Abstract | ||
---|---|---|
Numerous Directed-Acyclic Graph (DAG) schedulers have been developed to improve the energy efficiency of various multi-core systems. However, the DAG monitoring modules proposed by these schedulers make a priori assumptions about the workload and relationship between the task dependencies. Thus, schedulers are limited to work on a limited subset of DAG models. To address this problem, we propose a unified online DAG monitoring solution independent from the connected scheduler and able to handle all possible DAG models. Our novel low-complexity solution processes online the DAG of the application and provides relevant information about each task that can be used by any scheduler connected to it. Using H.264/AVC video decoding as an illustrative application and multiple configurations of complex synthetic DAGs, we demonstrate that our solution connected to an external simple energy-efficient scheduler is able to achieve significant improvements in energy-efficiency and deadline miss rates compared to existing approaches. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ASPDAC.2014.6742974 | ASP-DAC |
Keywords | Field | DocType |
processor scheduling,power aware computing,unified online directed acyclic graph flow manager,dag schedulers,complex synthetic dags,task dependency,h.264/avc video decoding,video coding,low-complexity solution,directed graphs,dag monitoring modules,multicore scheduler system,external simple energy-efficient scheduler,decoding,parallel processing | Efficient energy use,Computer science,Workload,Flow (psychology),A priori and a posteriori,Directed graph,Real-time computing,Directed acyclic graph,Decoding methods,Multi-core processor,Distributed computing | Conference |
ISSN | Citations | PageRank |
2153-6961 | 1 | 0.36 |
References | Authors | |
12 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Karim Kanoun | 1 | 17 | 2.27 |
David Atienza | 2 | 2219 | 149.60 |
Nicholas Mastronarde | 3 | 240 | 26.93 |
Mihaela Van Der Schaar | 4 | 3968 | 352.59 |