ARLGJun 12, 2020

A Unified Learning Platform for Dynamic Frequency Scaling in Pipelined Processors

arXiv:2006.07450v1
Originality Incremental advance
AI Analysis

This addresses energy efficiency and performance in processor design, but it is incremental as it builds on existing ML methods for hardware optimization.

The paper tackles dynamic frequency scaling in pipelined processors by proposing a machine learning framework that classifies propagation delays to adjust clock frequency, achieving a 68% speed-up and 37% energy reduction in simulations.

A machine learning (ML) design framework is proposed for dynamically 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 simulated at the gate-level in 45 nm CMOS technology, exhibiting a speed-up of 68% and energy reduction of 37% with coarse-grained ML classification. A speed-up of 95% is demonstrated with finer granularities at additional energy costs.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes