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

Theory and Application of Scalable Numerical Software on an O(100M) core environment

Research Project

Project/Area Number 15H02709
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Research Field High performance computing
Research InstitutionInstitute of Physical and Chemical Research

Principal Investigator

IMAMURA Toshiyuki  国立研究開発法人理化学研究所, 計算科学研究機構, チームリーダー (60361838)

Co-Investigator(Kenkyū-buntansha) 大井 祥栄  国立研究開発法人理化学研究所, 計算科学研究機構, 特別研究員 (10721045)
深谷 猛  北海道大学, 情報基盤センター, 助教 (30633846)
廣田 悠輔  国立研究開発法人理化学研究所, 計算科学研究機構, 特別研究員 (60709765)
椋木 大地  東京女子大学, 理学(系)研究科(研究院), 特任研究員 (90742289)
Co-Investigator(Renkei-kenkyūsha) YAMAMOTO Yusaku  国立大学法人電気通信大学, 情報理工学研究科, 教授 (20362288)
Todo Shinji  国立大学法人東京大学, 理学系研究科, 准教授 (10291337)
Project Period (FY) 2015-04-01 – 2018-03-31
Project Status Completed (Fiscal Year 2017)
Budget Amount *help
¥18,330,000 (Direct Cost: ¥14,100,000、Indirect Cost: ¥4,230,000)
Fiscal Year 2017: ¥5,200,000 (Direct Cost: ¥4,000,000、Indirect Cost: ¥1,200,000)
Fiscal Year 2016: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2015: ¥8,450,000 (Direct Cost: ¥6,500,000、Indirect Cost: ¥1,950,000)
Keywords高性能計算 / 非同期 / 省通信・省同期 / メニイコア / 自動チューニング / 分割統治法 / 時空間タイリング / 時間方向並列 / 非同期アルゴリズム / 通信回避 / 超メニイコア / スレッド数自動調整 / ハイパフォーマンス・コンピューティング / アルゴリズム / 数理工学 / 通信回避や非同期性 / ハイパフォーマンスコンピューティング / スケーラブル / 通信同期回避 / 時間方向離散 / 異粒度数値カーネル
Outline of Final Research Achievements

This research project aims to realize high performance numerical services investigated in the past based on new mathematical principles in the emerging computing system where tens of thousands to hundreds of millions of processing cores are installed. Giving two important themes, `Mixed-granularity numerical kernel' and `Asynchronous numerical algorithm,' we conducted; i) the research on the theory of asynchronous numerical algorithms. Also avoidance of communication and synchronization at a practical level, then CAHTR and a new method for the FDTD scheme were proposed. Furthermore, we have practiced; ii) promoting research on core numerical infrastructure technologies such as automatic tuning for scalable, lightweight code generation at super-many-core, and promoting innovative research leading to the next generation numerical calculation software.

Report

(4 results)
  • 2017 Annual Research Report   Final Research Report ( PDF )
  • 2016 Annual Research Report
  • 2015 Annual Research Report
  • Research Products

    (51 results)

All 2018 2017 2016 2015

All Journal Article (15 results) (of which Peer Reviewed: 5 results,  Acknowledgement Compliant: 7 results) Presentation (36 results) (of which Int'l Joint Research: 14 results,  Invited: 4 results)

  • [Journal Article] Time-space tiling with tile-level parallelism for the 3D FDTD method2018

    • Author(s)
      Fukaya Takeshi、Iwashita Takeshi
    • Journal Title

      Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region (HPC Asia 2018),

      Volume: - Pages: 116-126

    • DOI

      10.1145/3149457.3149478

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Parallel Divide-and-Conquer Algorithm for Solving Tridiagonal Eigenvalue Problems on Manycore Systems2018

    • Author(s)
      Hirota Yusuke、Imamura Toshiyuki
    • Journal Title

      Lecture Notes in Computer Science book series

      Volume: 10777 Pages: 623-633

    • DOI

      10.1007/978-3-319-78024-5_54

    • ISBN
      9783319780238, 9783319780245
    • Related Report
      2017 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Design Towards Modern High Performance Numerical LA Library Enabling Heterogeneity and Flexible Data Formats2018

    • Author(s)
      Toshiyuki Imamura, Daichi Mukunoki, Yusuke Hirota, Susumu Yamada, Masahiko Machida
    • Journal Title

      Advances in Parallel Computing

      Volume: 32 Pages: 97-106

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed
  • [Journal Article] メニーコアプロセッサにおける多軸分割を用いた3次元FFTの性能評価2018

    • Author(s)
      青木 聖陽, 今村 俊幸, 横川 三津夫, 廣田 悠輔
    • Journal Title

      研究報告ハイパフォーマンスコンピューティング(HPC)

      Volume: 2018-HPC-163(29) Pages: 1-7

    • Related Report
      2017 Annual Research Report
  • [Journal Article] Knights Landing におけるTiled 3D FDTDカーネルの性能評価2018

    • Author(s)
      深谷猛,岩下武史
    • Journal Title

      研究報告ハイパフォーマンスコンピューティング(HPC)

      Volume: Vol.2018-HPC-164(6) Pages: 1-9

    • Related Report
      2017 Annual Research Report
  • [Journal Article] FFTカーネルを用いたKNLでのスケーラビリティに関する調査2017

    • Author(s)
      青木 聖陽, 廣田 悠輔, 今村 俊,幸 横川 三津夫
    • Journal Title

      研究報告ハイパフォーマンスコンピューティング(HPC)

      Volume: 2017-HPC-161(16) Pages: 1-7

    • Related Report
      2017 Annual Research Report
  • [Journal Article] タイルレベルの並列処理を可能とする時空間タイリング手法を用いた3次元FDTDカーネルの実装と性能評価2017

    • Author(s)
      深谷猛, 岩下武史
    • Journal Title

      研究報告ハイパフォーマンスコンピューティング(HPC)

      Volume: Vol.2017‐HPC‐160(35) Pages: 1-11

    • Related Report
      2017 Annual Research Report
  • [Journal Article] メニーコアプロセッサ向け分割統治法の実装技術2017

    • Author(s)
      廣田悠輔,今村俊幸
    • Journal Title

      情報処理学会研究報告ハイパフォーマンスコンピューティング(HPC)

      Volume: Vol.2017-HPC-158, NO.20 Pages: 1-9

    • Related Report
      2016 Annual Research Report
    • Acknowledgement Compliant
  • [Journal Article] Automatic Thread-Block Size Adjustment for Memory-Bound BLAS Kernels on GPUs2016

    • Author(s)
      Daichi Mukunoki, Toshiyuki Imamura and Daisuke Takahashi
    • Journal Title

      Proceedings of IEEE 10th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC-16)

      Volume: なし Pages: 377-384

    • DOI

      10.1109/mcsoc.2016.32

    • Related Report
      2016 Annual Research Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Journal Article] 大規模並列計算機における連立一次方程式の精度保証付き数値計算に対する性能評価2016

    • Author(s)
      森倉 悠介, 椋木 大地, 深谷 猛, 山中 脩也, 大石 進一
    • Journal Title

      情報処理学会研究報告ハイパフォーマンスコンピューティング(HPC)

      Volume: Vol.2017-HPC-157, NO.1 Pages: 1-7

    • Related Report
      2016 Annual Research Report
    • Acknowledgement Compliant
  • [Journal Article] コンシューマレンジGPUに最適化した固有値ソルバーの実装と評価2016

    • Author(s)
      今村俊幸,椋木大地
    • Journal Title

      情報処理学会研究報告ハイパフォーマンスコンピューティング(HPC)

      Volume: 2016-HPC-157,NO.7 Pages: 1-9

    • Related Report
      2016 Annual Research Report
    • Acknowledgement Compliant
  • [Journal Article] ポストムーア時代のATと数値線形代数2016

    • Author(s)
      今村俊幸
    • Journal Title

      計算工学講演会論文集

      Volume: 21, F-2-2 Pages: 1-2

    • Related Report
      2016 Annual Research Report
  • [Journal Article] CAHTR: Communication-Avoiding Householder Tridiagonalization2016

    • Author(s)
      Toshiyuki Imamura, Takeshi Fukaya, Yusuke Hirota, Susumu Yamada, Masahiko Machida
    • Journal Title

      Advances in Parallel Computing

      Volume: 27 Pages: 381-390

    • Related Report
      2015 Annual Research Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Journal Article] NVIDIA GPUにおけるメモリ律速なBLASカーネルのスレッド数自動選択手法2015

    • Author(s)
      椋木大地,今村俊幸,高橋大介
    • Journal Title

      情報処理学会研究報告

      Volume: 2015-HPC-150, No.13 Pages: 1-13

    • Related Report
      2015 Annual Research Report
    • Acknowledgement Compliant
  • [Journal Article] SYMV・GEMVルーチン群のマルチGPU化とその評価2015

    • Author(s)
      今村俊幸, 椋木大地, 山田進, 町田昌彦
    • Journal Title

      情報処理学会研究報告

      Volume: 2015-HPC-151, Vol.13 Pages: 1-8

    • Related Report
      2015 Annual Research Report
    • Acknowledgement Compliant
  • [Presentation] Performance evaluation of time-space tiling with tile-level parallelism for iterative stencil computations2018

    • Author(s)
      Takeshi Fukaya and Takeshi Iwashita
    • Organizer
      2018 Conference on Advanced Topics and Auto Tuning in High-Performance Scientific Computing (ATAT in HPC 2018), Tainan, Taiwan
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Performance Evaluation of Tiled 3D FDTD Solver on Recent Multicore Processors2018

    • Author(s)
      Takeshi Iwashita and Takeshi Fukaya
    • Organizer
      SIAM Conference on Parallel Processing for Scientific Computing (SIAM PP18), Tokyo, Japan
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Communication Avoiding Approach for Reduction to Tri-Diagonal, Bi-Diagonal, and Hessenberg Forms2018

    • Author(s)
      T. Imamura, Y. Hirota, S. Yamada, M. Machida
    • Organizer
      SIAM Conference on Parallel Processing for Scientific Computing (SIAM PP18), Tokyo, Japan
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Parareal手法を用いた時間並列計算の有効性の検討,2018

    • Author(s)
      大井祥栄
    • Organizer
      科研費基盤B課題「O(1億)コア環境におけるスケーラブルな数値計算ソフトウェアの理論と応用」ワークショップ, 北海道大学情報基盤センター
    • Related Report
      2017 Annual Research Report
  • [Presentation] メニーコア環境における高性能分割統治法ソルバの研究2018

    • Author(s)
      廣田悠輔,今村俊幸
    • Organizer
      科研費基盤B課題「O(1億)コア環境におけるスケーラブルな数値計算ソフトウェアの理論と応用」ワークショップ, 北海道大学情報基盤センター
    • Related Report
      2017 Annual Research Report
  • [Presentation] Current Status of EigenExa, High-Performance Parallel Dense Eigensolver2018

    • Author(s)
      Toshiyuki Imamura, Yusuke Hirota, and Takeshi Fukaya
    • Organizer
      International Workshop on Eigenvalue Problems: Algorithms; Software and Applications, in Petascale Computing (EPASA 2018)
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Acceleration of the EigenG solver on a consumer-ranged GPU2017

    • Author(s)
      Toshiyuki Imamura
    • Organizer
      2017 Conference on Advanced Topics and Auto Tuning in High-Performance Scientific Computing
    • Place of Presentation
      National Taiwan University (Taipei, Taiwan)
    • Year and Date
      2017-03-10
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Communication Avoiding and Synchronous Reducing Techniques for Dense Parallel Eigenvalue Solver2017

    • Author(s)
      Toshiyuki Imamura, Yusuke Hirota, Susumu Yamada and Masahiko Machida
    • Organizer
      SIAM Conference on Computational Science and Engineering (CSE17)
    • Place of Presentation
      Hilton Atlanta (Atlanta, GA, USA)
    • Year and Date
      2017-03-01
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Implementation Techniques for High Performance BLAS Kernels on Modern GPUs2017

    • Author(s)
      Daichi Mukunoki, Toshiyuki Imamura and Daisuke Takahashi
    • Organizer
      SIAM Conference on Computational Science and Engineering (CSE17)
    • Place of Presentation
      Hilton Atlanta (Atlanta, GA, USA)
    • Year and Date
      2017-02-28
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Performance Evaluation of Time-Space Tiling Strategies for Iterative Stencil Computations on Multi/Many-Core CPU Systems2017

    • Author(s)
      Takeshi Fukaya and Takeshi Iwashita
    • Organizer
      SIAM Conference on Computational Science and Engineering (CSE17)
    • Place of Presentation
      Hilton Atlanta (Atlanta, GA, USA)
    • Year and Date
      2017-02-28
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Development of Banded Eigenvalue Solvers for Shared Memory Parallel Computers2017

    • Author(s)
      Yusuke Hirota and Toshiyuki Imamura
    • Organizer
      The 7th AICS International Symposium
    • Place of Presentation
      Integrated Research Center of Kobe University (Kobe, Japan)
    • Year and Date
      2017-02-23
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 帯行列固有値問題に対する高性能分割統治法アルゴリズム2017

    • Author(s)
      廣田悠輔
    • Organizer
      ワークショップ「行列計算のための数値計算法」
    • Place of Presentation
      名古屋大学 (名古屋市, 愛知県)
    • Year and Date
      2017-01-20
    • Related Report
      2016 Annual Research Report
  • [Presentation] 次世代計算機のための数値計算ライブラリの実装技術2017

    • Author(s)
      椋木大地
    • Organizer
      日本応用数理学会三部会連携「応用数理セミナー」, 東京大学本郷キャンパス
    • Related Report
      2017 Annual Research Report
  • [Presentation] メニーコアCPU向け高性能分割統治法アルゴリズム2017

    • Author(s)
      廣田悠輔,今村俊幸
    • Organizer
      ATμワークショッププログラム,自動チューニング研究会
    • Related Report
      2017 Annual Research Report
  • [Presentation] 時空間タイリングを用いた反復型ステンシル計算とその応用2017

    • Author(s)
      深谷猛, 岩下武史
    • Organizer
      日本機械学会第30回計算力学講演会(CMD2017), 東大阪市
    • Related Report
      2017 Annual Research Report
  • [Presentation] Temporal and spatial tiling technique with tile-level parallelism and its application to 3D FDTD method2017

    • Author(s)
      深谷猛, 岩下武史
    • Organizer
      Sapporo Summer HPC Seminar 2017, 札幌市
    • Related Report
      2017 Annual Research Report
  • [Presentation] Parareal手法を用いた時間並列計算の性能評価2017

    • Author(s)
      大井祥栄
    • Organizer
      第46回数値解析シンポジウム(NAS2017), グリーンパーク想い出の森, 滋賀県高島市
    • Related Report
      2017 Annual Research Report
  • [Presentation] 非同期的な数学的アルゴリズムのソフトウェアの可能性2016

    • Author(s)
      今村俊幸
    • Organizer
      第8回 自動チューニング技術の現状と応用に関するシンポジウム(ATTA2016)
    • Place of Presentation
      東京大学山上会館 (文京区, 東京都)
    • Year and Date
      2016-12-25
    • Related Report
      2016 Annual Research Report
  • [Presentation] 時空間タイリングによる反復型ステンシル計算の性能向上に関する基礎評価2016

    • Author(s)
      深谷 猛, 岩下 武史
    • Organizer
      大学ICT推進協議会 2016年度年次大会
    • Place of Presentation
      国立京都国際会館(京都市, 京都府)
    • Year and Date
      2016-12-16
    • Related Report
      2016 Annual Research Report
  • [Presentation] 時間並列計算手法に関する研究開発動向の調査について,2016

    • Author(s)
      大井祥栄
    • Organizer
      平成28年度自動チューニング研究会マイクロワークショップ
    • Place of Presentation
      登別温泉 (登別市, 北海道)
    • Year and Date
      2016-10-31
    • Related Report
      2016 Annual Research Report
  • [Presentation] メニーコアCPUにおける割統治法ルーチンの性能評価2016

    • Author(s)
      廣田悠輔,今村俊幸
    • Organizer
      平成28年度自動チューニング研究会マイクロワークショップ
    • Place of Presentation
      登別温泉 (登別市, 北海道)
    • Year and Date
      2016-10-31
    • Related Report
      2016 Annual Research Report
  • [Presentation] いま・これからのメニーコア向け線形計算カーネル実装技術2016

    • Author(s)
      椋木大地, 今村俊幸, 高橋大介
    • Organizer
      平成28年度自動チューニング研究会マイクロワークショップ
    • Place of Presentation
      登別温泉 (登別市, 北海道)
    • Year and Date
      2016-10-31
    • Related Report
      2016 Annual Research Report
  • [Presentation] Performance Analysis of the Householder Back-transformation with Asynchronous Collective Communication2016

    • Author(s)
      Toshiyuki Imamura
    • Organizer
      2015 SIAM Conference on Applied Linear Algebra
    • Place of Presentation
      Hyatt Regency Atlanta, US
    • Year and Date
      2016-10-26
    • Related Report
      2015 Annual Research Report
    • Int'l Joint Research
  • [Presentation] PascalアーキテクチャGPUにおける線形計算カーネルの実装技術の検討2016

    • Author(s)
      椋木大地, 今村俊幸, 高橋大介
    • Organizer
      GTC Japan 2016
    • Place of Presentation
      ヒルトン東京お台場 (港区, 東京都)
    • Year and Date
      2016-10-05
    • Related Report
      2016 Annual Research Report
  • [Presentation] マルチコア・メニーコア環境における反復型ステンシル計算と時空間タイリング2016

    • Author(s)
      深谷 猛, 岩下 武史
    • Organizer
      日本応用数理学会2016年度年会
    • Place of Presentation
      北九州国際会議場(北九州市, 福岡県)
    • Year and Date
      2016-09-07
    • Related Report
      2016 Annual Research Report
  • [Presentation] 反復型ステンシル計算のマルチコア・メニーコア向け実装に関する考察2016

    • Author(s)
      深谷 猛, 岩下 武史
    • Organizer
      日本応用数理学会「行列・固有値問題の解法とその応用」研究部会 第21回研究会
    • Place of Presentation
      キッセイ文化ホール(松本市, 長野県)
    • Year and Date
      2016-08-09
    • Related Report
      2016 Annual Research Report
  • [Presentation] Parallel dense eigenvalue solver and SVD solver for post-petascale computing systems2016

    • Author(s)
      Toshiyuki Imamura
    • Organizer
      The 9th International Workshop on Parallel Matrix Algorithms and Applications (PMAA16)
    • Place of Presentation
      The campus of Bordeaux-Victoire (Vordeaux, France)
    • Year and Date
      2016-07-07
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Auto-Tuning for Eigenvalue Solver on the Post Moore's Era2016

    • Author(s)
      Toshiyuki Imamura
    • Organizer
      SIAM Conference on Parallel Processing for Scientific Computing (PP16)
    • Place of Presentation
      Universite Pierre et Marie Curie, Cordelies Campus (Paris, France)
    • Year and Date
      2016-04-14
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Automatic Thread-Block Size Adjustment for Dense Matrix-Vector Multiplication on CUDA2016

    • Author(s)
      Daichi Mukunoki, Toshiyuki Imamura and Daisuke Takahashi
    • Organizer
      Conference on Advanced Topics and Auto Tuning in High-Performance Scientific Computing
    • Place of Presentation
      National Taiwan University
    • Year and Date
      2016-02-19
    • Related Report
      2015 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Present and Future of the EigenExa library2016

    • Author(s)
      Toshiyuki Imamura
    • Organizer
      Conference on Advanced Topics and Auto Tuning in High-Performance Scientific Computing
    • Place of Presentation
      National Taiwan University
    • Year and Date
      2016-02-19
    • Related Report
      2015 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Performance Evaluation of Verified Computation for Linear Systems on Parallel Computers2016

    • Author(s)
      Yusuke Morikura, Daichi Mukunoki, Takeshi Fukaya, Naoya Yamanaka, Shin’ichi Oishi
    • Organizer
      2nd Annual Meeting on Advanced Computing System and Infrastructure (ACSI2016)
    • Place of Presentation
      九州大学医学部百年講堂
    • Year and Date
      2016-01-19
    • Related Report
      2015 Annual Research Report
  • [Presentation] 非同期的な数学的アルゴリズムのソフトウェアの可能性2015

    • Author(s)
      今村俊幸
    • Organizer
      第7回 自動チューニング技術の現状と応用に関するシンポジウム(ATTA2015)
    • Place of Presentation
      東京大学山上会館
    • Year and Date
      2015-12-25
    • Related Report
      2015 Annual Research Report
  • [Presentation] 非同期アルゴリズムの類型とメニーコアプロセッサ向け同期削減技術の開発2015

    • Author(s)
      廣田悠輔,今村俊幸
    • Organizer
      平成27年度自動チューニング研究会マイクロワークショップ
    • Place of Presentation
      KKR甲府、甲府市
    • Year and Date
      2015-10-19
    • Related Report
      2015 Annual Research Report
  • [Presentation] 時間並列計算 -Parareal in time algorithm-2015

    • Author(s)
      大井祥栄
    • Organizer
      平成27年度自動チューニング研究会マイクロワークショップ
    • Place of Presentation
      KKR甲府、甲府市
    • Year and Date
      2015-10-19
    • Related Report
      2015 Annual Research Report
  • [Presentation] O(1億)コア環境におけるスケーラブルな数値計算ソフトウェアの理論と応用2015

    • Author(s)
      今村俊幸
    • Organizer
      平成27年度自動チューニング研究会マイクロワークショップ
    • Place of Presentation
      KKR甲府、甲府市
    • Year and Date
      2015-10-19
    • Related Report
      2015 Annual Research Report
  • [Presentation] GPUにおけるスレッド数自動選択機能を持ったメモリ律速な線形計算カーネル群「MUBLAS」の実装と評価2015

    • Author(s)
      椋木大地,今村俊幸,高橋大介
    • Organizer
      GTC Japan 2015
    • Place of Presentation
      虎ノ門ヒルズフォーラム
    • Year and Date
      2015-09-18
    • Related Report
      2015 Annual Research Report

URL: 

Published: 2015-04-16   Modified: 2019-03-29  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi