1,720,988 research outputs found
Quasi-Static Voltage Scaling for Energy Minimization with Time Constraints
No full textSupply voltage scaling and adaptive body-biasing are important tech-niques that help to reduce the energy dissipation of embedded systems. This is achieved by dynamically adjusting the voltage and performance settings according to the application needs. In order to take full ad-vantage of slack that arises from variations in the execution time, it is important to recalculate the voltage (performance) settings during run-time, i.e., online. However, voltage scaling (VS) is computationally ex-pensive, and thus significantly hampers the possible energy savings. To overcome the online complexity, we propose a quasi-static voltage scal-ing scheme, with a constant online time complexity O(1). This allows to increase the exploitable slack as well as to avoid the energy dissipated due to online recalculation of the voltage settings. We conduct several experiments that demonstrate the advantages of the proposed technique over the previously published voltage scaling approaches
Hibernus: sustaining computation during intermittent supply for energy-harvesting systems
Get PDFA key challenge to the future of energy-harvesting systems is the discontinuous power supply that is often generated. We propose a new approach, Hibernus, which enables computation to be sustained during intermittent supply. The approach has a low energy and time overhead which is achieved by reactively hibernating: saving system state only once, when power is about to be lost, and then sleeping until the supply recovers. We validate the approach experimentally on a processor with FRAM nonvolatile memory, allowing it to reactively hibernate using only energy stored in its decoupling capacitance. When compared to a recently proposed technique, the approach reduces processor time and energy overheads by 76-100% and 49-79% respectively
aEqualized: A novel routing algorithm for the Spidergon Network On Chip
No full textWe present the aEqualized routing algorithm: a novel algorithm for the Spidergon Network on Chip. AEqualized combines the well known aFirst and aLast algorithms proposed in literature obtaining an optimized use of the channels of the network. This optimization allows to reduce the number of channels actually implemented on the chip while maintaining similar performances achieved by the two basic algorithms. In the second part of this paper, we propose a variation on the Spidergon's router architecture that enhances the performance of the network especially when the aEqualized routing algorithm is adopted
- …
