arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.07450cs.ARcs.LG
收藏

流水线处理器动态频率调整的统一学习平台

A Unified Learning Platform for Dynamic Frequency Scaling in Pipelined Processors

University of Illinois at Chicago(伊利诺伊大学芝加哥分校)

Arash Fouman Ajirlou, Inna Partin-Vaisband

摘要:

提出了一种基于指令传播延迟动态调整时钟频率的机器学习设计框架。训练随机森林模型以利用当前操作类型、当前操作数和计算历史作为ML特征来实时分类传播延迟。训练的模型在Verilog中实现为基线处理器内的附加流水线阶段。改进后的系统在45 nm CMOS工艺的门级进行了仿真,采用粗粒度ML分类,速度提高了68%,能量降低了37%。95%的加速证明了更精细的粒度在额外的能源成本。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑