1745-1337
    • Year and Date
      2021-11-01
    • Related Report
      2021 Annual Research Report 2020 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Optical-electronic implementation of artificial neural network for ultrafast and accurate inference processing2021

    • Author(s)
      Hattori Naoki、Masuda Yutaka、Ishihara Tohru、Shiomi Jun、Shinya Akihiko、Notomi Masaya
    • Journal Title

      Proc. AI and Optical Data Sciences II. International Society for Optics and Photonics

      Pages: 415-421

    • DOI

      10.1117/12.2577966

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed
  • [Journal Article] 集積ナノフォトニクスに基づく光ニューラルネットワークを対象とした回路アーキテクチャ探索2020

    • Author(s)
      服部直樹, 増田豊, 石原亨, 塩見準, 新家昭彦, 納富雅也
    • Journal Title

      第33回 回路とシステムワークショップ論文集

      Volume: IEICE-VLD2019-137 Pages: 10-15

    • NAID

      40022400516

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed
  • [Journal Article] An Optical Accelerator for Deep Neural Network Based on Integrated Nanophotonics2020

    • Author(s)
      Shiomi Jun、Ishihara Tohru、Onodera Hidetoshi、Shinya Akihiko、Notomi Masaya
    • Journal Title

      Proc. IEEE International Conference on Rebooting Computing

      Pages: 95-101

    • DOI

      10.1109/icrc2020.2020.00017

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed
  • [Presentation] An optoelectronic pipelined convolutional-RNN architecture for energy-efficient AI accelerator2024

    • Author(s)
      Chunlu Wang, Yutaka Masuda, Tohru Ishihara
    • Organizer
      Workshop on Synthesis And System Integration of Mixed Information technologies (SASIMI)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Optoelectronic Implementation of Compact and Power-Efficient Recurrent Neural Networks2022

    • Author(s)
      Taisei Ichikawa, Yutaka Masuda, Tohru Ishihara, Akihiko Shinya, Masaya Notomi
    • Organizer
      IEEE Computer Society Annual Symposium on VLSI (ISVLSI)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Power-Aware Pruning for Ultrafast, Energy-Efficient, and Accurate Optical Neural Network Design2022

    • Author(s)
      Naoki Hattori, Yutaka Masuda, Tohru Ishihara, Akihiko Shinya, Masaya Notomi
    • Organizer
      Design Automation Conference (DAC)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 省面積と低電力を両立する光電融合RNN アーキテクチャ2022

    • Author(s)
      市川大生, 増田豊, 石原亨, 新家昭彦, 納富雅也
    • Organizer
      第35 回回路とシステムワークショップ論文集
    • Related Report
      2022 Annual Research Report
  • [Presentation] Energy efficient OEO conversion and its applications to photonic integrated systems2022

    • Author(s)
      Akihiko Shinya, Kengo Nozaki, Shota Kita, Tohru Ishihara, Shingo Matsuo, Masaya Notomi,
    • Organizer
      IEEE Optical Fiber Communications Conference and Exhibition (OFC)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Optical-electronic implementation of artificial neural network for ultrafast and accurate inference processing2021

    • Author(s)
      Hattori Naoki、Masuda Yutaka、Ishihara Tohru、Shiomi Jun、Shinya Akihiko、Notomi Masaya
    • Organizer
      SPIE Conference 11703, AI and Optical Data Sciences II
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 集積ナノフォトニクスに基づく光ニューラルネットワークを対象とした回路アーキテクチャ探索2020

    • Author(s)
      服部直樹, 増田豊, 石原亨, 塩見準, 新家昭彦, 納富雅也
    • Organizer
      第33回 回路とシステムワークショップ
    • Related Report
      2020 Annual Research Report
  • [Presentation] An Optical Accelerator for Deep Neural Network Based on Integrated Nanophotonics2020

    • Author(s)
      Shiomi Jun、Ishihara Tohru、Onodera Hidetoshi、Shinya Akihiko、Notomi Masaya
    • Organizer
      IEEE International Conference on Rebooting Computing
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research

URL: 

Published: 2020-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi