A Machine Learning Pipeline Stage for Adaptive Frequency Adjustment
Arash Fouman Ajirlou, Inna Partin-Vaisband

TL;DR
This paper introduces a machine learning pipeline stage that adaptively adjusts processor clock frequency based on instruction propagation delays, improving speed and energy efficiency.
Contribution
It presents a novel ML-based pipeline stage for real-time frequency adjustment, implemented in hardware and tested in a 45 nm CMOS processor.
Findings
70% speedup with 30% energy reduction at coarse granularity
89% speedup with 15.5% energy reduction at finer granularity
Effective real-time delay classification using random forest in hardware
Abstract
A machine learning (ML) design framework is proposed for adaptively adjusting clock frequency based on propagation delay of individual instructions. A random forest model is trained to classify propagation delays in real time, utilizing current operation type, current operands, and computation history as ML features. The trained model is implemented in Verilog as an additional pipeline stage within a baseline processor. The modified system is experimentally tested at the gate level in 45 nm CMOS technology, exhibiting a speedup of 70% and energy reduction of 30% with coarse-grained ML classification. A speedup of 89% is demonstrated with finer granularities with 15.5% reduction in energy consumption.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
