Dynamic frequency scaling: Difference between revisions

Revision as of 19:50, 16 April 2020

Revision as of 08:56, 9 June 2020

Line 3:

{{Use dmy dates|date=January 2014}}

'''Dynamic frequency scaling''' (also known as '''CPU throttling''') is a technique in [[computer architecture]] whereby the [[Clock rate|frequency]] of a microprocessor can be automatically adjusted "on the fly" depending on the actual needs, to [[Power management integrated circuit|conserve power]] and reduce the amount of heat generated by the chip. Dynamic frequency scaling helps preserve battery on mobile devices<ref>"[https://www.academia.edu/4186102/A_survey_of_techniques_for_improving_energy_efficiency_in_embedded_computing_systems A survey of techniques for improving energy efficiency in embedded computing systems]", IJCAET, 2014 </ref> and decrease cooling cost and noise on [[Quiet PC|quiet computing settings]], or can be useful as a security measure for overheated systems (e.g. after poor [[overclocking]]). Dynamic frequency scaling is used in all ranges of computing systems, ranging from mobile systems to data centers<ref>"[https://www.academia.edu/6982393/Power_Management_Techniques_for_Data_Centers_A_Survey Power Management Techniques for Data Centers: A Survey]", ORNL Technical Report, 2014 </ref> to reduce the power at the times of low workload.

Throttling is also known as "automatic [[underclocking]]". Automatic [[overclocking]] it also technically a form of dynamic frequency scaling, but it's relatively new and not discussed.

== Functioning ==