Automatic Generation of FFT for Translations of Multipole Expansions in Spherical Harmonics

The fast multipole method (FMM) is an efficient algorithm for calculating electrostatic interactions in molecular simulations and a promising alternative to Ewald summation methods. Translation of multipole expansion in spherical harmonics is the most important operation of the fast multipole method and the fast Fourier transform (FFT) acceleration of this operation is among the fastest methods of improving its performance. The technique relies on highly optimized implementation of fast Fourier transform routines for the desired expansion sizes, which need to incorporate the knowledge of symmetries and zero elements in the input arrays. Here a method is presented for automatic generation of such, highly optimized, routines.

[1]  P. Duhamel,et al.  `Split radix' FFT algorithm , 1984 .

[2]  William Prager,et al.  Applications of digital computers , 1963 .

[3]  Dragan Mirkovic,et al.  An adaptive software library for fast Fourier transforms , 2000, ICS '00.

[4]  H. Y. Wang,et al.  An efficient fast‐multipole algorithm based on an expansion in the solid harmonics , 1996 .

[5]  C. Loan.  Computational Frameworks for the Fast Fourier Transform , 1992 .

[6]  J. CARRIERt,et al.  A FAST ADAPTIVE MULTIPOLE ALGORITHM FOR PARTICLE SIMULATIONS * , 2022 .

[7]  R. Tolimieri,et al.  Algorithms for Discrete Fourier Transform and Convolution , 1989 .

[8]  L. Greengard,et al.  A new version of the Fast Multipole Method for the Laplace equation in three dimensions , 1997, Acta Numerica.

[9]  Vladimir Rokhlin,et al.  An Improved Fast Multipole Algorithm for Potential Fields , 1998, SIAM J. Sci. Comput..

[10]  Jakub Kurzak,et al.  Massively parallel implementation of a fast multipole method for distributed memory machines , 2005, J. Parallel Distributed Comput..

[11]  L. Greengard.  The Rapid Evaluation of Potential Fields in Particle Systems , 1988 .

[12]  Chao Lu,et al.  Mathematics of Multidimensional Fourier Transform Algorithms , 1993 .

[13]  Martin Vetterli,et al.  Fast Fourier transforms: a tutorial review and a state of the art , 1990 .

[14]  J. Tukey,et al.  An algorithm for the machine calculation of complex Fourier series , 1965 .

[15]  Michael T. Heideman.  Multiplicative complexity, convolution, and the DFT , 1988 .

[16]  William Dewey Elliott.  Multipole algorithms for molecular dynamics simulation on high performance computers , 1995 .

[17]  Irving John Good,et al.  The Interaction Algorithm and Practical Fourier Analysis , 1958 .

[18]  Matteo Frigo.  A Fast Fourier Transform Compiler , 1999, PLDI.

[19]  Leslie Greengard,et al.  A fast algorithm for particle simulations , 1987 .

[20]  B M Pettitt,et al.  Fast multipole methods for particle dynamics , 2006, Molecular simulation.

[21]  C. Rader.  Discrete Fourier transforms when the number of data samples is prime , 1968 .

[22]  Martin Head-Gordon,et al.  Rotating around the quartic angular momentum barrier in fast multipole method calculations , 1996 .

[23]  L Greengard,et al.  On the Efficient Implementation of the Fast Multipole Algorithm. , 1988 .

[24]  Steven G. Johnson,et al.  The Design and Implementation of FFTW3 , 2005, Proceedings of the IEEE.

[25]  John A. Board,et al.  Fast Fourier Transform Accelerated Fast Multipole Algorithm , 1996, SIAM J. Sci. Comput..

[26]  Dragan Mirkovic,et al.  Automatic Performance Tuning for Fast Fourier Transforms , 2004, Int. J. High Perform. Comput. Appl..

[27]  Jakub Kurzak,et al.  Communications overlapping in fast multipole particle dynamics methods , 2005 .