Lookup NU author(s): Dr Fei Xia,
Dr Ashur Rafiev,
Dr Andrey Mokhov,
Professor Alexander Romanovsky,
Dr Rishad Shafik,
Professor Alex Yakovlev
This is the authors' accepted manuscript of an article that has been published in its final definitive form by IEEE Computer Society, 2017.
For re-use rights please refer to the publisher's terms and conditions.
Parallelization has been used to maintain a reasonable balance between energy consumption and performance in computing platforms especially in modern multi- and many-core systems. This paper studies the interplay between performance and energy, and their relationships with parallelization scaling in the context of the reliable operating region, focusing on the effectiveness of parallelization scaling in throughput-power tradeoffs. Theoretical and experimental explorations show that a meaningful cross-platform analysis of this interplay can be achieved using the proposed method of bi-normalization of the ROR. The concept of this interplay is captured in an online tool for finding optimal operating points.
Author(s): Xia F, Rafiev A, Aalsaud A, Al-Hayanni M, Davis J, Levine J, Mokhov A, Romanovsky A, Shafik R, Yakovlev A, Yang S
Publication type: Article
Publication status: Published
Journal: IEEE Computer Magazine
Online publication date: 01/08/2017
Acceptance date: 20/12/2016
Date deposited: 16/01/2017
ISSN (electronic): 0018-9162
Publisher: IEEE Computer Society
Data Source Location: http://dx.doi.org/10.17634/123238-2
Altmetrics provided by Altmetric