• Home
  • Search
  • CAP-RAM: A Charge-Domain In-Memory Computing 6T-SRAM for Accurate and Precision-Programmable CNN Inference
  • Cite Icon124
  • https://doi.org/10.1109/jssc.2021.3056447Copy DOI Icon

CAP-RAM: A Charge-Domain In-Memory Computing 6T-SRAM for Accurate and Precision-Programmable CNN Inference

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

A compact, accurate, and bitwidth-programmable in-memory computing (IMC) static random-access memory (SRAM) macro, named CAP-RAM, is presented for energy-efficient convolutional neural network (CNN) inference. It leverages a novel charge-domain multiply-and-accumulate (MAC) mechanism and circuitry to achieve superior linearity under process variations compared to conventional IMC designs. The adopted semi-parallel architecture efficiently stores filters from multiple CNN layers by sharing eight standard 6T SRAM cells with one charge-domain MAC circuit. Moreover, up to six levels of bit-width of weights with two encoding schemes and eight levels of input activations are supported. A 7-bit charge-injection SAR (ciSAR) analog-to-digital converter (ADC) getting rid of sample and hold (S&H) and input/reference buffers further improves the overall energy efficiency and throughput. A 65-nm prototype validates the excellent linearity and computing accuracy of CAP-RAM. A single 512×128 macro stores a complete pruned and quantized CNN model to achieve 98.8% inference accuracy on the MNIST data set and 89.0% on the CIFAR-10 data set, with a 573.4-giga operations per second (GOPS) peak throughput and a 49.4-tera operations per second (TOPS)/W energy efficiency.

Similar Papers
  • PDF
  • Research Article
  • Citations36

10T SRAM Computing-in-Memory Macros for Binary and Multibit MAC Operation of DNN Edge Processors

  • Jan 01, 2021
  • IEEE Access
  • Van Truong Nguyen +2
  • PDF
  • Research Article
  • Citations23

Ultra-Low Power, Process-Tolerant 10T (PT10T) SRAM with Improved Read/Write Ability for Internet of Things (IoT) Applications

  • Sep 20, 2017
  • Journal of Low Power Electronics and Applications
  • Pooran Singh +1
  • PDF
  • Research Article
  • Citations25

Research on improved convolutional wavelet neural network

  • Sep 09, 2021
  • Scientific Reports
  • Jingwei Liu +4
  • Research Article
  • Citations63

PIMCA: A Programmable In-Memory Computing Accelerator for Energy-Efficient DNN Inference

  • May 01, 2023
  • IEEE Journal of Solid-State Circuits
  • Bo Zhang +9
  • Research Article

A 7T SECURITY ORIENTED SRAM BITCELL USING VLSI

  • Jun 22, 2022
  • INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT
  • C.Durga Tejaswi
  • Research Article
  • Citations1

HTCNN: High-Throughput Batch CNN Inference With Homomorphic Encryption

  • Mar 01, 2026
  • IEEE Transactions on Dependable and Secure Computing
  • Zewen Ye +6
  • Research Article
  • Citations27

SSM-CIM: An Efficient CIM Macro Featuring Single-Step Multi-bit MAC Computation for CNN Edge Inference

  • Nov 01, 2023
  • IEEE Transactions on Circuits and Systems I: Regular Papers
  • Heng Zhang +6
  • Preprint Article
  • Citations20

Optimization of Convolutional Neural Network Using the Linearly Decreasing Weight Particle Swarm Optimization

  • Jan 16, 2020
  • Proceedings of the Annual Conference of JSAI
  • T Serizawa +1
  • Conference Article
  • Citations1

A 12TOPS/W Computing-in-Memory Accelerator for Convolutional Neural Networks

  • May 28, 2022
  • Jun-Hui Fu +1
  • PDF
  • Research Article
  • Citations44

An Efficient Task Assignment Framework to Accelerate DPU-Based Convolutional Neural Network Inference on FPGAs

  • Jan 01, 2020
  • IEEE Access
  • Jiang Zhu +5
  • PDF
  • Research Article
  • Citations3

Logarithm Decreasing Inertia Weight Particle Swarm Optimization Algorithms for Convolutional Neural Network

  • May 27, 2022
  • JUITA: Jurnal Informatika
  • Murinto Murinto +1
  • Research Article
  • Citations25

MARS: Multimacro Architecture SRAM CIM-Based Accelerator With Co-Designed Compressed Neural Networks

  • Oct 24, 2020
  • IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
  • Syuan-Hao Sie +8
  • Research Article
  • Citations29

PUF-CIM: SRAM-Based Compute-In-Memory With Zero Bit-Error-Rate Physical Unclonable Function for Lightweight Secure Edge Computing

  • Aug 01, 2023
  • IEEE Transactions on Very Large Scale Integration (VLSI) Systems
  • Zhuojun Chen +5
  • Research Article
  • Citations15

PICO: Pipeline Inference Framework for Versatile CNNs on Diverse Mobile Devices

  • Apr 01, 2024
  • IEEE Transactions on Mobile Computing
  • Xiang Yang +6
  • Research Article
  • Citations4

An 11T1C Bit-Level-Sparsity-Aware Computing- in-Memory Macro With Adaptive Conversion Time and Computation Voltage

  • Nov 01, 2024
  • IEEE Transactions on Circuits and Systems I: Regular Papers
  • Ye Lin +7
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.