A Multi-Objective Perspective for Operator Scheduling Using Finegrained DVS Architectures

The stringent power budget of fine grained power managed digital integrated circuits have driven chipdesigners to optimize power at the cost of area anddelay, which were the traditional cost criteria forcircuit optimization. The emerging scenario motivates us to revisit the classical operator schedulingproblem under the availability of DVFS enabled functional units that can trade-off cycles with power.Westudy the design space defined due to this trade-off and present a branch-and-bound(B/B) algorithm toexplore this state space and report the pareto-optimal front with respect to area and power. The schedulingalso aims at maximum resource sharing and is able to attain sufficient area and power gains for complexbenchmarks when timing constraints are relaxed by sufficient amount. Experimental results show that thealgorithm that operates without any user constraint(area/power) is able to solve the problem for mostavailable benchmarks, and the use of power budgetor area budget constraints leads to significantperformance gain