Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-7074
Main Title: ALUPower: Data Dependent Power Consumption in GPUs
Author(s): Lucas, Jan
Juurlink, Ben
Type: Conference Object
Language Code: en
Abstract: Existing architectural power models for GPUs count activities such as executing floating point or integer instructions, but do not consider the data values processed. While data value dependent power consumption can often be neglected when performing architectural simulations of high performance Out-of-Order (OoO) CPUs, we show that this approach is invalid for estimating the power consumption of GPUs. The throughput processing approach of GPUs reduces the amount of control logic and shifts the area and power budget towards functional units and register files. This makes accurate estimations of the power consumption of functional units even more crucial than in OoO CPUs. Using measurements from actual GPUs, we show that the processed data values influence the energy consumption of GPUs significantly. For example, the power consumption of one kernel varies between 155 and 257 Watt depending on the processed values. Existing architectural simulators are not able to model the influence of the data values on power consumption. RTL and gate level simulators usually consider data values in their power estimates but require detailed modeling of the employed units and are extremely slow. We first describe how the power consumption of GPU functional units can be measured and characterized using microbenchmarks. Then measurement results are presented and several opportunities for energy reduction by software developers or compilers are described. Finally, we demonstrate a simple and fast power macro model to estimate the power consumption of functional units and provide a significant improvement in accuracy compared to previously used constant energy per instruction models.
URI: https://depositonce.tu-berlin.de//handle/11303/7913
http://dx.doi.org/10.14279/depositonce-7074
Issue Date: 2016
Date Available: 5-Jun-2018
DDC Class: 004 Datenverarbeitung; Informatik
Subject(s): data dependent power
GPU
power modelling
Sponsor/Funder: EC/H2020/688759/EU/Low-Power Parallel Computing on GPUs 2/LPGPU2
License: http://rightsstatements.org/vocab/InC/1.0/
Proceedings Title: 2016 IEEE 24th International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS)
Publisher: IEEE
Publisher Place: New York
Publisher DOI: 10.1109/MASCOTS.2016.21
Page Start: 95
Page End: 104
EISSN: 2375-0227
ISBN: 978-1-5090-3432-1
Appears in Collections:FG Architektur eingebetteter Systeme » Publications

Files in This Item:
File Description SizeFormat 
lucas_juurlink_2016.pdf2.07 MBAdobe PDFThumbnail
View/Open


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