OSA-HCIM: On-The-Fly Saliency-Aware Hybrid SRAM CIM with Dynamic Precision Configuration

TL;DR

This paper introduces OSA-HCIM, a flexible CIM architecture that dynamically adjusts precision based on input importance, significantly improving energy efficiency while maintaining accuracy for deep neural network computations.

Contribution

The paper presents a novel on-the-fly saliency-aware precision configuration scheme and a hybrid CIM array that enables flexible, resource-efficient neural network processing.

Findings

Achieves 1.95x energy efficiency improvement

Maintains minimal accuracy loss on CIFAR100

First CIM with dynamic digital-analog boundary

Abstract

Computing-in-Memory (CIM) has shown great potential for enhancing efficiency and performance for deep neural networks (DNNs). However, the lack of flexibility in CIM leads to an unnecessary expenditure of computational resources on less critical operations, and a diminished Signal-to-Noise Ratio (SNR) when handling more complex tasks, significantly hindering the overall performance. Hence, we focus on the integration of CIM with Saliency-Aware Computing -- a paradigm that dynamically tailors computing precision based on the importance of each input. We propose On-the-fly Saliency-Aware Hybrid CIM (OSA-HCIM) offering three primary contributions: (1) On-the-fly Saliency-Aware (OSA) precision configuration scheme, which dynamically sets the precision of each MAC operation based on its saliency, (2) Hybrid CIM Array (HCIMA), which enables simultaneous operation of digital-domain CIM (DCIM) and analog-domain CIM (ACIM) via split-port 6T SRAM, and (3) an integrated framework combining OSA and HCIMA to fulfill diverse accuracy and power demands. Implemented on a 65nm CMOS process, OSA-HCIM demonstrates an exceptional balance between accuracy and resource utilization. Notably, it is the first CIM design to incorporate a dynamic digital-to-analog boundary, providing unprecedented flexibility for saliency-aware computing. OSA-HCIM achieves a 1.95x enhancement in energy efficiency, while maintaining minimal accuracy loss compared to DCIM when tested on CIFAR100 dataset.