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

A research and development of an advanced CFD algorithm for next generation multi FPGA system.

Research Project

Project/Area Number 19K20282
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 60090:High performance computing-related
Research InstitutionMeiji University (2021)
Institute of Physical and Chemical Research (2019-2020)

Principal Investigator

Miyajima Takaaki  明治大学, 理工学部, 専任講師 (90770850)

Project Period (FY) 2019-04-01 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2021: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2020: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2019: ¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
Keywordsコンフィギュラブル・コンピューティング / 数値流体力学 / 高性能計算 / MPS法 / 粒子法 / temporal parallelism / FPGA / temporal blocking / GPGPU
Outline of Research at the Start

本研究の目的は、近年注目されている粒子系ソルバーMoving ParticleSemi-implicit (MPS)法を題材に、時空間ブロッキング (TB:TemporalBlocking) と呼ばれる最適化アルゴリズムを適用した新手法、TB-MPS法の提案を行い、TBの粒子系ソルバーへの適用可能性を理解することである。また、TB-MPS法をField Programmable Gate Array (FPGA) システムに適した形に変更した新手法、STREAM-TB-MPS法を提案し、さらにそれをマルチFPGAシステムへ拡張することである。

Outline of Final Research Achievements

A proposal to make a search for neighbour particles in MPS method into a form of data flow was published at an international conference. The proposal was also implemented on FPGA and evaluated. It is shown that the processing time on Arria10 FPGA slightly out-perform it on multi-core CPU. We found that there is room for improvement in a proposed model to estimate circuit area. Regarding multiple FPGA, a bridged data transfer with CPU was proposed and evaluated. An evaluation shows that although the bridged data transfer is more flexible than FPGA dedicated data transfer, bandwidth is lower than FPGA-dedicated one. We are now considering using the latter one to achieve higher performance.

Academic Significance and Societal Importance of the Research Achievements

非圧縮性流体の解析に用いられる粒子法の一種である、MPS法について、初めてデータフロー型のアルゴリズムの提案を行った。提案手法は広帯域のメモリを必要としない方法で、GPUなどの広帯域メモリを性能向上の要因とするデバイスの性能向上が頭打ちになった場合にも利用可能な手法である。他の粒子法に応用可能かどうかの要因解析も終わっており、Incompressive SPH法などへの応用も期待できる。

Report

(4 results)
  • 2021 Annual Research Report   Final Research Report ( PDF )
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (10 results)

All 2022 2021 2020

All Journal Article (3 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 3 results,  Open Access: 2 results) Presentation (7 results) (of which Int'l Joint Research: 3 results,  Invited: 2 results)

  • [Journal Article] FPGA-Dedicated Network vs. Server Network for Pipelined Computing with Multiple FPGAs2022

    • Author(s)
      Tomohiro Ueno, Takaaki Miyajima and Kentaro Sano
    • Journal Title

      International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies ( HEART Symposium )

      Volume: -

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] A memory bandwidth improvement with memory space partitioning for single-precision floating-point FFT on Stratix 10 FPGA2021

    • Author(s)
      Miyajima Takaaki、Sano Kentaro
    • Journal Title

      2021 IEEE International Conference on Cluster Computing (CLUSTER)

      Volume: -

    • DOI

      10.1109/cluster48925.2021.00117

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Exploiting temporal parallelism in particle-based incompressive fluid simulation on FPGA2020

    • Author(s)
      Orsztynowicz Manfred、Amano Hideharu、Kubota Kenichi、Miyajima Takaaki
    • Journal Title

      2020 Eighth International Symposium on Computing and Networking (CANDAR)

      Volume: 1 Pages: 195-201

    • DOI

      10.1109/candar51075.2020.00034

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Presentation] 高性能計算のための高速フーリエ変換のFPGA実装と評価2021

    • Author(s)
      宮島敬明、上野知洋、佐野健太郎
    • Organizer
      電子情報通信学会 リコンフィギャラブルシステム研究会
    • Related Report
      2020 Research-status Report
  • [Presentation] Research activity on a high-performance off-loading engine with multiple FPGAs2020

    • Author(s)
      Takaaki Miyajima, Tomohiro Ueno, Jens Huthmann, Kentaro Sano and Atsushi Koshiba
    • Organizer
      The 3rd R-CCS International Symposium
    • Related Report
      2020 Research-status Report
  • [Presentation] High-Performance Off-loading Engine with multiple FPGAs through Custom Computing2020

    • Author(s)
      Takaaki Miyajima, Tomohiro Ueno, Atsushi Koshiba, Jens Huthmann, Kentaro Sano
    • Organizer
      The 2nd R-CCS International Symposium
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] High-Performance Custom Computing with FPGA Cluster as an Off-loading Engine2020

    • Author(s)
      Takaaki Miyajima, Tomohiro Ueno, Atsushi Koshiba, Jens Huthmann, Kentaro Sano, and Mitsuhisa Sato
    • Organizer
      International Conference for High Performance Computing, Networking, Storage and Analysis (SC ’19) Research Poster
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] A software bridged data transfer on a FPGA cluster by using pipelining and InfiniBand verbs2020

    • Author(s)
      Takaaki Miyajima, Tomoya Hirao, Naoya Miyamoto, Jeongdo Son and Kentaro Sano
    • Organizer
      10th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies (HEART 2019)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] An optimization of search for neighbour-particle in MPS method for Xeon, Xeon Phi and GPU by using directives2020

    • Author(s)
      Takaaki Miyajima
    • Organizer
      OpenACC Annual Meeting 2019
    • Related Report
      2019 Research-status Report
    • Invited
  • [Presentation] MPS法への連結リストの適用と各種並列計算機を用いた 近傍粒子探索の高速化2020

    • Author(s)
      宮島敬明
    • Organizer
      GPU Computing Workshop for Advanced Manufacturing 2019
    • Related Report
      2019 Research-status Report
    • Invited

URL: 

Published: 2019-04-18   Modified: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi