Energy-Quality Scalable Design Space Exploration of Approximate FFT Hardware Architectures
- 28 July 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 69 (11) , 4524-4534
Abstract
This paper presents a comprehensive design space exploration for boosting energy efficiency of a fast Fourier transform (FFT) VLSI accelerator, exploiting several approximate multipliers (AxM) combined with approximate adder (AxA) circuits. The FFT hardware herein presented consists of a fixed-point sequential architecture using a radix-2 butterfly with decimation in time. We explore a set of AxMs – namely Dynamic Range Unbiased (DRUM), Rounding-based Approximate (RoBA), leading one Bit-based Approximate (LoBA), and Truncated approach – jointly with the LOA, ETA-I, CopyA, CopyB, Trunc0, Trunc1 approximate adders. The approximate arithmetic operators are used in the butterfly kernel with exploration of the approximation levels (for the ${L}$ and ${K}$ least-significant bits, respectively, for the AxM and AxA), aiming at discovering the most energy-efficient configuration under a design-time QoR constraint. The mean square error and peak signal-to-noise ratio metrics define which approximate levels combining ${L}$ and ${K}$ variations will enable the FFT to process signals to generate spectrograms without significant losses. Our results show that the LoBA multiplier with $L$ =8 together with the LOA, Trunc1 and Trunc0, at different approximation levels, provide most energy savings with controllable quality degradation, presenting a minimum decrease of 20.2% in power dissipation without degrading the spectrogram generation quality.Keywords
Funding Information
- CNPq
- CAPES
- FAPERGS Research and Development
This publication has 49 references indexed in Scilit:
- A power-efficient imprecise radix-4 multiplier applied to high resolution audio processing2016
- Architectural-space exploration of approximate multipliers2016
- Energy-Efficient Reduce-and-Rank Using Input-Adaptive ApproximationsIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2016
- RoBA Multiplier: A Rounding-Based Approximate Multiplier for High-Speed yet Energy-Efficient Digital Signal ProcessingIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2016
- DRUM: A Dynamic Range Unbiased Multiplier for approximate applications2015
- Design of power efficient butterflies from Radix-2 DIT FFT using adder compressors with a new XOR gate topologyAnalog Integrated Circuits and Signal Processing, 2012
- A Low-Cost 256-Point FFT Processor for Portable Speech and Audio Applications2007
- A Low Multiplier and Multiplication Costs 256-point FFT Implementation with Simplified Radix-24 SDF Architecture2006
- Real-valued fast Fourier transform algorithmsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987
- An algorithm for the machine calculation of complex Fourier seriesMathematics of Computation, 1965