# Arithmetic Intensity Balancing Convolution for Hardware-aware Efficient Block Design

arXiv: https://arxiv.org/abs/2304.04016 · HTML: https://mlsanity.com/paper/2304.04016/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 8 Apr 2023.

## Builds on (most cited first, 9 of 9)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications](https://mlsanity.com/paper/1811.09886/) (2018)
- [Modeling Data Reuse in Deep Neural Networks by Taking Data-Types into Cognizance](https://mlsanity.com/paper/2008.02565/) (2020)
- [Searching for Efficient Neural Architectures for On-Device ML on Edge TPUs](https://mlsanity.com/paper/2204.14007/) (2022)

## Abstract (arXiv)

As deep learning advances, edge devices and lightweight neural networks are becoming more important. To reduce latency in the AI accelerator, it's essential to not only reduce FLOPs but also enhance hardware performance. We proposed an arithmetic intensity balancing convolution (ABConv) to address the issue of the overall intensity being limited by the small weight arithmetic intensity for convolution with a small spatial size. ABConv increased the maximum bound of overall arithmetic intensity and significantly reduced latency, without sacrificing accuracy. We tested the latency and hardware performance of ABConv on the Arm Ethos-U65 NPU in various configurations and used it to replace some of MobileNetV1 and ResNet50 in image classification for CIFAR100.