Mixed-clock issue queue design for energy aware, high-performance cores

Abstract

Globally-asynchronous, locally-synchronous (GALS) design style has started to gain interest recently as a possible solution to the increased design complexity, power and thermal costs, as well as an enabler for allowing fine grain speed and voltage management. Due to its inherent complexity, a possible driver application for such a design style is the case of superscalar, out-of-order processors. We propose a novel mixed-clock issue queue design, and compares and contrasts this new implementation with existing synchronous or mixed-clock versions of issue queues, used in standalone mode or in conjunction with mixed-clock FIFO (first-in, first-out) buffers for inter-domain synchronization. Both transistor level, SPICE simulation, as well as cycle-accurate, microarchitectural analysis, show that cores using mixed-clock issue queues are able to provide better energy-performance operating points when compared to their synchronous or asynchronous FIFO-based counterparts.