NL-DPE: An Analog In-memory Non-Linear Dot Product Engine for Efficient CNN and LLM Inference

TL;DR

NL-DPE is a novel in-memory computing engine that enables efficient, non-linear, and data-dependent neural network inference by transforming complex functions into decision trees, eliminating ADCs, and improving scalability and accuracy.

Contribution

It introduces a new analog in-memory computing architecture with RRAM-based ACAM to support arbitrary non-linear functions and data-dependent operations, overcoming key limitations of prior IMC accelerators.

Findings

28X energy efficiency over GPU baseline

249X speedup over GPU baseline

Eliminates ADCs for non-linear computations

Abstract

Resistive Random Access Memory (RRAM) based in-memory computing (IMC) accelerators offer significant performance and energy advantages for deep neural networks (DNNs), but face three major limitations: (1) they support only \textit{static} dot-product operations and cannot accelerate arbitrary non-linear functions or data-dependent multiplications essential to modern LLMs; (2) they demand large, power-hungry analog-to-digital converter (ADC) circuits; and (3) mapping model weights to device conductance introduces errors from cell nonidealities. These challenges hinder scalable and accurate IMC acceleration as models grow. We propose NL-DPE, a Non-Linear Dot Product Engine that overcomes these barriers. NL-DPE augments crosspoint arrays with RRAM-based Analog Content Addressable Memory (ACAM) to execute arbitrary non-linear functions and data-dependent matrix multiplications in the analog domain by transforming them into decision trees, fully eliminating ADCs. To address device noise, NL-DPE uses software-based Noise Aware Fine-tuning (NAF), requiring no in-device calibration. Experiments show that NL-DPE delivers 28X energy efficiency and 249X speedup over a GPU baseline, and 22X energy efficiency and 245X speedup over existing IMC accelerators, while maintaining high accuracy.