# OpenHLS: High-Level Synthesis for Low-Latency Deep Neural Networks for Experimental Science

arXiv: https://arxiv.org/abs/2302.06751 · HTML: https://mlsanity.com/paper/2302.06751/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 52 references that are in the map.
- First posted on arXiv 13 Feb 2023.

## Builds on (most cited first, 12 of 12)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems](https://mlsanity.com/paper/1512.01274/) (2015)
- [Fast inference of deep neural networks in FPGAs for particle physics](https://mlsanity.com/paper/1804.06913/) (2018)
- [Glow: Graph Lowering Compiler Techniques for Neural Networks](https://mlsanity.com/paper/1805.00907/) (2018)
- [MLIR: A Compiler Infrastructure for the End of Moore's Law](https://mlsanity.com/paper/2002.11054/) (2020)
- [Optimizing CNN Model Inference on CPUs](https://mlsanity.com/paper/1809.02697/) (2018)
- [ScaleHLS: A New Scalable High-Level Synthesis Framework on Multi-Level Intermediate Representation](https://mlsanity.com/paper/2107.11673/) (2021)
- [BraggNN: Fast X-ray Bragg Peak Analysis Using Deep Learning](https://mlsanity.com/paper/2008.08198/) (2020)
- [Deep Learning Accelerated Light Source Experiments](https://mlsanity.com/paper/1910.04081/) (2019)
- [A Data-Centric Optimization Framework for Machine Learning](https://mlsanity.com/paper/2110.10802/) (2021)
- [Gradual Tensor Shape Checking](https://mlsanity.com/paper/2203.08402/) (2022)

## Built on by (most cited first, 1 of 1)

- [Neural Architecture Codesign for Fast Bragg Peak Analysis](https://mlsanity.com/paper/2312.05978/) (2023)

## Abstract (arXiv)

In many experiment-driven scientific domains, such as high-energy physics, material science, and cosmology, high data rate experiments impose hard constraints on data acquisition systems: collected data must either be indiscriminately stored for post-processing and analysis, thereby necessitating large storage capacity, or accurately filtered in real-time, thereby necessitating low-latency processing. Deep neural networks, effective in other filtering tasks, have not been widely employed in such data acquisition systems, due to design and deployment difficulties. We present an open source, lightweight, compiler framework, without any proprietary dependencies, OpenHLS, based on high-level synthesis techniques, for translating high-level representations of deep neural networks to low-level representations, suitable for deployment to near-sensor devices such as field-programmable gate arrays. We evaluate OpenHLS on various workloads and present a case-study implementation of a deep neural network for Bragg peak detection in the context of high-energy diffraction microscopy. We show OpenHLS is able to produce an implementation of the network with a throughput 4.8 μs/sample, which is approximately a 4× improvement over the existing implementation