.png){kind=icon}
Return
Binary Weight Multibit Activation Quantization for Compute-in-Memory CNN Accelerators
.png){kind=icon}
PRE
AI
DOI：10.1109/TCAD.2025.3595830.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
compute-in-memory (CIM) accelerators have emerged as a promising way for enhancing the energy efficiency of convolutional neural networks (CNNs). Deploying CNNs on CIM platforms generally requires quantization of network weights and activations to meet hardware constraints. However, existing approaches either prioritize hardware efficiency with binary weight and activation quantization at the cost of accuracy, or utilize multibit weights and activations for greater accuracy but limited efficiency. In this article, we introduce a novel binary weight multibit activation (BWMA) method for CNNs on CIM-based accelerators. Our contributions include: deriving closed-form solutions for weight quantization in each layer, significantly improving the representational capabilities of binarized weights; and developing a differentiable function for activation quantization, approximating the ideal multibit function while bypassing the extensive search for optimal settings. Through comprehensive experiments on CIFAR-10 and ImageNet datasets, we show that BWMA achieves notable accuracy improvements over existing methods, registering gains of 1.44%–5.46% and 0.35%–5.37% on respective datasets. Moreover, hardware simulation results indicate that 4-bit activation quantization strikes the optimal balance between hardware cost and model performance.
Keywords:
compute-in-memory (CIM)
ferroelectric field-effect transistor (FeFET)
model quantization
resistive random-access memory (RRAM)
static random-access memory (SRAM)
Journal
I
IF:
2.9
Papers:
671
Citations:
9.6K
Organization
Cited Papers
.png){kind=icon}
ShareSave
ShareSaveShareSaveShareSaveShareSave
View more