Training DNN IoT Applications for Deployment On Analog NVM Crossbars

TL;DR

This paper presents a training framework for deploying DNNs on analog NVM crossbars, addressing noise and weight representation issues, and demonstrating significant efficiency gains on CIFAR10 and HAR tasks.

Contribution

It introduces a novel training algorithm for uniform layer weights and activations, and employs NAS to use unipolar weights, simplifying hardware and improving efficiency.

Findings

Achieved up to 92.91% accuracy on HAR with 2-bit positive weights.

Realized 80% area reduction and 45% energy savings.

Validated approach on CIFAR10 and HAR applications with 4-bit and 2-bit devices.

Abstract

A trend towards energy-efficiency, security and privacy has led to a recent focus on deploying DNNs on microcontrollers. However, limits on compute and memory resources restrict the size and the complexity of the ML models deployable in these systems. Computation-In-Memory architectures based on resistive nonvolatile memory (NVM) technologies hold great promise of satisfying the compute and memory demands of high-performance and low-power, inherent in modern DNNs. Nevertheless, these technologies are still immature and suffer from both the intrinsic analog-domain noise problems and the inability of representing negative weights in the NVM structures, incurring in larger crossbar sizes with concomitant impact on ADCs and DACs. In this paper, we provide a training framework for addressing these challenges and quantitatively evaluate the circuit-level efficiency gains thus accrued. We make two contributions: Firstly, we propose a training algorithm that eliminates the need for tuning individual layers of a DNN ensuring uniformity across layer weights and activations. This ensures analog-blocks that can be reused and peripheral hardware substantially reduced. Secondly, using NAS methods, we propose the use of unipolar-weighted (either all-positive or all-negative weights) matrices/sub-matrices. Weight unipolarity obviates the need for doubling crossbar area leading to simplified analog periphery. We validate our methodology with CIFAR10 and HAR applications by mapping to crossbars using 4-bit and 2-bit devices. We achieve up to 92:91% accuracy (95% floating-point) using 2-bit only-positive weights for HAR. A combination of the proposed techniques leads to 80% area improvement and up to 45% energy reduction.