Publication | Closed Access
Configuration management in multi-context reconfigurable systems for simultaneous performance and power optimizations
21
Citations
7
References
2000
Year
EngineeringEnergy EfficiencyPower Optimization (Eda)Computer ArchitectureEnergy OptimizationSystems EngineeringParallel ComputingPower-aware SoftwarePower-aware ComputingComputer EngineeringConfiguration ManagementConfiguration LatencyComputer ScienceReconfigurable ArchitecturePower ConsumptionReconfigurabilitySmart GridEnergy ManagementSimultaneous PerformanceMulti-context Reconfigurable SystemsPower-efficient Computing
In this paper, we present a novel solution to the problem of configuration management for multi-context reconfigurable systems targeting DSP applications, its goal being to minimize both, configuration latency and power consumption. We assume that this technique is applied within a larger compilation framework, which provides a scheduled task sequence of the considered application. Reconfiguration latency reduction is the first criteria to consider, and we prove that the optimal solution can be obtained in all cases. Secondly, power is optimized without affecting performance. The assumptions of the method are supported by the analysis of a mathematical model, and its effectiveness is demonstrated by some experiments.
| Year | Citations | |
|---|---|---|
Page 1
Page 1