Basic Block energy prediction using machine learning
methods

Siozos, Theodoros; Σιώζος, Θεόδωρος

dc.contributor.author	Siozos, Theodoros	en
dc.contributor.author	Σιώζος, Θεόδωρος	el
dc.date.accessioned	2023-05-19T06:46:03Z
dc.date.available	2023-05-19T06:46:03Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/57721
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.25418
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/gr/	*
dc.subject	Μηχανική μάθηση	el
dc.subject	Νευρωνικά δίκτυα	el
dc.subject	Κατανάλωση ενέργειας	el
dc.subject	Στοιχειώδης δομή κώδικα	el
dc.subject	Παρεμβολή	el
dc.subject	Neural networks	en
dc.subject	Machine learning	en
dc.subject	Basic block	en
dc.subject	Energy consumption	en
dc.subject	Regression models	en
dc.title	Basic Block energy prediction using machine learning methods	en
heal.type	bachelorThesis
heal.classification	Computer Science	en
heal.language	el
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2023-03-22
heal.abstract	Over the past few decades, there has been a significant effort to find energy-efficient solutions due to climate change. One approach to reducing energy consumption is to minimize the energy consumption of code, particularly for large-scale scenarios such as data centers. Basic block energy consumption prediction is an essential step in creating energy-optimized compilers and schedulers that can significantly decrease code energy consumption. However, this task poses several challenges due to its fine granularity and hardware-specific sensors. To address these challenges, this research investigates the efficiency of machine learning approaches in basic block energy consumption prediction. A basic block energy measurement dataset created in previous research was used for training several machine learning architectures, including both traditional regression methods and deep neural network architectures. Sophisticated code representation techniques were implemented to enable this task, given the nature of the basic block as a sequence of Assembly instructions. In particular, sequential neural networks, such as LSTMs, were used to achieve high accuracy in predicting basic block energy consumption, while traditional methods like linear regression and support vector machines proved to perform great as well. The final best-performing models were able to predict basic block energy consumption with a Mean Absolute Error fluctuating around 0.25 $(61\mu J)$ for energy measurements with standard deviation around 0.7 $(61\mu J)$. Despite these promising results, the research has discovered that basic block energy consumption is highly correlated with its preceding basic blocks, therefore the findings were deteriorated due to the lack of data for basic blocks sequences. The final contributions of this research can be summed up as: an extensive empirical study of machine learning for energy consumption prediction, the realization that basic block energy prediction necessitates contextual information for preceding basic blocks, the recognition that whole-program error is an inadequate measure for evaluating a basic block dataset, and lastly, an informed outline of future work.	en
heal.advisorName	Σούντρης, Δημήτριος	el
heal.committeeMemberName	Σούντρης, Δημήτριος	el
heal.committeeMemberName	Τσανάκας, Παναγιώτης	el
heal.committeeMemberName	Ξύδης, Σωτήριος	el
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών. Τομέας Τεχνολογίας Πληροφορικής και Υπολογιστών	el
heal.academicPublisherID	ntua
heal.numberOfPages	96 σ.	el
heal.fullTextAvailability	false