DeepAI AI Chat
Log In Sign Up

The Fast and Free Memory Method for the efficient computation of convolution kernels

by   Matthieu Aussal, et al.
Ecole Polytechnique

We introduce the Fast Free Memory method (FFM), a new fast method for the numerical evaluation of convolution products. Inheriting from the Fast Multipole Method, the FFM is a descent-only and kernel-independent algorithm. We give the complete algorithm and the relevant complexity analysis. While dense matrices arise normally in such computations, the linear storage complexity and the quasi-linear computational complexity enable the evaluation of convolution products featuring up to one billion entries. We show how we are able to solve complex scattering problems using Boundary Integral Equations with dozen of millions of unknowns. Our implementation is made freely available within the Gypsilab framework under the GPL 3.0 license.


page 13

page 14


Kernel-Independent Sum-of-Exponentials with Application to Convolution Quadrature

We propose an accurate algorithm for a novel sum-of-exponentials (SOE) a...

Solving acoustic scattering problems by the isogeometric boundary element method

We solve acoustic scattering problems by means of the isogeometric bound...

HODLR2D: A new class of Hierarchical matrices

This article introduces HODLR2D, a new hierarchical low-rank representat...

A general and fast convolution-based method for peridynamics: applications to elasticity and brittle fracture

We introduce a general and fast convolution-based method (FCBM) for peri...

Computing Free Convolutions via Contour Integrals

This work proposes algorithms for computing additive and multiplicative ...

Parallel Algorithms for Successive Convolution

In this work, we consider alternative discretizations for PDEs which use...

Reflective Conditions for Radiative Transfer in Integral Form with H-Matrices

In a recent article the authors showed that the radiative Transfer equat...