Benchmarking the Epiphany Processor as a Reference Neuromorphic Architecture

This short article explains why the Epiphany architecture is a proper refer-
ence for digital large-scale neuromorphic design. We compare the Epiphany
architecture with several modern digital neuromorphic processors. We show
the result of mapping the binary LeNet-5 neural network into few modern
neuromorphic architectures and demonstrate the efficient use of memory in
Epiphany. Finally, we show the results of our benchmarking experiments
with Epiphany and propose a few suggestions to improve the architecture
for neuromorphic applications. Epiphany can update a neuron on average in
120ns which is enough for many real-time neuromorphic applications.