rkeops: Kernel Operations on the GPU, with Autodiff, without Memory Overflows

The 'KeOps' library lets you compute generic reductions of very large arrays whose entries are given by a mathematical formula. It combines a tiled reduction scheme with an automatic differentiation engine, and can be used through 'R', 'Matlab', 'NumPy' or 'PyTorch' backends. It is perfectly suited to the computation of Kernel dot products and the associated gradients, even when the full kernel matrix does not fit into the GPU memory.

Version: 1.4.1
Depends: R (≥ 3.1.0)
Imports: Rcpp (≥ 1.0.1), openssl (≥ 1.3), stringr (≥ 1.4.0)
LinkingTo: Rcpp (≥ 1.0.1), RcppEigen (≥
Suggests: testthat (≥ 2.1.0), knitr, rmarkdown
OS_type: unix
Published: 2020-05-25
Author: Benjamin Charlier [aut] (<http://imag.umontpellier.fr/~charlier/>), Jean Feydy [aut] (<https://www.math.ens.fr/~feydy/>), Joan A. Glaunès [aut] (<https://www.mi.parisdescartes.fr/~glaunes/>), Ghislain Durif [aut, cre] (<https://gdurif.perso.math.cnrs.fr/>), François-David Collin [ctb] (Development-related consulting and support), Daniel Frey [ctb] (Author of the included C++ library 'sequences')
Maintainer: Ghislain Durif <gd.dev at libertymail.net>
BugReports: https://github.com/getkeops/keops/issues
License: MIT + file LICENSE
Copyright: see file COPYRIGHTS
URL: https://www.kernel-operations.io/, https://github.com/getkeops/keops/
NeedsCompilation: yes
SystemRequirements: C++11, cmake (>= 3.10), clang (optional), CUDA (optional but recommended)
Materials: README
CRAN checks: rkeops results


Reference manual: rkeops.pdf
Vignettes: Introduction to RKeOps
RKeOps: R bindings for KeOps
Package source: rkeops_1.4.1.tar.gz
Windows binaries: r-devel: not available, r-release: not available, r-oldrel: not available
macOS binaries: r-release: rkeops_1.4.tgz, r-oldrel: not available
Old sources: rkeops archive


Please use the canonical form https://CRAN.R-project.org/package=rkeops to link to this page.