On the Accuracy of Analog Neural Network Inference Accelerators

by   T. Patrick Xiao, et al.

Specialized accelerators have recently garnered attention as a method to reduce the power consumption of neural network inference. A promising category of accelerators utilizes nonvolatile memory arrays to both store weights and perform in situ analog computation inside the array. While prior work has explored the design space of analog accelerators to optimize performance and energy efficiency, there is seldom a rigorous evaluation of the accuracy of these accelerators. This work shows how architectural design decisions, particularly in mapping neural network parameters to analog memory cells, influence inference accuracy. When evaluated using ResNet50 on ImageNet, the resilience of the system to analog non-idealities - cell programming errors, analog-to-digital converter resolution, and array parasitic resistances - all improve when analog quantities in the hardware are made proportional to the weights in the network. Moreover, contrary to the assumptions of prior work, nearly equivalent resilience to cell imprecision can be achieved by fully storing weights as analog quantities, rather than spreading weight bits across multiple devices, often referred to as bit slicing. By exploiting proportionality, analog system designers have the freedom to match the precision of the hardware to the needs of the algorithm, rather than attempting to guarantee the same level of precision in the intermediate results as an equivalent digital accelerator. This ultimately results in an analog accelerator that is more accurate, more robust to analog errors, and more energy-efficient.


page 7

page 11

page 13

page 14

page 15


Leveraging Residue Number System for Designing High-Precision Analog Deep Neural Network Accelerators

Achieving high accuracy, while maintaining good energy efficiency, in an...

Neural-PIM: Efficient Processing-In-Memory with Neural Approximation of Peripherals

Processing-in-memory (PIM) architectures have demonstrated great potenti...

Design space exploration of Ferroelectric FET based Processing-in-Memory DNN Accelerator

In this letter, we quantify the impact of device limitations on the clas...

Tetris: Re-architecting Convolutional Neural Network Computation for Machine Learning Accelerators

Inference efficiency is the predominant consideration in designing deep ...

Neural Network-Hardware Co-design for Scalable RRAM-based BNN Accelerators

Recently, RRAM-based Binary Neural Network (BNN) hardware has been gaini...

Neuron inspired data encoding memristive multi-level memory cell

Mapping neuro-inspired algorithms to sensor backplanes of on-chip hardwa...

Multiscale Co-Design Analysis of Energy, Latency, Area, and Accuracy of a ReRAM Analog Neural Training Accelerator

Neural networks are an increasingly attractive algorithm for natural lan...

Please sign up or login with your details

Forgot password? Click here to reset