A Low-Energy Inductive Transceiver using Spike-Latency Encoding for Wireless 3D Integration

Recently, the use of wireless (or contactless) 3D integration has been proposed as a low-cost method of stacking disparate processing and sensor dies into singular, small form-factor ICs. Whilst such devices would be ideally suited for the Internet of Things (IoT), in the IoT, maintaining low-power consumption is of paramount importance. Contactless intertier links use significant energy when forming a magnetic field which can penetrate multiple silicon dies, and hence are often criticised for their poor power efficiency when compared to wired alternatives such as through silicon vias (TSVs). To address this, in this paper we present a novel, neuro-inspired, inductive transceiver (for transmitting data between tiers of a 3D-IC) that maintains low power consumption by encoding frames of data in terms of the latency between pulses, thereby reducing the number of transmit pulses and energy required per bit. The proposed approach is validated using commercial electromagnetic and electrical circuit simulators in 65nm CMOS technology. Results demonstrate an energy consumption of 0.79pJ/bit, representing a reduction of 31% when compared to existing state-of-the-art transceivers, or an increased communication distance of up to 1.8x for the same energy budget.