High-Speed Performance, Power and Thermal Co-simulation For SoC Design

Abstract

This dissertation presents a multi-faceted effort at developing standard System Design Language based tools that allow designers to the model power and thermal behavior of SoCs, including heterogeneous SoCs that include non-digital components. The research contributions made in this dissertation include:

• SystemC-based power/performance co-simulation for the Intel XScale microprocessor. We performed detailed characterization of the power dissipation patterns of a variety of system components and used these results to build detailed power models, including a highly accurate, validated instruction-level power model of the XScale processor. We also proposed a scalable, efficient and validated methodology for incorporating fast, accurate power modeling capabilities into system description languages such as SystemC. This was validated against physical measurements of hardware power dissipation.

• Modeling the behavior of non-digital SoC components within standard System Design Languages. We presented an approach for modeling the functionality, performance, power, and thermal behavior of a complex class of non-digital components — MEMS microhotplate-based gas sensors — within a SystemC design framework. The components modeled include both digital components (such as microprocessors, busses and memory) and MEMS devices comprising a gas sensor SoC. The first SystemC models of a MEMS-based SoC and the first SystemC models of MEMS thermal behavior were described. Techniques for significantly improving simulation speed were proposed, and their impact quantified.

• Vertically Integrated Execution-Driven Power, Performance and Thermal Co-Simulation For SoCs. We adapted the above techniques and used numerical methods to model the system of differential equations that governs on-chip thermal diffusion. This allows a single high-speed simulation to span performance, power and thermal modeling of a design. It also allows feedback behaviors, such as the impact of temperature on power dissipation or performance, to be modeled seamlessly. We validated the thermal equation-solving engine on test layouts against detailed low-level tools, and illustrated the power of such a strategy by demonstrating a series of studies that designers can perform using such tools. We also assessed how simulation and accuracy are impacted by spatial and temporal resolution used for thermal modeling.