Project FDNN: FPGA-based Deep Neural Networks
This project aims to accelerate the inference and training of Deep Neural Networks (DNN) using FPGAs for high energy efficiency and low latency in data centers. We have been developing a CNN (Convolutional Neural Network) accelerator…
FUSO: A Fast Multi-path Transport Loss Recovery Scheme for Data Centers
Packet loss in data centers, caused by both congestion and failures, greatly hurts the performance of the transport layer, leading to a long tail of flow completion time. FUSO is a fast multi-path transport loss…
Project ClickNP
ClickNP is a programming model/language for modularized packet processing on FPGA-accelerated servers. ClickNP is designed with the following four goals: Flexibility. ClickNP fully programs using high-level languages. Developers program with high-level abstractions and familiar tools, and…