A technique to determine power-efficient, high-performance superscalar processors

Processor performance advances are increasingly inhibited by limitations in thermal power dissipation. Part of the problem is the lack of architectural power estimates before implementation. Although high-performance designs exist that dissipate low power, the method for finding these designs has been through trial-and-error. The paper presents systematic techniques to find low-power, high-performance superscalar processors tailored to specific user benchmarks. The model of power is novel because it separates power into architectural and technology components. The architectural component is found via trace-driven simulation, which also produces performance estimates. An example technology model is presented that estimates the technology component, along with critical delay time and real estate usage. This model is based on case studies of actual designs. It is used to solve an important problem: increasing the duplication in superscalar execution units without excessive power consumption. Results are presented from runs using simulated annealing to maximize processor performance subject to power and area constraints. The major contributions of the paper are the separation of architectural and technology components of dynamic power, the use of trace-driven simulation for architectural power measurement, and the use of a near-optimal search to tailor a processor design to a benchmark