Performance, Power, and Energy-Efficiency Impact Analysis of Compiler Optimizations on the SPEC CPU 2017 Benchmark Suite

Author(s):  
Norbert Schmitt ◽  
James Bucek ◽  
John Beckett ◽  
Aaron Cragin ◽  
Klaus-Dieter Lange ◽  
...  
2012 ◽  
Vol 430-432 ◽  
pp. 1786-1790 ◽  
Author(s):  
Shu Fang Li

The energy efficiency experiment of electric light is implemented according to the lighting design of the physical training venues. In the experiment, the corresponding illumination, power and energy efficiency ratio of the commonly used high pressure sodium lamp and metal halide lamp which work under the voltage ranging from 187V to 234V are experimentally measured and the lighting effect characteristics of the two kinds of electric light sources compared, proving that the high pressure sodium light source should be employed in the training venue for physical education of universities.


Computation ◽  
2020 ◽  
Vol 8 (1) ◽  
pp. 20 ◽  
Author(s):  
Enrico Calore ◽  
Alessandro Gabbana ◽  
Sebastiano Fabio Schifano ◽  
Raffaele Tripiccione

In the last years, the energy efficiency of HPC systems is increasingly becoming of paramount importance for environmental, technical, and economical reasons. Several projects have investigated the use of different processors and accelerators in the quest of building systems able to achieve high energy efficiency levels for data centers and HPC installations. In this context, Arm CPU architecture has received a lot of attention given its wide use in low-power and energy-limited applications, but server grade processors have appeared on the market just recently. In this study, we targeted the Marvell ThunderX2, one of the latest Arm-based processors developed to fit the requirements of high performance computing applications. Our interest is mainly focused on the assessment in the context of large HPC installations, and thus we evaluated both computing performance and energy efficiency, using the ERT benchmark and two HPC production ready applications. We finally compared the results with other processors commonly used in large parallel systems and highlight the characteristics of applications which could benefit from the ThunderX2 architecture, in terms of both computing performance and energy efficiency. Pursuing this aim, we also describe how ERT has been modified and optimized for ThunderX2, and how to monitor power drain while running applications on this processor.


2018 ◽  
Vol 64 ◽  
pp. 08007
Author(s):  
Corredor Lesme ◽  
Avendaño José ◽  
Bello Robert ◽  
Redondo Álvaro ◽  
Calle José ◽  
...  

Process industries located in emerging economies have relative low levels of production to similar ones located in developed countries, this fact influences the implementation feasibility of cogeneration and/or tri-generation systems that allow a substantial increase in the plant global energy efficiency. In this paper, an energy and economic analysis of several alternatives of cogeneration was done for a company located in Barranquilla (Colombia, South America) that produces vegetable oils and derivatives and its energy matrix is approximately 90% thermal and 10% electric. In this investigation two type of analysis were done, both supported by process simulation software, these are: 1) Taking the plant as the control volume and evaluating the entire electrical demand supply with natural gas engine and turbine – generator, plus exhaust gases heat recovery for refrigeration and/or preheating of thermal oil or water in boilers. 2) As an energy-industrial district, where the company takes advantage of the residual heat of a gas turbine and sells the excess of electrical power to nearby plants, a concept introduced by the authors as Sustainable Energetic Industrial District in Emerging Economies (SEIDEE). The input variable considered for this analysis was electric demand which restricts the technology implementation. It was found that the investment return period is notably lengthy when the thermal machine supplies the electric power demanded by the industrial plant. This period is considerably reduced when the SEIDEE concept is implemented, this period reduction is between 57% and 65%.


2011 ◽  
Vol 40 (5) ◽  
pp. 1238-1243 ◽  
Author(s):  
Yonghua Cai ◽  
Jinsheng Xiao ◽  
Wenyu Zhao ◽  
Xinfeng Tang ◽  
Qingjie Zhang

2014 ◽  
Vol 9 (1) ◽  
pp. 48-59
Author(s):  
Ismael Seidel ◽  
André Beims Bräscher ◽  
Bruno George De Moraes ◽  
Marcio Monteiro ◽  
José Luis Güntzel

As the number of pixels per frame tends to increase in new high definition video coding standards such as HEVC and VP9, pel decimation appears as a viable means of increasing the energy efficiency of Sum of Absolute Differences (SAD) calculation. First, we analyze the quality costs of pel decimation using a video coding software. Then we present and evaluate two VLSI architectures to compute the SAD of 4x4 pixel blocks: one that can be configured with 1:1, 2:1 or 4:1 sampling ratios and a non-configurable one, to serve as baseline in comparisons. The architectures were synthesized for 90nm, 65nm and 45nm standard cell libraries assuming both nominal and Low-Vdd/High-Vt (LH) cases for maximum and for a given target throughput. The impacts of both subsampling and LH on delay, power and energy efficiency are analyzed. In a total of 24 syntheses, the 45nm/LH configurable SAD architecture synthesis achieved the highest energy efficiency for target throughput when operating in pel decimation 4:1, spending only 2.05pJ for each 4×4 block. This corresponds to about 13.65 times less energy than the 90nm/nominal configurable architecture operating in full sampling mode and maximum throughput and about 14.77 times less than the 90nm/nominal non-configurable synthesis for target throughput. Aside the improvements achieved by using LH, pel decimation solely was responsible for energy reductions of 40% and 60% when choosing 2:1 and 4:1 subsampling ratios, respectively, in the configurable architecture. Finally, it is shown that the configurable architecture is more energy-efficient than the non-configurable one.


Sign in / Sign up

Export Citation Format

Share Document