SonicFFT: A system architecture for ultrasonic-based FFT acceleration

Darayus Adil Patel, Viet Phuong Bui, Kevin Tshun Chuan Chai, Amit Lal, Mohamed M. Sabry Aly

Abstract: Fast Fourier Transform (FFT) is an essential algorithm for numerous scientific and engineering applications. It is key to implement FFT in a high-performance and energy-efficient manner. In this paper, we leverage the properties of ultrasonic wave propagation in silicon for FFT computation. We introduce SonicFFT: A system architecture for ultrasonic-based FFT acceleration. To evaluate the benefits of SonicFFT, a compact-model based simulation framework that quantifies the performance and energy of an integrated system comprising of digital computing components interfaced with an ultrasonic FFT accelerator has been developed. We also present mapping strategies to compute 2D FFT utilizing the accelerator. Simulation results show that SonicFFT achieves a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$2317\times$</tex> system-level energy-delay product benefits-a simultaneous <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$117.69\times$</tex> speedup and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$19.69\times$</tex> energy reduction-versus state-of-the-art baseline all-digital configuration.