On Control and Data Plane Programmability for Data-Driven Networking

Sacco, Alessio; Esposito, Flavio; Marchetto, Guido

doi:10.1109/hpsr52026.2021.9481859

Cited by 3 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The advent of in-network Artificial Intelligence (AI) will enable future network devices to process data (i.e., packets, flows, aggregate traffic) at wirespeed with the support of builtin AI-enabled components [1], [2]. In-network function offloading is becoming popular thanks to the flexibility and maturity of programmable data plane languages such as P4, and has the potential to bring programmable and versatile networking operation at the data plane thus saving computational resources for applications at the edge and with limited energy consumption, since re-using the same network infrastructure devices [3].…”

Section: Introductionmentioning

confidence: 99%

Cascaded Look Up Table Distillation of P4 Deep Neural Network Switches

De Marinis,

Paolini,

Bakar

et al. 2023

GLOBECOM 2023 - 2023 IEEE Global Communications Conference

View full text Add to dashboard Cite

In-network function offloading represents a key enabler of the SDN-based data plane programmability to enhance network operation and awareness while speeding up applications and reducing the energy footprint. The offload of network functions exploiting machine learning and artificial intelligence has been recently considered with intermediate solutions such as feature extraction acceleration and mixed architectures including AI-specific platforms (e.g., GPU, FPGA).Indeed, the P4 language enables the programmability of deep neural networks inside the pipelines of both software and hardware switches and NICs. However, programmable hardware pipeline chipsets suffer from significant computing capability limitations (e.g., missing arithmetic logic units, limited and slow stateful registers) preventing the plain programmability of a deep neural network (DNN) operating at wirespeed. This paper proposes an innovative knowledge distillation technique that maps a DNN into a cascade of lookup tables (i.e., flow tables) with limited entry size. The proposed mapping avoids stateful elements and maths operators, whose requirement prevented the deployment of DNNs within hardware switches up to now. The evaluation is carried out considering a cyber security use case targeting a DDoS mitigator network function, showing negligible impact due to the lossless mapping reduction and feature quantization.

show abstract

Section: Introductionmentioning

confidence: 99%