Title :
Neural networks simulation with array processors
Author :
Pazienti, Francesco
Author_Institution :
Alcatel Face Res. Centre, Pomezia, Italy
Abstract :
A strategy is presented for implementing neural models, based on an array of interconnected processing elements. A proprietary VLSI parallel processing chip (the array chip ACIIM) is briefly described. It incorporates 16 16-bit processors, 8 kBytes of local memory, external logic, and interface hardware in a single package. Using this chip, a 128-processor computer has been built, the array processor APx, which fits on two circuit boards and plugs into the backplane of an IBM PC AT microcomputer. By providing peak rates of up to 1600 32-bit MIPS and 160 MFLOPS, the APx accelerator achieves as much as a thousandfold improvement over PC/workstations for many computationally intensive tasks
Keywords :
VLSI; digital simulation; logic arrays; microcomputer applications; neural nets; parallel processing; 16 bit; 160 MFLOPS; 1600 MIPS; 32 bit; 8 kByte; IBM PC AT microcomputer; VLSI parallel processing chip; array chip ACIIM; array processor APx; array processors; computationally intensive tasks; external logic; neural network simulation; Backplanes; Hardware; Integrated circuit interconnections; Logic; Neural networks; Packaging; Parallel processing; Plugs; Printed circuits; Very large scale integration;
Conference_Titel :
CompEuro '91. Advanced Computer Technology, Reliable Systems and Applications. 5th Annual European Computer Conference. Proceedings.
Conference_Location :
Bologna
Print_ISBN :
0-8186-2141-9
DOI :
10.1109/CMPEUR.1991.257445