# Quantization of Deep Neural Networks for Accumulator-constrained Processors

Source: [Quantization of Deep Neural Networks for Accumulator-constrained Processors](<https://www.sota2.com/research/paper/68fa67731e209131cea165cc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:15:13.389Z

Authors: Barry de Bruin, Zoran Zivkovic, Henk Corporaal

Published: 2020-04-24T14:47:14.000Z

## Abstract

We introduce an Artificial Neural Network (ANN) quantization methodology for platforms without wide accumulation registers. This enables fixed-point model deployment on embedded compute platforms that are not specifically designed for large kernel computations (i.e. accumulator-constrained processors). We formulate the quantization problem as a function of accumulator size, and aim to maximize the model accuracy by maximizing bit width of input data and weights. To reduce the number of configurations to consider, only solutions that fully utilize the available accumulator bits are being tested. We demonstrate that 16-bit accumulators are able to obtain a classification accuracy within 1\\% of the floating-point baselines on the CIFAR-10 and ILSVRC2012 image classification benchmarks. Additionally, a near-optimal $2\\times$ speedup is obtained on an ARM processor, by exploiting 16-bit accumulators for image classification on the All-CNN-C and AlexNet networks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2004.11783>)

[PDF](<https://arxiv.org/pdf/2004.11783.pdf>)