# Optimizing Grouped Convolutions on Edge Devices

arXiv: https://arxiv.org/abs/2006.09791 · HTML: https://mlsanity.com/paper/2006.09791/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2020.

## Built on by (most cited first, 12 of 12)

- [NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results](https://mlsanity.com/paper/2205.05675/) (2022)
- [MicroNet: Improving Image Recognition with Extremely Low FLOPs](https://mlsanity.com/paper/2108.05894/) (2021)
- [Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottlenecks](https://mlsanity.com/paper/2109.14320/) (2021)
- [Neural Architecture Search as Program Transformation Exploration](https://mlsanity.com/paper/2102.06599/) (2021)
- [Transfer-Tuning: Reusing Auto-Schedules for Efficient Tensor Program Code Generation](https://mlsanity.com/paper/2201.05587/) (2022)
- [Learning Features with Parameter-Free Layers](https://mlsanity.com/paper/2202.02777/) (2022)
- [Deep Learning on Home Drone: Searching for the Optimal Architecture](https://mlsanity.com/paper/2209.11064/) (2022)
- [IMDeception: Grouped Information Distilling Super-Resolution Network](https://mlsanity.com/paper/2204.11463/) (2022)
- [Image Classification on Accelerated Neural Networks](https://mlsanity.com/paper/2203.11081/) (2022)
- [Productive Reproducible Workflows for DNNs: A Case Study for Industrial Defect Detection](https://mlsanity.com/paper/2206.09359/) (2022)
- [Hardware-aware mobile building block evaluation for computer vision](https://mlsanity.com/paper/2208.12694/) (2022)
- [DLAS: An Exploration and Assessment of the Deep Learning Acceleration Stack](https://mlsanity.com/paper/2311.08909/) (2023)

## Abstract (arXiv)

When deploying a deep neural network on constrained hardware, it is possible to replace the network's standard convolutions with grouped convolutions. This allows for substantial memory savings with minimal loss of accuracy. However, current implementations of grouped convolutions in modern deep learning frameworks are far from performing optimally in terms of speed. In this paper we propose Grouped Spatial Pack Convolutions (GSPC), a new implementation of grouped convolutions that outperforms existing solutions. We implement GSPC in TVM, which provides state-of-the-art performance on edge devices. We analyze a set of networks utilizing different types of grouped convolutions and evaluate their performance in terms of inference time on several edge devices. We observe that our new implementation scales well with the number of groups and provides the best inference times in all settings, improving the existing implementations of grouped convolutions in TVM, PyTorch and TensorFlow Lite by 3.4x, 8x and 4x on average respectively. Code is available at https://github.com/gecLAB/tvm-GSPC/