Abstract
The chances to reach Exascale or Ultrascale Computing are strongly connected with the problem of the energy consumption for processing applications. For physical and economical reasons, the energy consumption has to be reduced significantly to make Ultrascale Computing possible. The research efforts towards energy-saving mechanisms of the hardware have already made energy-aware hardware systems available. However, to achieve a strong energy reduction, hardware mechanisms must be complemented with new energy-efficient software that can exploit them so that the foreseen energy savings actually result. In the software area, there also exist a multitude of research approaches towards energy saving, often concentrating either on the system software level or the application organization level, reflecting the expertise of the corresponding research group. The challenge of reducing the energy consumption dramatically to make Ultrascale Computing possible is so ambitious that a concerted action combining research efforts through all the software levels seems reasonable. In this article, we discuss the current research efforts and results related to energy efficiency in the diverse areas of software. We conclude with open problems and questions concerning energy-related techniques with an emphasis on the application or algorithmic side.
Highlights
The performance of high-end HPC systems has been increased roughly by a factor of 1000 in each of the last two decades
Of power-aware software for the entire software stack, including operating systems, compilers, applications and algorithms. This second direction is the topic of this survey article, in which we summarize important contributions towards energy reduction that can be provided by the system software or the programming model and discuss how these contributions can be used for the construction of energy-efficient algorithms and applications
If the execution time of the implementation variants depends on characteristics of the specific input, offline autotuning has to be replaced by online autotuning, where applications are able to monitor and automatically tune themselves to optimize a particular objective, as in the case shown for ordinary differential equations in [55]
Summary
The performance of high-end HPC systems has been increased roughly by a factor of 1000 in each of the last two decades. With the world’s most powerful systems already well past the Petaflop/s level in 2014, a projection of this trend leads to the prediction that by 2022, Exascale computing will be possible Progress towards this goal is threatened by energy issues because, based on the current technology, systems with Exascale performance would use excessive amounts of energy (e.g. Tianhe-2, a 33 PFlops system, needs about 18 MW). Of power-aware software for the entire software stack, including operating systems, compilers, applications and algorithms This second direction is the topic of this survey article, in which we summarize important contributions towards energy reduction that can be provided by the system software or the programming model and discuss how these contributions can be used for the construction of energy-efficient algorithms and applications. The final section concludes the article with a discussion of important research directions that are crucial for reaching energy efficiency in algorithms
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
