T. Ebisuzaki, T. Ito, J. Makino, S. Okumura, D. Sugimoto
{"title":"GRAPE-2A: a special purpose computer for simulations of many-body systems with arbitrary central force","authors":"T. Ebisuzaki, T. Ito, J. Makino, S. Okumura, D. Sugimoto","doi":"10.1109/HICSS.1992.183159","DOIUrl":null,"url":null,"abstract":"The authors are developing GRAPE-2A which is a back-end processor to accelerate the simulations of many-body systems such as stellar clusters and systems of molecules. GRAPE-2A calculates forces exerted on one particle from all other particles. The host computer, connected to GRAPE-2A through a VME bus, performs other calculations such as time integration. In the simulation of many-body systems, almost all computation time is consumed in the calculation of forces between particles, i.e. gravitational, Coulomb, and van der Waals forces. GRAPE-2A can calculate the forces with an arbitrary functional form using a hardwired pipeline. The host computer can set the functional form of the force by sending the interpolation data to GRAPE-2A. The computational speed of GRAPE-2A is 300 MFLOPS. Aiming at a speed of 1 TFLOPS, the authors are planning to develop a GRAPE system in which many GRAPE pipelines work in parallel.<<ETX>>","PeriodicalId":103288,"journal":{"name":"Proceedings of the Twenty-Fifth Hawaii International Conference on System Sciences","volume":"112 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1992-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Twenty-Fifth Hawaii International Conference on System Sciences","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/HICSS.1992.183159","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4
Abstract
The authors are developing GRAPE-2A which is a back-end processor to accelerate the simulations of many-body systems such as stellar clusters and systems of molecules. GRAPE-2A calculates forces exerted on one particle from all other particles. The host computer, connected to GRAPE-2A through a VME bus, performs other calculations such as time integration. In the simulation of many-body systems, almost all computation time is consumed in the calculation of forces between particles, i.e. gravitational, Coulomb, and van der Waals forces. GRAPE-2A can calculate the forces with an arbitrary functional form using a hardwired pipeline. The host computer can set the functional form of the force by sending the interpolation data to GRAPE-2A. The computational speed of GRAPE-2A is 300 MFLOPS. Aiming at a speed of 1 TFLOPS, the authors are planning to develop a GRAPE system in which many GRAPE pipelines work in parallel.<>