betaFeedback

WorksEngineering

ASDL: A Fast Vector Approximation Algorithm for Multiplierless Designs of Convolutional Neural Networks

Abstract

Matrix multiplications are one of the main computational bottlenecks in neural networks. The calculation reduces to numerous sums of partial products, which scale with the total number of Signed Power of Two (SPT) values in the multiplier matrix. Minimizing the SPT count can significantly reduce the computational burden.In this context, we present a Sum Of (signed) Powers Of Two (SOPOT) vector approximation algorithm that limits SPT counts, namely the Accelerated Signed Digit Loading (ASDL) algorithm. This approximation algorithm converts ResNet50 1010 times faster than its predecessor MPGBP, while being more precise. We apply this method to the pre-trained coefficients of different convolutional neural networks, achieving 80.41%80.41\% ImageNet accuracy down from 81.3%81.3\%, at an average of only 1.51.5 active bits per coefficient. This is done without any retraining or calibration, which are typically required for the most aggressive quantization methods. Our approach offers a promising direction for neural network inference with higher energy efficiency and fewer hardware requirements: we anticipate up to 1010 times improvement over float16 inference.

Paper details

vlnc:W_6n4gnt2z
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC-BY-NC-ND-4.0
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Engineering

Not recorded for this paper

View statement
Looking for related papers…