2019 · 35 citations · 27 references
EngineeringComputer EngineeringComputer ScienceHardware-software Co-designLow-power DesignSystem-on-chip DesignAccelerator ArchitectureApproximation AlgorithmsHardware AccelerationLow-power Digital Circuit DesignPower OptimizationPower-aware DesignApproximate ComputingApproximate Computing For Power ReductionArithmetic Unit DesignEnergy-efficient ArchitectureEnergy-efficient Hardware AccelerationMultiplier DesignMultipliersPower-efficient Design
Approximate computing appears as an emerging and promising solution for energy-efficient system designs, exploiting the inherent error-tolerant nature of various applications. In this paper, targeting multiplication circuits, i.e., the energy-hungry counterpart of hardware accelerators, an extensive exploration of the error--energy trade-off, when combining arithmetic-level approximation techniques, is performed for the first time. Arithmetic-aware approximations deliver significant energy reductions, while allowing to control the error values with discipline by setting accordingly a configuration parameter. Inspired from the promising results of prior works with one configuration parameter, we propose 5 hybrid design families for approximate and energy-friendly hardware multipliers, consisting of two independent parameters to tune the approximation levels. Interestingly, the resolution of the state-of-the-art Pareto diagram is improved, giving the flexibility to achieve better energy gains for a specific error constraint imposed by the system. Moreover, we outperform prior works in the field of approximate multipliers by up to 60% energy reduction, and thus, we define the new Pareto front.
27
Neural Acceleration for General-Purpose Approximate Programs
Hadi Esmaeilzadeh, Adrian Sampson, Luís Ceze et al. · 2012 · 624 citations
Design and Analysis of Approximate Compressors for Multiplication
Amir Momeni, Jie Han, Paolo Montuschi et al. · IEEE Transactions on Computers · 2014 · 620 citations · Full text