Demo: First Demonstration of Real-Time Photonic-Electronic DNN Acceleration on SmartNICs

PROCEEDINGS OF THE 2023 ACM SIGCOMM 2023 CONFERENCE, SIGCOMM 2023(2023)

引用 1|浏览6
暂无评分
摘要
We demonstrate Lightning, a reconfigurable photonic-electronic deep learning smartNIC that serves real-time inference requests at 4.055 GHz compute frequency. To do so, Lightning uses a novel datapath to feed traffic from the NIC into its photonic computing cores without incurring digital data movement bottlenecks. Lightning achieves this by employing a reconfigurable count-action abstraction, which decouples the compute control plane from the data plane. The count-action abstraction counts the number of operations for each computation task in the Directed Acyclic Graph (DAG). It then triggers the execution of the next task(s) as soon as the previous task is finished without interrupting the dataflow. Our prototype shows that Lightning achieves 99.25% photonic MAC accuracy. When serving real-time inference requests, Lightning accelerates the end-to-end inference latency of the LeNet DNN by 9.4x and 6.6x compared to Nvidia P4 and A100 GPUs, respectively.
更多
查看译文
关键词
Photonic computing,Network hardware design,Computer architecture,Real-time AI,Machine learning inference
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要