Donald Bren School of Information and Computer Sciences

Array variables are extensively used in many behavioral descriptions especially for digital and image processing applications. During synthesis, these array variables are implemented with memory modules. In this report, we show that simple one-to-one mapping between the array variables and the memory modules lead to inefficient designs. We propose a new algorithm (MeSA} for efficient allocation and mapping of array variables onto memory modules. MeSA computes, (a) the number of memory modules required, (b) the size of each module (c) the number of ports on each module and (d) and the grouping of array variables that map onto each memory module. It also considers the effects of address translations that are required when two or more array variables are stored in one memory module. While, most previous research efforts have concentrated on optimizing the scalar variables, the primary focus in this report is deriving efficient storage mechanisms for array variables. We show the efficiency of our technique on some standard benchmarks.