Energy-optimal dynamic voltage scaling in multicore platforms with reconfigurable power distribution network
2018
This work addresses a new problem of dynamic voltage scaling (DVS) in multicore platforms. We solve the multicore DVS problem, i.e., simultaneously scheduling execution of tasks assigned to cores and determining dynamically-varying voltage levels, with the objective of minimizing total energy consumption of the cores and voltage regulators (VRs) in the reconfigurable VR-to-core power distribution network (PDN) of platform while meeting the arrival/deadline constraint of tasks. Here, the key factors to be exploited for energy saving are (1) available voltage levels, (2) power conversion efficiency curve of VRs, and (3) turning on/off VRs. Specifically, we formulate the problem of task scheduling with the relation between factors 1, 2, and 3 into a linear programming problem and solve optimally in polynomial time.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
10
References
0
Citations
NaN
KQI