DocumentCode :
278893
Title :
GRAPE-3: highly parallelized special-purpose computer for gravitational many-body simulations
Author :
Okumura, S.K. ; Makino, J. ; Ebisuzaki, T. ; Ito, T. ; Fukushige, T. ; Sugimoto, D. ; Hashimoto, E. ; Tomida, K. ; Miyakawa, N.
Author_Institution :
Dept. of Earth Sci. & Astron., Tokyo Univ., Japan
Volume :
i
fYear :
1992
fDate :
7-10 Jan 1992
Firstpage :
151
Abstract :
The authors have developed a highly parallelized special-purpose computer GRAPE (GRAvity PipE)-3 for gravitational many-body simulations. It accelerates gravitational force calculations which are the most expensive part of the many-body simulations. The peak computing speed is equivalent to about 15 GFLOPS. The GRAPE-3 system consists of two identical boards connected to a host computer through a VME bus. Each board has 24 custom LSI GRAPE chips which calculate gravitational forces in parallel. The gravitational force calculation is easily parallelized because the forces on different particles con be calculated independently. Using the pipelined architecture, one GRAPE chip calculates one gravitational force between a pair of particles at every clock cycle. The number of floating point operations needed to calculate one force is about 90. Therefore, one GRAPE chip running at 10 MHz clock-rate has a computing speed equivalent to 0.3 GFLOPS. The GRAPE-3 with 48 GRAPE chips achieves about 15 GFLOPS. One GRAPE chip has 110000 transistors in an 8 mm×8 mm area and its power consumption is 1.2 W at 10 MHz. Its package is ceramic PGA with 181 pins. One GRAPE-3 board is a 9U Eurocard, on which 159 chips are wire-wrapped
Keywords :
N-body problems; astronomy computing; astrophysical fluid dynamics; digital simulation; galaxies; large scale integration; packaging; parallel architectures; parallel machines; pipeline processing; special purpose computers; stellar dynamics; 1.2 W; 10 MHz; 15 FLOPS; 8 mm; 9U Eurocard; GRAPE-3; Gravity Pipe; LSI chips; ceramic pin grid array; gravitational force calculations; gravitational many-body simulations; highly parallelized special-purpose computer; pipelined architecture; wire wrapping; Acceleration; Clocks; Computational modeling; Computer architecture; Computer simulation; Concurrent computing; Energy consumption; Gravity; Large scale integration; Pipelines;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
System Sciences, 1992. Proceedings of the Twenty-Fifth Hawaii International Conference on
Conference_Location :
Kauai, HI
Print_ISBN :
0-8186-2420-5
Type :
conf
DOI :
10.1109/HICSS.1992.183157
Filename :
183157
Link To Document :
بازگشت