Athena: Add More Intelligence to RMT-Based Network Data Plane with Low-Bit Quantization
摘要
Performing per-packet neural network (NN) inference on the network data plane is a promising approach for accurate and fast decision-making in computer network. However, data plane architecture like the Reconfigurable Match Tables (RMT) pipeline has limited support for NN computation. Previous efforts have utilized the Binary Neuron Network (BNN) as a compromise, but the accuracy loss of BNN is high. Inspired by the accuracy gain of the low-bit (2-bit and 4-bit) models, this paper proposes Athena. Athena can deploy the sparse low-bit quantization models on RMT. Compared with the BNN-based state-of-the-art, Athena achieves new Pareto frontier regarding model accuracy and inference latency.