Distilling Arbitration Logic from Traces using Machine Learning: A Case Study on NoC*
TimeTuesday, December 7th10:53am - 11:23am PST
Event Type
Research Manuscript
Virtual Programs
In-Person Only
In-Package and On-Chip Communication and Networks-on-Chip
DescriptionDeep learning techniques have been shown to achieve superior performance on several arbitration tasks in computer hardware. However, these techniques cannot be directly implemented in hardware because of the prohibitive area and latency overhead. In this work, we propose a novel methodology to automatically "distill" the arbitration logic from simulation traces. We leverage tree-based models as a bridge to convert deep learning models to logic, and present a case study on a network-on-chip port arbitration task. The generated arbitration logic achieves significant reduction in average packet latency compared with the baselines.