Adaptive Methods to Minimize Decompression Overhead for Compressed On-Chip Caches

Abstract

Decompression time is the largest overhead in online compression techniques, and may offset any benefit obtained by compression. This article presents the upper bounds of decompression overhead required to achieve performance improvement in compressed memory systems and proposes several effective techniques for reducing or hiding decompression overhead. These techniques include selective compression, the choice of X-RL algorithm, early restarting, overlapped decompression, and use of a decompression buffer. Moreover. the conceptual architecture of a compressed memory system using the proposed techniques is suggested. These techniques are evaluated via simulation. The simulation results show that the proposed techniques can sufficiently reduce the decompression overhead to attain performance improvement against conventional memory systems.