Empirical method based on neural networks for analog power modeling
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
| Hi-index | 0.00 |
The increasing popularity of low power computing drivesthe need for increasing battery life-time by power-optimizingapplication programs. This requires a tool capableof providing a system-level energy model. We present amethodology for simulating and profiling energy consumedby software applications running on computing systems.The uniqueness of our framework lies in its ability to captureat a fine granularity, power behavior of the softwareexecuting on the system as well as of each of the hardwarecomponents in the system and its applicability to a wide varietyof computing systems. We demonstrate our work on areal world platform, the Itsy, a handheld computer developedby Compaq's Western Research Labs.