ACE

a digital floating point CNN emulator engine

Bela Feher, P. Szolgay, T. Roska, Andras G. Radvanyi, T. Szirányi, Marton Csapodi, Karoly Laszlo, L. Nemes, Istvan Szatmari, Geza Toth, Peter L. Venetianer

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

The architecture of ACE, a multiprocessor analogic 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) 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 approx. 2.8 μsec/cell/iteration/DSP for 3*3 linear templates.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications
PublisherIEEE
Pages273-278
Number of pages6
Publication statusPublished - 1996
EventProceedings of the 1996 4th IEEE International Workshop on Cellular Neural Networks, and Their Applications, CNNA-96 - Seville, Spain
Duration: Jun 24 1996Jun 26 1996

Other

OtherProceedings of the 1996 4th IEEE International Workshop on Cellular Neural Networks, and Their Applications, CNNA-96
CitySeville, Spain
Period6/24/966/26/96

Fingerprint

Engines
Random access storage
Multilayers
Simulators

ASJC Scopus subject areas

  • Software

Cite this

Feher, B., Szolgay, P., Roska, T., Radvanyi, A. G., Szirányi, T., Csapodi, M., ... Venetianer, P. L. (1996). ACE: a digital floating point CNN emulator engine. In Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications (pp. 273-278). IEEE.

ACE : a digital floating point CNN emulator engine. / Feher, Bela; Szolgay, P.; Roska, T.; Radvanyi, Andras G.; Szirányi, T.; Csapodi, Marton; Laszlo, Karoly; Nemes, L.; Szatmari, Istvan; Toth, Geza; Venetianer, Peter L.

Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE, 1996. p. 273-278.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Feher, B, Szolgay, P, Roska, T, Radvanyi, AG, Szirányi, T, Csapodi, M, Laszlo, K, Nemes, L, Szatmari, I, Toth, G & Venetianer, PL 1996, ACE: a digital floating point CNN emulator engine. in Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE, pp. 273-278, Proceedings of the 1996 4th IEEE International Workshop on Cellular Neural Networks, and Their Applications, CNNA-96, Seville, Spain, 6/24/96.
Feher B, Szolgay P, Roska T, Radvanyi AG, Szirányi T, Csapodi M et al. ACE: a digital floating point CNN emulator engine. In Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE. 1996. p. 273-278
Feher, Bela ; Szolgay, P. ; Roska, T. ; Radvanyi, Andras G. ; Szirányi, T. ; Csapodi, Marton ; Laszlo, Karoly ; Nemes, L. ; Szatmari, Istvan ; Toth, Geza ; Venetianer, Peter L. / ACE : a digital floating point CNN emulator engine. Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE, 1996. pp. 273-278
@inproceedings{87b8ea9b18394d56901088529fcff42e,
title = "ACE: a digital floating point CNN emulator engine",
abstract = "The architecture of ACE, a multiprocessor analogic 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) 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 approx. 2.8 μsec/cell/iteration/DSP for 3*3 linear templates.",
author = "Bela Feher and P. Szolgay and T. Roska and Radvanyi, {Andras G.} and T. Szir{\'a}nyi and Marton Csapodi and Karoly Laszlo and L. Nemes and Istvan Szatmari and Geza Toth and Venetianer, {Peter L.}",
year = "1996",
language = "English",
pages = "273--278",
booktitle = "Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications",
publisher = "IEEE",

}

TY - GEN

T1 - ACE

T2 - a digital floating point CNN emulator engine

AU - Feher, Bela

AU - Szolgay, P.

AU - Roska, T.

AU - Radvanyi, Andras G.

AU - Szirányi, T.

AU - Csapodi, Marton

AU - Laszlo, Karoly

AU - Nemes, L.

AU - Szatmari, Istvan

AU - Toth, Geza

AU - Venetianer, Peter L.

PY - 1996

Y1 - 1996

N2 - The architecture of ACE, a multiprocessor analogic 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) 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 approx. 2.8 μsec/cell/iteration/DSP for 3*3 linear templates.

AB - The architecture of ACE, a multiprocessor analogic 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) 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 approx. 2.8 μsec/cell/iteration/DSP for 3*3 linear templates.

UR - http://www.scopus.com/inward/record.url?scp=0030418223&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030418223&partnerID=8YFLogxK

M3 - Conference contribution

SP - 273

EP - 278

BT - Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications

PB - IEEE

ER -