Pegasus: A Universal Framework for Scalable Deep Learning Inference on the Dataplane

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yinchao, Yao, Su, Feng, Yong, Chen, Kang, Li, Tong, Liu, Zhuotao, Zhao, Yi, Zhang, Lexuan, Gao, Xiangyu, Xiong, Feng, Li, Qi, Xu, Ke
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913881184534528
author Zhang, Yinchao
Yao, Su
Feng, Yong
Chen, Kang
Li, Tong
Liu, Zhuotao
Zhao, Yi
Zhang, Lexuan
Gao, Xiangyu
Xiong, Feng
Li, Qi
Xu, Ke
author_facet Zhang, Yinchao
Yao, Su
Feng, Yong
Chen, Kang
Li, Tong
Liu, Zhuotao
Zhao, Yi
Zhang, Lexuan
Gao, Xiangyu
Xiong, Feng
Li, Qi
Xu, Ke
contents The paradigm of Intelligent DataPlane (IDP) embeds deep learning (DL) models on the network dataplane to enable intelligent traffic analysis at line-speed. However, the current use of the match-action table (MAT) abstraction on the dataplane is misaligned with DL inference, leading to several key limitations, including accuracy degradation, limited scale, and lack of generality. This paper proposes Pegasus to address these limitations. Pegasus translates DL operations into three dataplane-oriented primitives to achieve generality: Partition, Map, and SumReduce. Specifically, Partition "divides" high-dimensional features into multiple low-dimensional vectors, making them more suitable for the dataplane; Map "conquers" computations on the low-dimensional vectors in parallel with the technique of fuzzy matching, while SumReduce "combines" the computation results. Additionally, Pegasus employs Primitive Fusion to merge computations, improving scalability. Finally, Pegasus adopts full precision weights with fixed-point activations to improve accuracy. Our implementation on a P4 switch demonstrates that Pegasus can effectively support various types of DL models, including Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), and AutoEncoder models on the dataplane. Meanwhile, Pegasus outperforms state-of-the-art approaches with an average accuracy improvement of up to 22.8%, along with up to 248x larger model size and 212x larger input scale.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05779
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pegasus: A Universal Framework for Scalable Deep Learning Inference on the Dataplane
Zhang, Yinchao
Yao, Su
Feng, Yong
Chen, Kang
Li, Tong
Liu, Zhuotao
Zhao, Yi
Zhang, Lexuan
Gao, Xiangyu
Xiong, Feng
Li, Qi
Xu, Ke
Networking and Internet Architecture
Machine Learning
The paradigm of Intelligent DataPlane (IDP) embeds deep learning (DL) models on the network dataplane to enable intelligent traffic analysis at line-speed. However, the current use of the match-action table (MAT) abstraction on the dataplane is misaligned with DL inference, leading to several key limitations, including accuracy degradation, limited scale, and lack of generality. This paper proposes Pegasus to address these limitations. Pegasus translates DL operations into three dataplane-oriented primitives to achieve generality: Partition, Map, and SumReduce. Specifically, Partition "divides" high-dimensional features into multiple low-dimensional vectors, making them more suitable for the dataplane; Map "conquers" computations on the low-dimensional vectors in parallel with the technique of fuzzy matching, while SumReduce "combines" the computation results. Additionally, Pegasus employs Primitive Fusion to merge computations, improving scalability. Finally, Pegasus adopts full precision weights with fixed-point activations to improve accuracy. Our implementation on a P4 switch demonstrates that Pegasus can effectively support various types of DL models, including Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), and AutoEncoder models on the dataplane. Meanwhile, Pegasus outperforms state-of-the-art approaches with an average accuracy improvement of up to 22.8%, along with up to 248x larger model size and 212x larger input scale.
title Pegasus: A Universal Framework for Scalable Deep Learning Inference on the Dataplane
topic Networking and Internet Architecture
Machine Learning
url https://arxiv.org/abs/2506.05779