CULA is a GPU-accelerated linear algebra library that utilizes the NVIDIA CUDA parallel computing architecture to dramatically improve the computation speed of sophisticated mathematics.

Feature rich and easy to use

» Familiar LAPACK interface
» No CUDA experience required
» MATLAB and Python Integration
» Read more about CULA's features

» System Solvers
» Eigenvalues Routines
» Singular Value Decomposition
» See the full function list

GPU acceleration for a variety of platforms

» Supercomputing performance
» Parallel GPU implementation
» Accurate results
» See how CULA performs

» Device & host interfaces
» C, C++, and Fortran libraries
» Cross platform (Win, Linux, Mac)
» Learn more about CULA's interfaces

To try our free version, CULA Basic, register and go to our download page. For full product functionality, updates, and technical support, choose CULA Premium.

CUDA Training

EM Photonics and the CULA development team offer customized on-site CUDA training. If your company is looking to benefit from GPU computing we can offer a hands-on learning experience.

News & Events

For products updates and news, please visit our forums or read our blog. You can also learn about our latest efforts by coming to our booth at:

» NVIDIA GPU Technology Conference, September 20-23, San Jose, California

» Super Computing 2010, November 15-18, New Orleans, Lousiana

CULA was developed by a team of engineers at EM Photonics in partnership with NVIDIA®. CULA leverages the power of NVIDIA’s Tesla™ many-core computing processor with the CUDA™ architecture for accelerated linear algebra.