Journal article · 2024 · Open access
ShaderNN: A lightweight and efficient inference engine for real-time applications on mobile GPUs
Neurocomputing, 611, 128628 · Published 19 September 2024 · DOI 10.1016/j.neucom.2024.128628
In brief
“ShaderNN: A lightweight and efficient inference engine for real-time applications on mobile GPUs” is a 2024 journal article by Jing Xie and 7 co-authors, published in Neurocomputing. OpenAlex counts 7 citations as of 19 November 2026. It is open access under a CC BY-NC licence: the full text is free to read at Neurocomputing.
- Citations
- 7
- Most cited in
- 2025 (3)
- Field-weighted impact
- 1.34
- References
- 25
- Authors
- 8
Abstract
Inference using deep neural networks on mobile devices has been an active area of research in recent years. The design of a deep learning inference framework targeted for mobile devices needs to consider various factors, such as the limited computational capacity of the devices, low power budget, varied memory access methods, and I/O bus bandwidth governed by the underlying processor's architecture. Furthermore, integrating an inference framework with time-sensitive applications - such as games and video-based software to perform tasks like ray tracing denoising and video processing - introduces the need to minimize data movement between processors and increase data locality in the target processor. In this paper, we propose Shader Neural Network (ShaderNN), an OpenGL-based, fast, and power-efficient inference framework designed for mobile devices to address these challenges. Our contributions include the following: (1) the texture-based input/output provides an efficient, zero-copy integration with real-time graphics pipelines or image processing applications, thereby saving expensive data transfers between CPU and GPU, which are unavoidable in most existing inference engines; (2) we are the first to leverage fragment shaders based on the OpenGL backend in neural network inference operators, which has an advantage in deploying parametrically small neural network models; (3) a hybrid implementation of the compute shader and fragment shader is proposed that enables layer-level shader selection to boost performance; and (4) we utilize OpenGL features - such as normalization, interpolation and texture padding - to improve performance. Experiments illustrate the favorable performance of ShaderNN over other popular on-device deep learning frameworks such as TensorFlow-Lite on the latest mobile devices powered by Qualcomm and MediaTek chips. A case study further demonstrates the usability and integration of the ShaderNN framework with a media processing Android application seamlessly. ShaderNN is available open source at Github (https://github.com/inferenceengine/shadernn).
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Xie, J., Yan, Y., Saxena, A., Qiu, Q., Chen, J., Sun, H., Chen, R., & Bhattacharyya, S. S. (2024). ShaderNN: A lightweight and efficient inference engine for real-time applications on mobile GPUs. Neurocomputing, 611, 128628. https://doi.org/10.1016/j.neucom.2024.128628
MLA 9
Xie, Jing, et al. “ShaderNN: A lightweight and efficient inference engine for real-time applications on mobile GPUs.” Neurocomputing, vol. 611, 2024, p. 128628. https://doi.org/10.1016/j.neucom.2024.128628.
Chicago
Xie, Jing, Yuzhong Yan, Abhishek Saxena, Qiang Qiu, Jiangong Chen, Hongyu Sun, Rong Chen, and Shuvra S. Bhattacharyya. 2024. “ShaderNN: A lightweight and efficient inference engine for real-time applications on mobile GPUs.” Neurocomputing 611: 128628. https://doi.org/10.1016/j.neucom.2024.128628.
Harvard
Xie, J. et al. (2024) ‘ShaderNN: A lightweight and efficient inference engine for real-time applications on mobile GPUs’, Neurocomputing, 611, p. 128628. doi:10.1016/j.neucom.2024.128628.
IEEE
J. Xie et al., “ShaderNN: A lightweight and efficient inference engine for real-time applications on mobile GPUs,” Neurocomputing, vol. 611, p. 128628, 2024, doi: 10.1016/j.neucom.2024.128628.
BibTeX
@article{xie2024shadernn,
title = {{ShaderNN: A lightweight and efficient inference engine for real-time applications on mobile GPUs}},
author = {Xie, Jing and Yan, Yuzhong and Saxena, Abhishek and Qiu, Qiang and Chen, Jiangong and Sun, Hongyu and Chen, Rong and Bhattacharyya, Shuvra S.},
journal = {Neurocomputing},
year = {2024},
volume = {611},
pages = {128628},
doi = {10.1016/j.neucom.2024.128628},
url = {https://doi.org/10.1016/j.neucom.2024.128628}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 1 | |
| 2025 | 3 | |
| 2026 | 3 |
Its field-weighted citation impact is 1.34: it has been cited 1.34 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- neural network inference
- mobile GPUs
- OpenGL
- fragment shader
- compute shaders
- zero-copy data transfer
- power efficiency
- video processing
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Xie, J., Yan, Y., Saxena, A., Qiu, Q., Chen, J., Sun, H., Chen, R., & Bhattacharyya, S. S. (2024). ShaderNN: A lightweight and efficient inference engine for real-time applications on mobile GPUs. Neurocomputing, 611, 128628. https://doi.org/10.1016/j.neucom.2024.128628
How many times has this paper been cited?
7 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Neurocomputing: sign in and open the full text from this page.
Who wrote this paper?
Jing Xie, Yuzhong Yan, Abhishek Saxena, Qiang Qiu, Jiangong Chen, Hongyu Sun, Rong Chen, Shuvra S. Bhattacharyya.
What is the DOI of this paper?
10.1016/j.neucom.2024.128628, permanently at https://doi.org/10.1016/j.neucom.2024.128628. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.