Please use this identifier to cite or link to this item:
For citation please use:
Main Title: Predictable GPUs Frequency Scaling for Energy and Performance
Author(s): Fan, Kaijie
Cosenza, Biagio
Juurlink, Ben
Type: Conference Object
Abstract: Dynamic voltage and frequency scaling (DVFS) is an important solution to balance performance and energy consumption, and hardware vendors provide management libraries that allow the programmer to change both memory and core frequencies. The possibility to manually set these frequencies is a great opportunity for application tuning, which can focus on the best applicationdependent setting. However, this task is not straightforward because of the large set of possible configurations and because of the multi-objective nature of the problem, which minimizes energy consumption and maximizes performance. This paper proposes a method to predict the best core and memory frequency configurations on GPUs for an input OpenCL kernel. Our modeling approach, based on machine learning, first predicts speedup and normalized energy over the default frequency configuration. Then, it combines the two models into a multi-objective one that predicts a Pareto-set of frequency configurations. The approach uses static code features, is built on a set of carefully designed microbenchmarks, and can predict the best frequency settings of a new kernel without executing it. Test results show that our modeling approach is very accurate on predicting extrema points and Pareto set for ten out of twelve test benchmarks, and discover frequency configurations that dominate the default configuration in either energy or performance.
Subject(s): frequency scaling
energy efficiency
Issue Date: 2019
Date Available: 18-Jun-2019
Language Code: en
DDC Class: 004 Datenverarbeitung; Informatik
Sponsor/Funder: DFG, 360291326, CELERITY: Innovative Modellierung für Skalierbare Verteilte Laufzeitsysteme
Proceedings Title: Proceedings of the 48th International Conference on Parallel Processing (ICPP 2019)
Publisher: Association for Computing Machinery (ACM)
Publisher DOI: 10.1145/3337821.3337833
ISBN: 978-1-4503-6295-5
TU Affiliation(s): Fak. 4 Elektrotechnik und Informatik » Inst. Technische Informatik und Mikroelektronik » FG Architektur eingebetteter Systeme
Appears in Collections:Technische Universität Berlin » Publications

Files in This Item:

Item Export Bar

Items in DepositOnce are protected by copyright, with all rights reserved, unless otherwise indicated.