Senputing: An Ultra-Low-Power Always-On Vision Perception Chip Featuring the Deep Fusion of Sensing and Computing

TLDR

Always‑on intelligent visual perception applications are widely deployed at the edge in the AIoT era. To eliminate power costs of data conversion and transmission, the authors propose Senputing, an ultra‑low‑power processing‑in‑sensor chip that fuses sensing and computing into a BNN‑based hierarchical system. The chip computes directly from photocurrents in a first BNN layer, sending coarse classification results to downstream processors, and switches to sensor mode for full‑resolution images when an object is detected, all fabricated as a 32×32 180 nm CMOS prototype. It operates in two modes and achieves 93.76 % accuracy on MNIST at 147 nW and 156 fps, a 13.1× energy‑efficiency improvement over state‑of‑the‑art.

Abstract

Always-on intelligent visual perception applications are widely deployed in edges in the AIoT era. In order to eliminate power costs of data conversion and transmission, this paper proposes Senputing, an ultra-low-power processing-in-sensor chip that completely fuses sensing and computing together for a BNN-based hierarchical processing system. This chip could operate in two modes. In computation mode, photocurrents are directly utilized for computing without being converted into voltages, and the computation results of 1-st BNN layer are directly sent out to subsequent BNN processors for an always-on coarse classification, eliminating conversion power and storage cost of raw images. Once an interested objected is detected, this chip switches to sensor mode and sends raw images to potential full-precision processors or cloud servers for fine-grained recognition or segmentation. A <inline-formula> <tex-math notation="LaTeX">$32\times 32$ </tex-math></inline-formula> prototype is fabricated with 180nm CMOS process. It accomplishes MNIST dataset classification task with the accuracy of 93.76&#x0025; and the power consumption of 147nW at 156fps, achieving <inline-formula> <tex-math notation="LaTeX">$13.1\times $ </tex-math></inline-formula> energy efficiency compared with state-of-the-art work.