Please note that User Registration has been temporarily disabled due to a recent increase in automated registrations. If anyone needs an account, please request one here: RequestAccount. Thanks for your patience!--Wmat (talk)
Please email User:Wmat if you experience any issues with the Request Account form.

Difference between revisions of "Asymmetric Scheduling"

From eLinux.org
Jump to: navigation, search
(Created page with "'''Adventures in (simulated) Asymmetric Scheduling''' - Pantelis Antoniou, Antoniou Consulting Asymmetric processing, spearheaded by ARM's big.LITTLE architecture, has been t...")
 
m (Prpplague moved page Asymmetric Schdeduling to Asymmetric Scheduling without leaving a redirect)
 
(No difference)

Latest revision as of 19:13, 18 February 2013

Adventures in (simulated) Asymmetric Scheduling - Pantelis Antoniou, Antoniou Consulting

Asymmetric processing, spearheaded by ARM's big.LITTLE architecture, has been touted as a method for solving both the power & performance problem of mobile devices. This architecture requires changes to core scheduling concepts, which are extremely difficult to debug and diagnose, especially since existing tools do not capture useful data for evaluating such a system. A brief overview of the proposed scheduling changes will be presented, with major focus on Paul Turner's load average patches. Methods of simulating an asymmetric system will be described. Additionally a portable process workload capturing method, based on perf, will be presented, i.e. one can capture traces from an Android based system and run it on a standard Linux box.