TY - GEN
T1 - An emulated digital wave computer core implementation
AU - Yeniçeri, Ramazan
AU - Yalçin, Müştak E.
PY - 2009
Y1 - 2009
N2 - In this paper, a novel cellular nonlinear network emulator core which executes wave computing within an FPGA-based platform is proposed. This wave computer core has 4 x 4 parallel processing units and emulates 16, 384 nodes which are arranged in 128x128 normal grid form. The wave computer core can be programmed to generate active waves such as autowaves, travelling waves and spiral waves, and also allow to have an inhomogeneous network using fixed-state options. By virtue of its on chip memory and floating point number arithmetics ability, high emulation speed and high precision on variable values are achieved. The FPGA wave computer has not only an online monitor output to observe active wave evaluation, also a communication interface which allows to program the network with host computer. The introduced system was experimented in a path planning application and can be used to develop more active wave computing based algorithms for image processing and path planning.
AB - In this paper, a novel cellular nonlinear network emulator core which executes wave computing within an FPGA-based platform is proposed. This wave computer core has 4 x 4 parallel processing units and emulates 16, 384 nodes which are arranged in 128x128 normal grid form. The wave computer core can be programmed to generate active waves such as autowaves, travelling waves and spiral waves, and also allow to have an inhomogeneous network using fixed-state options. By virtue of its on chip memory and floating point number arithmetics ability, high emulation speed and high precision on variable values are achieved. The FPGA wave computer has not only an online monitor output to observe active wave evaluation, also a communication interface which allows to program the network with host computer. The introduced system was experimented in a path planning application and can be used to develop more active wave computing based algorithms for image processing and path planning.
KW - Cellular Neural/Nonlinear Networks (CNNs)
KW - Core design
KW - Field-Programmable Gate Array (FPGA)
KW - Wave computer
UR - http://www.scopus.com/inward/record.url?scp=71249085206&partnerID=8YFLogxK
U2 - 10.1109/ECCTD.2009.5275112
DO - 10.1109/ECCTD.2009.5275112
M3 - Conference contribution
AN - SCOPUS:71249085206
SN - 9781424438969
T3 - ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program
SP - 831
EP - 834
BT - ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program
T2 - ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program
Y2 - 23 August 2009 through 27 August 2009
ER -