SLEPc#
Scalable Library for Eigenvalue Problem Computations#
SLEPc is a software library for the solution of large scale eigenvalue problems on parallel computers. It is an extension of PETSc and can be used for several related linear algebra problems such as:
Linear eigenvalue problems in either standard or generalized form, with real or complex arithmetic.
Partial SVD of a large, sparse, rectangular matrix, as well as other types of singular value problems.
Nonlinear eigenvalue problems, either polynomial or general.
The computation of the action of a matrix function on a vector.
SLEPc relies on PETSc data structures and linear solvers. The model of parallelism employs the MPI standard for message-passing communication, with additional support for GPU as is done in PETSc. SLEPc has bindings for C, Fortran, and Python (via slepc4py). It is being developed mainly by researchers from Universitat Politècnica de València (Spain).
The current version of SLEPc is 3.24, released in September, 2025.
Latest News and Forthcoming Events#
