Abstract
The Fast Fourier Transform (FFT) is required for chemistry, weather, defense, and signal processing for seismic exploration and radio astronomy. It is communication-bound, making supercomputers thousands of times slower at FFTs then at dense linear algebra. The key to accelerating FFTs is to minimize bits per datum without sacrificing accuracy. The 16-bit fixed point and IEEE float type lack sufficient accuracy for 1024- and 4096-point FFTs of data from analog-to-digital converters. We show that the 16-bit posit, with higher accuracy and larger dynamic range, can perform FFTs so accurately that a forward-inverse FFT restores the original signal perfectly. “Reversible” FFTs with posits are lossless, eliminating the need for 32-bit or higher precision. Similarly, 32-bit posit FFTs can replace 64-bit float FFTs for many HPC tasks. Speed, energy efficiency, and storage costs can thus be improved by 2\(\times \) for a broad range of HPC workloads.
Supported by organization A*STAR and NSCC Singapore.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bouziane, R., et al.: Optimizing FFT precision in optical OFDM transceivers. IEEE Photonics Technol. Lett. 23(20), 1550–1552 (2011). https://doi.org/10.1109/LPT.2011.2164059
Buddhiram, C.R., et al.: Parameterized posit arithmetic generator (2018). Submitted to ICCD 2018
Chang, W.H., Nguyen, T.Q.: On the fixed-point accuracy analysis of FFT algorithms. IEEE Trans. Signal Process. 56(10), 4673–4682 (2008). https://doi.org/10.1109/TSP.2008.924637
Chang, W.H., Nguyen, T.Q.: On the fixed-point accuracy analysis of FFT algorithms. IEEE Trans. Signal Process. 56(10), 4673–4682 (2008)
Chen, J., Al-Ars, Z., Hofstee, H.P.: A matrix-multiply unit for posits in reconfigurable logic using (Open) CAPI. ACM (2018)
Chung, S.Y.: Provably correct posit arithmetic with fixed-point big integer. ACM (2018)
Cochran, W.T., et al.: What is the fast Fourier transform? Proc. IEEE 55(10), 1664–1674 (1967). https://doi.org/10.1109/PROC.1967.5957
Cooley, J.W., Tukey, J.W.: An algorithm for the machine calculation of complex Fourier series. Math. Comput. 19, 297–301 (1965)
Duhamel, P., Hollmann, H.: ‘Split radix’ FFT algorithm. Electron. Lett. 20(1), 14–16 (1984). https://doi.org/10.1049/el:19840012
Goldberg, D.: What every computer scientist should know about floating-point arithmetic
Good, I.: The interaction algorithm and practical Fourier analysis. J. Roy. Stat. Soc. Ser. B (Methodol.) 361–372 (1958)
Good, I.: The interaction algorithm and practical Fourier analysis: an addendum. J. Roy. Stat. Soc. Ser. B (Methodol.) 372–375 (1960)
Gustafson, J.L.: The End of Error: Unum Computing. Chapman & Hall/CRC Computational Science, CRC Press (2015)
Gustafson, J.L.: Posit arithmetic (2017). Mathematica notebook
Gustafson, J.L., Yonemoto, I.: Beating floating point at its own game: posit arithmetic. Supercomput. Front. Innov. 4(2) (2017). https://doi.org/10.14529/jsfi170206
Gustafson, J.L., Yonemoto, I.: Beyond floating point: next generation computer arithmetic (2017). https://www.youtube.com/watch?v=aP0Y1uAA-2Y
Hauser, J.R.: Berkeley SoftFloat (2018). http://www.jhauser.us/arithmetic/SoftFloat.html
Hutter, J., Iannuzzi, M., Schiffmann, F., VandeVondele, J.: CP2K: atomistic simulations of condensed matter systems. Wiley Interdisc. Rev.: Comput. Mol. Sci. 4(1), 15–25 (2014)
Kahan, W.: IEEE standard 754 for binary floating-point arithmetic. Lect. Notes Status EEE 754(94720–1776), 11 (1996)
Komatitsch, D., Tromp, J.: Spectral-element simulations of global seismic wave propagation-I. Validation. Geophys. J. Int. 149(2), 390–412 (2002). https://doi.org/10.1046/j.1365-246X.2002.01653.x
Komatitsch, D., Tromp, J.: Spectral-element simulations of global seismic wave propagation–II. Three-dimensional models, oceans, rotation and self-gravitation. Geophys. J. Int. 150(1), 303–318 (2002)
Kulisch, U.W., Miranker, W.L.: The arithmetic of the digital computer: a new approach. SIAM Rev. 28(1), 1–40 (1986). https://doi.org/10.1137/1028001, http://dx.doi.org/10.1137/1028001
Langroudi, S.H.F., Pandit, T.N., Kudithipudi, D.: Deep learning inference on embedded devices: fixed-point vs posit. In: Energy Efficiency Machine Learning and Cognitive Computing for Embedded Applications (EMC\(^{2}\)) (2018). https://sites.google.com/view/asplos-emc2/program
Lehoczky, Z., Szabo, A., Farkas, B.: High-level.NET software implementations of unum type I and posit with simultaneous FPGA implementation using Hastlayer. ACM (2018)
Li, M., et al.: Evaluation of variable precision computing with variable precision FFT implementation on FPGA. In: 2016 International Conference on Field-Programmable Technology (FPT), pp. 299–300 (2016). https://doi.org/10.1109/FPT.2016.7929560
Lindstrom, P., Lloyd, S., Hittinger, J.: Universal coding of the reals: alternatives to IEEE floating point. In: Conference for Next Generation Arithmetic. ACM (2018)
Mallasén, D., Murillo, R., Barrio, A.A.D., Botella, G., Piñuel, L., Prieto-Matias, M.: Percival: open-source posit RISC-V core with quire capability. IEEE Trans. Emerg. Top. Comput. 10(3), 1241–1252 (2022). https://doi.org/10.1109/TETC.2022.3187199
Oppenheim, A.V., Schafer, R.W.: Discrete-Time Signal Processing, Second Edition. Prentice-Hall (1998)
Podobas, A.: Accelerating POSIT-based computations using FPGAs and OpenCL (2018). https://posithub.org/conga/2018/techprogramme#invitedtalk2
Rader, C., Brenner, N.: A new principle for fast Fourier transformation. IEEE Trans. Acoust. Speech Signal Process. 24(3), 264–266 (1976). https://doi.org/10.1109/TASSP.1976.1162805
Skamarock, W.C., Klemp, J.B., Dudhia, J.: Prototypes for the WRF (weather research and forecasting) model. In: Preprints, Ninth Conf. Mesoscale Processes, J11–J15, American Meteorological Society, Fort Lauderdale, FL (2001)
Soni, M., Kunthe, P.: A General comparison of FFT algorithms (2011). http://pioneerjournal.in/conferences/tech-knowledge/9th-national-conference/3471-a-general-comparison-of-fft-algorithms.html
Thomas, L.: Using a computer to solve problems in physics. Appl. Digit. Comput. 458, 44–45 (1963)
Weinstein, C.J.: Quantization effects in digital filters. Technical report, MIT Lexington Lincoln Lab (1969)
Winograd, S.: On computing the discrete Fourier transform. Math. Comput. 32(141), 175–199 (1978)
Winograd, S.: On the multiplicative complexity of the discrete Fourier transform. Adv. Math. 32(2), 83–117 (1979). https://doi.org/10.1016/0001-8708(79)90037-9, http://www.sciencedirect.com/science/article/pii/0001870879900379
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Leong, S.H., Gustafson, J.L. (2023). Lossless FFTs Using Posit Arithmetic. In: Gustafson, J., Leong, S.H., Michalewicz, M. (eds) Next Generation Arithmetic. CoNGA 2023. Lecture Notes in Computer Science, vol 13851. Springer, Cham. https://doi.org/10.1007/978-3-031-32180-1_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-32180-1_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-32179-5
Online ISBN: 978-3-031-32180-1
eBook Packages: Computer ScienceComputer Science (R0)