Experimenting with runtime and energy tradeoffs in high-performance computing
by G. Uma Maheswari; S. Subha
Progress in Industrial Ecology, An International Journal (PIE), Vol. 12, No. 1/2, 2018

Abstract: In a given organisation or society, energy dependence increases rapidly due to shipping, transportation, and even food production. This dependency generally results in high costs and pollution, which threatens to disrupt our ecosystem. At this time, the earth is rapidly approaching a point of no return that requires international cooperation. In the following decade, reliance on effective energy-computing designs will become imperative, as power and cooling begin to cause restrictions on microchip clock speeds. Therefore, personal computer organisations are fast expanding on-chip parallelism to expedite execution. Combined operations are the most fundamental part of a transmission in shared and distributed parallel applications. In this paper, the tradeoffs between energy, memory, and runtime of various algorithms that accomplish such operations are investigated. The influence of aggregate transmissions on the execution of parallel calculation, specifically, is shown. A nondirect association with execution seen in the energy required is also presented. The best streamlining between runtime, energy, and memory tradeoff is demonstrated and a better result in the energy-effective execution of calculations is displayed.

Online publication date: Thu, 25-Oct-2018

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the Progress in Industrial Ecology, An International Journal (PIE):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com