# Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1809.07196 · HTML: https://mlsanity.com/paper/1809.07196/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2018.

## Built on by (most cited first, 10 of 10)

- [SECDA: Efficient Hardware/Software Co-Design of FPGA-based DNN Accelerators for Edge Inference](https://mlsanity.com/paper/2110.00478/) (2021)
- [DNNShifter: An Efficient DNN Pruning System for Edge Computing](https://mlsanity.com/paper/2309.06973/) (2023)
- [Exploring Effects of Computational Parameter Changes to Image Recognition Systems](https://mlsanity.com/paper/2211.00471/) (2022)
- [Improving Robustness Against Adversarial Attacks with Deeply Quantized Neural Networks](https://mlsanity.com/paper/2304.12829/) (2023)
- [DeltaNN: Assessing the Impact of Computational Environment Parameters on the Performance of Image Recognition Models](https://mlsanity.com/paper/2306.06208/) (2023)
- [Optimizing Data Processing in Space for Object Detection in Satellite Imagery](https://mlsanity.com/paper/2107.03774/) (2021)
- [Bifrost: End-to-End Evaluation and Optimization of Reconfigurable DNN Accelerators](https://mlsanity.com/paper/2204.12418/) (2022)
- [Productive Reproducible Workflows for DNNs: A Case Study for Industrial Defect Detection](https://mlsanity.com/paper/2206.09359/) (2022)
- [Rapid Deployment of DNNs for Edge Computing via Structured Pruning at Initialization](https://mlsanity.com/paper/2404.16877/) (2024)
- [DLAS: An Exploration and Assessment of the Deep Learning Acceleration Stack](https://mlsanity.com/paper/2311.08909/) (2023)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) are extremely computationally demanding, presenting a large barrier to their deployment on resource-constrained devices. Since such systems are where some of their most useful applications lie (e.g. obstacle detection for mobile robots, vision-based medical assistive technology), significant bodies of work from both machine learning and systems communities have attempted to provide optimisations that will make CNNs available to edge devices. In this paper we unify the two viewpoints in a Deep Learning Inference Stack and take an across-stack approach by implementing and evaluating the most common neural network compression techniques (weight pruning, channel pruning, and quantisation) and optimising their parallel execution with a range of programming approaches (OpenMP, OpenCL) and hardware architectures (CPU, GPU). We provide comprehensive Pareto curves to instruct trade-offs under constraints of accuracy, execution time, and memory space.