• DocumentCode
    1832386
  • Title

    GRAPE-4: a teraFLOPS massively parallel special-purpose computer system for astrophysical N-body simulations

  • Author

    Taiji, Makoto ; Makino, Junichiro ; Ebisuzaki, Toshikazu ; Sugimoto, Daiichiro

  • Author_Institution
    Dept. of Earth Sci. & Astron., Tokyo Univ., Japan
  • fYear
    1994
  • fDate
    26-29 Apr 1994
  • Firstpage
    280
  • Lastpage
    287
  • Abstract
    We are developing a massively parallel special-purpose computer system for astrophysical N-body simulations, GRAPE-4 (Gravity-Pipe 4). The GRAPE-4 system is designed to simulate dynamics of classical particles which interact each other gravitationally by using predictor-corrector methods. We have developed two application-specific LSIs, the HARP (Hermite Accelerator Pipe) chip and the PROMETHEUS chip for the GRAPE-4 system. The HARP chip calculates gravitational forces and its performance exceeds 600 megaFLOPS. The PROMETHEUS chip calculates predictors for the time-integration. Using multi-chip module technology, we can integrate 1920 HARP chips into a single system. The GRAPE-4 system consists of 4 clusters, which are connected to a single host workstation. The peak speed of GRAPE-4 will exceed 1 teraFLOPS even in the worst case, and will reach around 1.8 tetraFLOPS in the typical case
  • Keywords
    N-body problems; application specific integrated circuits; astronomy computing; celestial mechanics; discrete event simulation; gravitational waves; parallel machines; performance evaluation; predictor-corrector methods; special purpose computers; 1 TFLOPS; 1.8 TFLOPS; 600 MFLOPS; GRAPE-4; Gravity-Pipe 4; HARP; Hermite Accelerator Pipe; PROMETHEUS chip; application-specific LSIs; astrophysical N-body simulations; classical particles; gravitation; massively parallel special-purpose computer system; predictor-corrector methods; time-integration; Arithmetic; Computational modeling; Computer simulation; Concurrent computing; Microprocessors; Orbital calculations; Pipelines; Supercomputers; Very large scale integration; Workstations;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Parallel Processing Symposium, 1994. Proceedings., Eighth International
  • Conference_Location
    Cancun
  • Print_ISBN
    0-8186-5602-6
  • Type

    conf

  • DOI
    10.1109/IPPS.1994.288288
  • Filename
    288288