A C++ linear algebra library for GPUs and multi-core CPUs using CUDA, OpenCL, and OpenMP

• Three computing backends: CUDA, OpenCL, OpenMP
• Iterative Solvers: Conjugate Gradient, Stabilized BiConjugate Gradient, Generalized Minimum Residual
• Preconditioners: ICHOL, ILUT, ILU0, Block-ILU, AMG, (F)SPAI, Jacobi
• BLAS Level 1, Level 2 and Level 3 routines on GPUs and multi-core CPUs
• Fast Fourier transform
• C++ Interface is mostly uBLAS compatible
• Interfaces for uBLAS, Eigen and MTL 4
• Iterative Solvers can directly be used with uBLAS, Eigen and MTL4 objects
• MATLAB interface for iterative solvers (as separate download)
• Structured matrices: Circulant, Hankel, Toeplitz, Vandermonde
• OpenCL Kernel optimization environment for optimal performance on the target device
• Header-only library
• MIT (X11) open source license

More information can be found at http://viennacl.sourceforge.net/