DocumentCode
3738290
Title
Energy-efficient computing from systems-on-chip to micro-server and data centers
Author
Paul Bogdan;Siddharth Garg;Umit Y. Ogras
Author_Institution
Dept. of Electrical Engineering, University of Southern California, Los Angeles, 90089-5720, USA
fYear
2015
Firstpage
1
Lastpage
6
Abstract
Energy-efficiency has become a key metric for a wide range of computing platforms from low power mobile processors all the way up to data centers. Utilizing the many cores and architectural heterogeneity have been shown to be very effective in increasing the energy efficiency, which implies more performance under the same or lower power consumption budgets. Despite the obvious differences between low power processors, servers and data centers, there is also a common mathematical foundation applicable across different domains. This paper overviews cutting-edge aspects of energy-efficient design of next-generation manycore systems and highlights future research and development challenges.
Keywords
"Servers","Mathematical model","Optimization","Power demand","Thermal management","Program processors","Processor scheduling"
Publisher
ieee
Conference_Titel
Green Computing Conference and Sustainable Computing Conference (IGSC), 2015 Sixth International
Type
conf
DOI
10.1109/IGCC.2015.7393686
Filename
7393686
Link To Document