DocumentCode :
2680083
Title :
IP-based methodology for analog design flow: Application on neuromorphic engineering
Author :
Levi, T. ; Lewis, N. ; Tomas, J. ; Fouillat, P.
Author_Institution :
IMS Lab. (CNRS/ENSEIRB), Univ. Bordeaux 1, Talence
fYear :
2008
fDate :
22-25 June 2008
Firstpage :
343
Lastpage :
346
Abstract :
Analog and Mixed Signal design flow has to be improved. In a specific application, neuromorphic engineering, we propose a definition of the analog IP (Intellectual Property) content and the structure of an IP-based library. The case study consists in the neuron-level integration of a complete system that emulates spiking neural networks. A reuse methodology based on the IP concept is developed and we show how it can be used to accelerate the design cycle of the next ASIC generation.
Keywords :
analogue integrated circuits; industrial property; mixed analogue-digital integrated circuits; IP-based methodology; analog IP content; analog design flow; intellectual property; neuromorphic engineering; Acceleration; Analog circuits; Application specific integrated circuits; Biological system modeling; Design methodology; Intellectual property; Neural networks; Neuromorphic engineering; Neurons; Signal design;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems and TAISA Conference, 2008. NEWCAS-TAISA 2008. 2008 Joint 6th International IEEE Northeast Workshop on
Conference_Location :
Montreal, QC
Print_ISBN :
978-1-4244-2331-6
Electronic_ISBN :
978-1-4244-2332-3
Type :
conf
DOI :
10.1109/NEWCAS.2008.4606391
Filename :
4606391
Link To Document :
بازگشت