Automatic data migration for reducing energy consumption in multi-bank memory systems

Abstract

An architectural solution to reducing memory energy consumption is to adopt a multi-bank memory system instead of a monolithic (single-bank) memory system. Some recent multi-bank memory architectures help reduce memory energy by allowing an unused bank to be placed into a low-power operating mode. This paper describes an automatic data migration strategy which dynamically places the arrays with temporal affinity into the same set of banks. This strategy increases the number of banks which can be put into low-power modes and allows the use of more aggressive energy-saving modes. Experiments using several array-dominated applications show the usefulness of data migration and indicate that large energy savings can be achieved with low overhead.