Kernel Operations on the GPU, with Autodiff,without Memory Overflows - Archive ouverte HAL Access content directly
Journal Articles Journal of Machine Learning Research Year : 2021

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

Benjamin Charlier
Jean Feydy
Joan Glaunès


The KeOps library provides a fast and memory-efficient GPU support for tensors whose entries are given by a mathematical formula, such as kernel and distance matrices. KeOps alleviates the major bottleneck of tensor-centric libraries for kernel and geometric applications: memory consumption. It also supports automatic differentiation and outperforms standard GPU baselines, including PyTorch CUDA tensors or the Halide and TVM libraries. KeOps combines optimized C++/CUDA schemes with binders for high-level languages: Python (Numpy and PyTorch), Matlab and GNU R. As a result, high-level "quadratic" codes can now scale up to large data sets with millions of samples processed in seconds. KeOps brings graphics-like performances for kernel methods and is freely available on standard repositories (PyPi, CRAN). To showcase its versatility, we provide tutorials in a wide range of settings online at
Fichier principal
Vignette du fichier
KeOps_2021.pdf (342.37 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

hal-02517462 , version 1 (24-03-2020)
hal-02517462 , version 2 (08-04-2021)




  • HAL Id : hal-02517462 , version 2


Benjamin Charlier, Jean Feydy, Joan Glaunès, François-David Collin, Ghislain Durif. Kernel Operations on the GPU, with Autodiff,without Memory Overflows. Journal of Machine Learning Research, 2021, 22 (74), pp.1-6. ⟨hal-02517462v2⟩
248 View
364 Download


Gmail Facebook X LinkedIn More