Machine learning techniques to support many-core resource management: Challenges and opportunities

Martin Rapp, Hussam Amrouch, Marilyn Wolf, Jorg Henkel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

Resource management in many-core processors, housing tens to hundreds of cores on a single die, becomes more and more challenging due to the ever-increasing number of possible management decisions (e.g., task mapping). Machine learning (ML) techniques emerge as promising solutions to support resource management algorithms in taking the best decisions due to their adaptability. However, there are several challenges with ML-based solutions. We discuss two key challenges in detail. Firstly, ML-based techniques often suffer from high computational complexity for the inference at run-time-which is especially critical when it comes to the embedded system domain. Secondly, employing ML techniques as a 'black box' may result in deriving models that fail in reflecting the reality.We take a task migration technique that maximizes the performance of a thermally-constrained many-core as a case study. This technique selects the migration to execute next with the support of a neural network (NN) that predicts the performance impact of a migration. We demonstrate the abovementioned challenges in this case study and discuss potential remedies. To lower the run-time overhead, we discuss overhead-aware design of the NN and using already existing accelerators in smartphone SoCs. Finally we also demonstrate how existing domain knowledge can be introduced into the models to ensure that models are consistent with the reality and experimentally show the potential.

Original languageEnglish
Title of host publication2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728157580
DOIs
StatePublished - Sep 2019
Externally publishedYes
Event1st ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2019 - Canmore, Canada
Duration: 3 Sep 20194 Sep 2019

Publication series

Name2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019

Conference

Conference1st ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2019
Country/TerritoryCanada
CityCanmore
Period3/09/194/09/19

Keywords

  • Accelerator
  • Gray Box Modeling
  • Machine Learning
  • Neural Network Design
  • Resource Management

Fingerprint

Dive into the research topics of 'Machine learning techniques to support many-core resource management: Challenges and opportunities'. Together they form a unique fingerprint.

Cite this