000197772 001__ 197772
000197772 005__ 20190123024023.0
000197772 0247_ $$2doi$$a10.1109/TCAD.2014.2316094
000197772 022__ $$a0278-0070
000197772 02470 $$2ISI$$a000340528200007
000197772 037__ $$aARTICLE
000197772 245__ $$aOnline Energy-Efficient Task-Graph Scheduling for Multicore Platforms
000197772 269__ $$a2014
000197772 260__ $$aPiscataway$$bInstitute of Electrical and Electronics Engineers$$c2014
000197772 300__ $$a14
000197772 336__ $$aJournal Articles
000197772 520__ $$aNumerous Directed-Acyclic Graph (DAG) schedulers have been developed to improve the energy efficiency of various multi-core platforms. However, these schedulers make a priori assumptions about the relationship between the task dependencies, and they are unable to adapt online to the characteristics of each application without offline profiling data. Therefore, we propose a novel energy-efficient online scheduling solution for the general DAG model to address the two aforementioned problems. Our proposed scheduler is able to adapt at runtime to the characteristics of each application by making smart foresighted decisions, which take into account the impact of current scheduling decisions on the present and future deadline miss rates and energy efficiency. Moreover, our scheduler is able to efficiently handle execution with very limited resources by avoiding scheduling tasks that are expected to miss their deadlines and do not have an impact on future deadlines. We validate our approach against state-of-the-art solutions. In our first set of experiments, our results with the H.264 video decoder demonstrate that the proposed low-complexity solution for the general DAG model reduces the energy consumption by up to 15% compared to an existing sophisticated and complex scheduler that was specifically built for the H.264 video decoder application. In our second set of experiments, our results with different configurations of synthetic DAGs demonstrate that our proposed solution is able to reduce the energy consumption by up to 55% and the deadline miss rates by up to 99% compared to a second existing scheduling solution. Finally, we show that our DFM and scheduler have low complexities on a real mobile platform and we show that our solution is resilient to workload prediction errors by using different estimator accuracies.
000197772 6531_ $$ascheduling
000197772 6531_ $$aMPSoC
000197772 6531_ $$aSoC
000197772 6531_ $$adirected acyclic graph
000197772 6531_ $$apower management
000197772 6531_ $$aenergy efficiency
000197772 6531_ $$aembedded systems
000197772 6531_ $$aH.264 decoder
000197772 700__ $$0245383$$aKanoun, Karim$$g206311
000197772 700__ $$aMastronade, Nicholas
000197772 700__ $$0240268$$aAtienza Alonso, David$$g169199
000197772 700__ $$aVan der Schaar, Mihaela
000197772 773__ $$j33$$k8$$q1194-1207$$tIEEE Transactions on Computer Aided Design of Integrated Circuits and Systems
000197772 8564_ $$s2598325$$uhttps://infoscience.epfl.ch/record/197772/files/TCAD2014-06856301.pdf$$yPublisher's version$$zPublisher's version
000197772 909C0 $$0252050$$pESL$$xU11977
000197772 909CO $$ooai:infoscience.tind.io:197772$$pSTI$$particle$$qGLOBAL_SET
000197772 917Z8 $$x169199
000197772 917Z8 $$x169199
000197772 917Z8 $$x169199
000197772 937__ $$aEPFL-ARTICLE-197772
000197772 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000197772 980__ $$aARTICLE