FPGAs are being increasingly used in a wide variety of applications. While power optimization has been only of secondary importance in many FPGA applications, growing importance of leakage in FPGAs designed in 90nm and below makes it imperative to treat power optimization as a first class citizen. In this paper, we propose a leakage-saving technique for FPGAs that involves dividing the FPGA fabric into small regions and switching on/off the power supply to each region using a sleep transistor in order to conserve leakage energy. Specifically, the regions not used by the placed design are supply gated. Next, we present a new placement strategy to increase the number of regions that can be supply gated. Finally, the supply gating technique is extended to exploit idleness in different parts of the same design during different time periods. Our experiments with different region sizes using various commercial and academic designs indicate that the proposed optimization outperforms conventional placement, and reduces leakage power consumption significantly.

No abstract

While some leakage power reduction techniques require modification of process technology achieving savings at the fabrication stage, others are based on circuit-level optimizations and are applied at run-time. We focus our study on the latter kind and compare three techniques: Input Vector Control, Body Bias Control and Power Supply Gating. We determine their limits and benefits, in terms of the potential leakage reduction, performance penalty and area and power overhead. The importance of the 'minimum idle time' parameter, as an additional evaluation tool, is emphasized, as well as the feasibility of achieving Power Supply Gating at low levels of granularity. The obtained data supports the formulation of a comprehensive leakage reduction scheme, in which each technique is targeted for certain types of functional units and a given level of granularity depending on the incurred overhead cost and the obtainable savings.

In this paper, we present an algorithm for the minimization of total power consumption via multiple V DD assignment, multiple V TH assignment, device sizing and stack forcing, while maintaining performance requirements. These four power reduction techniques are properly encoded in genetic algorithm and evaluated simultaneously. The overhead imposed by the insertion of level converters is also taken into account. The effectiveness of each power reduction mechanism is verified, as are the combinations of different approaches. Experimental results are given for a number of 65 nm benchmark circuits that span typical circuit topologies, including inverter chains, SRAM decoders, multiplier and a 32bit carry adders. From the experimental results, we show that the combination of four low power techniques is the effective way to achieve low power budget.

No abstract