ACE: a digital floating point CNN emulator engine

Author

Fehér, Béla ; Szolgay, Peter ; Roska, Tamás ; Radványi, András G. ; Szirányi, Tamás ; Csapodi, Márton ; Laszlo, Károly ; Nemes, Laszlo ; Szatmári, István ; Tóth, Géza ; Venetianer, Péter L.

Author_Institution

Dept. of Meas. & Instrum. Eng., Tech. Univ. Budapest, Hungary

fYear

1996

Firstpage

273

Lastpage

278

Abstract

The architecture of ACE, a multiprocessor analogic cellular neural network (CNN) emulator engine consisting of 2 to 16 TMS320C40 floating point DSPs is introduced. The engine containing up to 512 Mbyte RAM (enough to store a 512×512×512 sized CNN cube) which can be controlled through its SCSI port. It can either accelerate the multilayer CNN simulator CNNM or be accessed directly from the high level, C-based analogic CNN language ACL to achieve the simulation speed of ~2.8 μsec/cell/iteration/DSP for 3×3 linear templates

Keywords

cellular neural nets; digital signal processing chips; floating point arithmetic; neural net architecture; virtual machines; ACE architecture; ACL cellular neural network language; SCSI port; TMS320C40 DSP chips; cellular neural network emulator; digital floating point; linear templates; multiprocessor emulator engine; simulator; Cellular neural networks; Computational modeling; Computer architecture; Digital signal processing; Engines; Hardware; Logic arrays; Programmable logic arrays; Signal processing algorithms; Very large scale integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Cellular Neural Networks and their Applications, 1996. CNNA-96. Proceedings., 1996 Fourth IEEE International Workshop on

Conference_Location

Seville

Print_ISBN

0-7803-3261-X

Type

conf

DOI

10.1109/CNNA.1996.566574

Filename

566574