Breaking the energy-efficiency barriers for smart sensing applications with “Sensing with Computing” architectures

With the developing technologies of artificial intelligence and the Internet of Things, intelligent IoT (iIoT) is prevailing currently. Design and implementation of integrated IoT nodes with continuous perception capability are indispensable to realize various smart terminal devices, which would also be vital to reduce the power consumption, improve the real-time performance, and enhance the security/privacy of the IoT system. In this paper, we present the architecture of “Sensing with Computing” and its chip design for smart sensing applications, which would support multi-modal perception signal processing with multi-dimension extension ability. Specially, we explore the analog/mixed-signal circuit designs and algorithm-hardware co-design methodologies for perception signal processing, and we also study the multi-modal integration of novel sensors and their interface technologies. Additionally, some multi-modal smart sensing systems with “Sensing + Computing in Memory” mixed-signal chips would be fabricated, which would support typical always-on smart sensing tasks.