Skip to content

Introduce parallel eigensolver using ScalaPACK or ELPA

Sebastian Ohlmann requested to merge parallel_eigensolve into develop

Description

This function solves the eigenproblem in parallel for a non-distributed matrix. It transparently distributes the matrix, solves the problem in parallel and gathers the eigenvector matrix again.

For this, some more interfaces to pblas/scalapack functions are introduced.

The parallel eigensolver is called from one place in the Casida implementation right now.

News snippet

Introduce parallel eigensolver using ScalaPACK or ELPA

Checklist

  • I have checked that my code follows the Octopus coding standards
  • I have added tests for all the new features added in this request.

Merge request reports