Eigencuda

Offload Eigen matrix-matrix multiplications to an Nvidia GPU

2
contributors
158 commits | Last update: February 13, 2020

Cite this software

DOI:
[[ releases.length > 0 ? releases[selectedIndex].doi : conceptDOI ]]
Copy to clipboard
Choose a citation style:
Download file

What Eigencuda can do for you

  • Simple interface to copy matrices to GPU
  • Automatic conversion to Eigen matrix type

Taking advantage of accelerators like GPU is fundamental in modern HPC applications. This library offers a simple interface to perform matrix-matrix multiplication in GPU for the C++ Eigen library. This library uses the same notation and operators that Eigen, automatically handling the GPU memory management.

Read more
Tags
  • GPU
  • High performance computing
Programming Language
  • C++
License
  • Apache-2.0
Source code

Participating organizations

Contributors

  • Felipe Zapata
    Netherlands eScience Center
  • Nicolas Renaud
    Netherlands eScience Center
Contact person
Felipe Zapata
Netherlands eScience Center