36.6 A Sparsity-Aware Neural Interface with CIM-Based Predictive Focused Sampling for Hotspot Spike Tracking

Digest of technical papers/Digest of technical papers - IEEE International Solid-State Circuits Conference 2026

View at publisher
Authors: Hui Wu, Fengshi Tian, Jinbo Chen, Zhipeng Liao, Hongyong Zhang, Xing Liu, Wenjun Zou, Sirui Cheng, Zhao Zhang, Jianlong Xu, Chi-Ying Tsui, Kwang-Ting Tim Cheng
+2 more Jie Yang, Mohamad Sawan
DOI: 10.1109/isscc49663.2026.11409079
Cited by: 0
References: 23

Abstract

This 1024-electrode neural interface solves the power, area, and bandwidth bottleneck by combining low-power panoramic scanning for hotspot prediction with high-fidelity spike tracking on active sites. The dynamic allocation is guided by a real-time compute-in-memory (CIM) engine, providing a$16 \times$resolution boost$(10 \text{kHz})$and$0.0011 \text{mm}^{2} / \text{ch}$efficiency in 40 nm CMOS. The design maximizes spike density to lower power and silicon area.

Fields of Study & Subjects

Analog and Mixed-Signal Circuit Design Advanced Memory and Neural Computing Neuroscience and Neural Engineering

Publication details

Journal / source
Digest of technical papers/Digest of technical papers - IEEE International Solid-State Circuits Conference
Pages
610–612
Publication date
15 February 2026
Language
EN