Skip to main navigation Skip to search Skip to main content

SACIM: A Synapse-inspired Asynchronous CIM with Discharging Feedback, Dynamic Delay and Parallelism Extension for CNN Inference

  • Tingran Chen
  • , Xiao Ya Wang
  • , Yuxuan Ran
  • , Kaiying Yang
  • , Yi Zhao
  • , Kexun Cheng
  • , Chen Li
  • , He Zhang
  • , Xueyan Wang
  • , Biao Pan*
  • *Corresponding author for this work
  • Beihang University
  • University of Science and Technology Beijing

Research output: Contribution to journalArticlepeer-review

Abstract

This brief presents a charge-domain analog compute-in-memory (ACIM) architecture, the Synapse-inspired Asynchronous CIM (SACIM), which addresses key challenges in generality, latency, and parallelism. The architecture includes three structures: a Non-Differential Decoupled (NDDC) bit-cell array for implementing negative signed weights; a Clock-free Asynchronous Controller (CFAC) to dynamically shorten latency; and an asynchronous Pulse-based Analog-to-Digital Converter (PADC) circuit with an NDDC coordination mechanism for parallelism extension. Fabricated in 40nm CMOS, the prototype achieves a peak energy efficiency of 655.78 TOPS/W and a throughput of 1180.4 GOPS, with 5.1 μW static power in a 99,280 μm2 area.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

  1. SDG 7 - Affordable and Clean Energy
    SDG 7 Affordable and Clean Energy

Keywords

  • Analog Computing-in-Memory
  • charging feedback
  • dynamic delay
  • parallelism extension
  • signed weight

Fingerprint

Dive into the research topics of 'SACIM: A Synapse-inspired Asynchronous CIM with Discharging Feedback, Dynamic Delay and Parallelism Extension for CNN Inference'. Together they form a unique fingerprint.

Cite this