Exploiting Resonant Behavior to Reduce Inductive Noise

TLDR: This proposal changes the frequency of current variations away from the resonance band to a non-resonant frequency to be absorbed by the power supply, because inductive noise is a resonance problem.

Abstract: Inductive noise in high-performance microprocessors is a reliabilityissue caused by variations in processor current (di/dt)which are converted to supply-voltage glitches by impedances inthe power-supply network. Inductive noise has been addressed byusing decoupling capacitors to maintain low impedance in thepower supply over a wide range of frequencies. However, evenwell-designed power supplies exhibit (a few) peaks of high impedanceat resonant frequencies caused by RLC resonant loops. Previousarchitectural proposals adjust current variations bycontrolling instruction fetch and issue, trading off performanceand energy for noise reduction. However, the proposals do notconsider some conceptual issues and have implementation challenges.The issues include requiring fast response, responding tovariations that do not threaten the noise margins, or respondingto variations only at the resonant frequency while the range ofhigh impedance extends to a resonance band around the resonantfrequency. While previous schemes reduce the magnitude of variations,our proposal, called resonance tuning, changes the frequencyof current variations away from the resonance band to anon-resonant frequency to be absorbed by the power supply.Because inductive noise is a resonance problem, resonance tuningreacts only to repeated variations in the resonance band, andnot to isolated variations. Reacting after a few repetitions allowsmore time for the response and reduces unnecessary responses,decreasing performance and energy loss.