2009 · 14 citations · 12 references
ArchitectureComputer EngineeringDesign OptimizationLow-power DesignOptimizationEvolutionary OptimizationGenetic AlgorithmsMulti-objective Design OptimizationMulti-objective OptimizationMultiobjective OptimizationPerformance OptimizationMulti-objective Evolutionary AlgorithmsMulti-objective Evolutionary ComputationMulti-objective Evolutionary OptimizationMultiobjective Evolutionary AlgorithmsPower ConsumptionPower Consumption OptimizationSolution Space DesignSolution Space Exploration
Designing an optimal NoC for a particular application requires the specification of a large set of configuration parameters leading to a wide solution space. It has been shown that IP mapping is one of the most critical parameters in NoC design, strongly influencing the SoC performance. IP mapping has been solved using single and multi-objective optimization algorithms. In this paper we propose the use of a multi-objective adaptive immune algorithm (MAIA), an evolutionary approach to solve the NoC mapping problem. Latency and power consumption were adopted as the target multi-objective functions. To compare the efficiency of our approach, our results were compared with those of the genetic and branch-and-bound multi-objective mapping algorithms. We tested 4 well-known benchmarks and 2 real SoC applications (MPEG-4 decoder and VOPD). The experimental results showed that the MAIA improves power consumption and latency respectively in almost 58% and 57% compared to the branch-and-bound approach and 40% and 50% compared to genetic approach.
12
QNoC: QoS architecture and design process for network on chip
Evgeny Bolotin, Israel Cidon, Ran Ginosar et al. · Journal of Systems Architecture · 2003 · 540 citations