I. Introduction
The increasing need for energy-efficient digital circuits, driven by the widespread use of the Internet of Things (IoT) devices and wearables, has introduced challenges stemming from the inherent trade-off between limited on-chip energy resources and essential speed [1], [2]. Near-threshold operation has been proposed to mitigate this, offering a balance between performance and energy consumption. However, this approach introduces increased path delays due to variability in process, voltage, temperature, and aging effects, alongside design margins instituted for reliability [3]. Although these margins ensure reliable low-voltage operation, they negate some of the energy savings achieved in this regime.