The CULA team is pleased to announce that we are now accepting applications for our upcoming GPU accelerated sparse linear algebra library: CULA Sparse. Separate from our “CULAPACK” library for dense matrices, CULA Sparse features solves and routines designed to work with sparse matrices.
Our first release (Beta1) will feature a handful of iterative solvers (CG, BiCG, GMRES), various storage formats (CSR, CSC, COO), and associated preconditioners (Jacobi, Block Jacobi, ILU). Future beta versions will introduce more solvers, storage formats, preconditioners, and features.
Please visit our application page to apply for admittance into the beta program. If selected, we’ll notify you by e-mail with access to the CULA Sparse installer.
Apply here: http://www.culatools.com/sparse-beta