Abstract: Neuromorphic computing with crossbar arrays has emerged as a promising alternative to improve computing efficiency for machine learning. Previous work has focused on implementing crossbar arrays to perform basic mathematical operations. However, in this paper, we explore the impact of mapping the layers of an artificial neural network onto physical cross-bar arrays arranged in tiles across a chip. We have developed a simplified mapping algorithm to determine the number of physical tiles, with fixed optimal array dimensions, and to estimate the minimum area occupied by these tiles for a given design objective. This simplified algorithm is compared with conventional binary linear optimization, which solves the equivalent bin-packing problem. We have found that the optimum solution is not necessarily related to the minimum number of tiles; rather, it is shown to be an interaction between tile array capacity and the scaling properties of its peripheral circuits. Additionally, we have discovered that square arrays are not always the best choice for optimal mapping, and that performance optimization comes at the cost of total tile area. 1 Introduction The dream of emulating the operations of the brain is the driving force behind neuromorphic computing [1] [2] [3]. Coming even close to the capabilities of the brain, however, has been elusive. The use of artificial neural networks (ANN) for machine learning is a rapidly advancing step in this direction [4] [5]. ANNs allow domain-specific learning without knowledge of the intricate details of a specific domain. Instead, they connect numerical representations of domainspecific inputs with domain-specific outputs [6] [7] [8]. A neural network, in general, has several layers represented by a weight matrix.