TY - GEN
T1 - System on Chip Testbed for Deep Neuromorphic Neural Networks
AU - Rodriguez, Nicolas Daniel
AU - Villemur, Martin
AU - Klepatsch, Daniel
AU - Gigena Ivanovich, Diego
AU - Julian, Pedro
PY - 2023/7/21
Y1 - 2023/7/21
N2 - This paper describes a first prototype of a testbed System on chip (SoC) to design and evaluate different Neuromorphic Deep Neural Networks (NN) cores. The $1.25mm \times 1.25mm$ SoC was fabricated in a 65nm CMOS technology and implements a system composed of an ARM based microprocessor, two memory banks of 32KB, a QSPI serial interface and two NN accelerators. The first one is a novel neuromorphic accelerator consisting of a 5x5 kernel Symmetrical Simplicial (SymSimp) core with a depthwise separable structure, which allows to efficiently implement multi-channel convolutional layers by breaking 3D kernels into 2D kernels. The second is a 3x3 conventional MAC engine to implement the fully connected layers. Experimental results show an energy efficiency of 0.49pJ/OP, which is competitive when compared to similar technology ICs, and extrapolated to the MobileNetworkV2 ImageNet represents a factor of 2 improvement with respect to NVIDIA Jetson Nano.
AB - This paper describes a first prototype of a testbed System on chip (SoC) to design and evaluate different Neuromorphic Deep Neural Networks (NN) cores. The $1.25mm \times 1.25mm$ SoC was fabricated in a 65nm CMOS technology and implements a system composed of an ARM based microprocessor, two memory banks of 32KB, a QSPI serial interface and two NN accelerators. The first one is a novel neuromorphic accelerator consisting of a 5x5 kernel Symmetrical Simplicial (SymSimp) core with a depthwise separable structure, which allows to efficiently implement multi-channel convolutional layers by breaking 3D kernels into 2D kernels. The second is a 3x3 conventional MAC engine to implement the fully connected layers. Experimental results show an energy efficiency of 0.49pJ/OP, which is competitive when compared to similar technology ICs, and extrapolated to the MobileNetworkV2 ImageNet represents a factor of 2 improvement with respect to NVIDIA Jetson Nano.
KW - VLSI
KW - Neuromorphic Computing
KW - Neural Network Accelerators
KW - CMOS
U2 - 10.1109/ISCAS46773.2023.10182079
DO - 10.1109/ISCAS46773.2023.10182079
M3 - Conference Paper
BT - 2023 IEEE International Symposium on Circuits and Systems (ISCAS)
ER -