Efficient parallel implementation of multilayer backpropagation networks on SpiNNaker

This paper presents an efficient implementation and performance analysis of mapping multilayer perceptron networks with the backpropagation learning rule on SpiNNaker - a massively parallel architecture dedicated for neural network simulation. A new algorithm called pipelined checker-boarding partitioning scheme is proposed for efficient mapping. The new mapping algorithm relies on a checker-board partitioning scheme, but the key advantage comes from introducing a pipelined mode. The six-stage pipelined mode captures the parallelism within each partition of the weight matrix, allowing the overlapping of communication and computation. Not only does the proposed mapping localize communication, but it can also hide a part of or even all the communication for high efficiency.