Design of an one-cycle decompression hardware for performance increase in embedded systems

Abstract

Code compression is known as an effective technique to reduce instruction memory size on an embedded system. However, code compression can also be very effective in increasing processor-to-memory bandwidth and hence provide increased system performance. In this paper we describe our design and design methodology of the first running prototype of a one-cycle code decompression unit that decompresses compressed instructions on-the-fly. We describe in detail the architecture that enables decompression of multiple instructions in one cycle and we present the design methodologies and tools used. The stand-alone decompression unit does not require any modifications on the processor core. We observed up to 63% performance increase with 25% in average over a wide variety of applications running on the hardware prototype under various system configurations.