Title :
Achieving super computer performance with a DSP array processor
Author :
Gunzinger, A. ; Muller, U.A. ; Scott, W. ; Bäumle, B. ; Kohler, P. ; Mühll, H. R vonder ; Müller-Plathe, F. ; van Gunsteren, W.F. ; Guggenbühl, W.
Author_Institution :
Swiss Federal Inst. of Technol., Zurich, Switzerland
Abstract :
The authors discuss the MUSIC (multi-signal-processor system with intelligent communication) system, a parallel distributed memory architecture based on digital signal processors (DSPs). A system with 60 processor elements is operational. It has a peak performance of 3.8 GFlops and an electrical power consumption of less than 800 W (including forced air cooling), and it fits into a 19" rack. Two applications (the backpropagation algorithm for neural network learning and molecular dynamics simulations) run about six times faster than on a CRAY Y-MP and two times faster than on a NEC SX-3. A sustained performance of more than 1 GFlops is reached
Keywords :
backpropagation; digital signal processing chips; distributed memory systems; molecular dynamics method; neural nets; parallel architectures; 3.8 GFLOPS; DSP array processor; backpropagation algorithm; digital signal processors; intelligent communication; molecular dynamics simulations; multi-signal-processor system; neural network learning; parallel distributed memory architecture; supercomputer performance; Backpropagation algorithms; Computer performance; Cooling; Digital signal processing; Digital signal processors; Energy consumption; Intelligent systems; Memory architecture; Multiple signal classification; Neural networks;
Conference_Titel :
Supercomputing '92., Proceedings
Conference_Location :
Minneapolis, MN
Print_ISBN :
0-8186-2630-5
DOI :
10.1109/SUPERC.1992.236650
