FFI bindings to the CUDA Sparse BLAS library

Version on this page:
LTS Haskell 19.7:
Stackage Nightly 2022-03-17:
Latest on Hackage:

See all snapshots cusparse appears in

BSD-3-Clause licensed by Trevor L. McDonell
Maintained by Trevor L. McDonell
This version can be pinned in stack with:cusparse-,2849

Haskell FFI Bindings to cuSPARSE

Travis build status AppVeyor build status Stackage LTS Stackage Nightly Hackage

The cuSPARSE library contains a set of basic linear algebra subroutines for handling sparse matrices. Sparse vectors and matrices are those where the majority of elements are zero. Sparse BLAS routines are specifically implemented to take advantage of this sparsity. This package provides FFI bindings to the functions of the cuSPARSE library. You will need to install the CUDA driver and developer toolkit:


Revision history for cusparse

Notable changes to the project will be documented in this file.

The format is based on Keep a Changelog. - 2018-10-02


  • Level 3 operations from CUDA-9.2
  • Format conversion operations from CUDA-9.0
  • Precondition operations from CUDA-9.0
  • Precondition operations from CUDA-9.2 - 2018-03-12


  • Build fix for Cabal-2.2 (ghc-8.4) - 2017-08-24

  • First version; split off from bmsherman/cublas. Released on an unsuspecting world.