Using Machine Learning for predicting area and Firmware metrics of hardware designs from abstract specifications

Lorenzo Servadei, Elena Zennaro, Tobias Fritz, Keerthikumara Devarajegowda, Wolfgang Ecker, Robert Wille

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

Advancements of Machine Learning (ML) in the field of computer vision have paved the way for its potential application in many other fields. Researchers and Hardware domain experts are exploring possible applications of Machine Learning in optimizing many aspects of the Hardware development process. In this paper, we propose a novel approach for predicting area and multiple Firmware metrics of Hardware components from specifications. The flow uses an existing RTL generation framework for generating valid data samples that enable ML algorithms to train the learning models. The approach has been successfully employed to predict the area and Firmware measurements of real-life Hardware components such as Control and Status Register (CSR) interfaces, that are ubiquitous in embedded systems. With our method we are able to perform an estimation on the area of an Hardware component with more than 98% accuracy and 600x faster than the existing methods. In addition, we are able to rank the features according to their importance in final area estimations. Finally, we are as well able to predict with an accuracy of approx. 85% the size and the CPU running cycles of a Firmware program embedded on the same Hardware component. This method, as a whole, is an important approach towards an accurate and fast estimation in the context of Hardware/Software trade-off analysis.

Original languageEnglish
Article number102853
JournalMicroprocessors and Microsystems
Volume71
DOIs
StatePublished - Nov 2019

Keywords

  • Area estimation
  • Code generation
  • Design productivity
  • Machine Learning
  • Meta-modeling
  • Model-Driven-Architecture
  • Register interface

Fingerprint

Dive into the research topics of 'Using Machine Learning for predicting area and Firmware metrics of hardware designs from abstract specifications'. Together they form a unique fingerprint.

Cite this