EM Photonics announced the general availability of their latest release of CULA this morning. Version 2.0 adds support in their linear algebra libraries for NVIDIA’s latest Fermi silicon.
The Tesla 20-series GPUs deliver a huge increase in double precision performance,” said Andy Keane, General Manager for the Tesla high-performance computing group at NVIDIA. “The LAPACK functionality provided by CULA is critical to many applications ranging from computer-aided engineering and medical image reconstruction to climate change models, financial analysis and more. This new release is great news for developers who can easily accelerate their application with CULA 2.0.,” he added.
So what do you get with the 2.0 release? CULA 2.0 contains a LAPACK interface with over 150 routines. These include many common solvers for systems, least squares, orthogonal factorization, eigenvalues and singular value decompositions. Applications folks can call CULA routines from their C, C++, FORTRAN, MATLAB and Python codes.
CULA 2.0 is the next step in the evolution of our product, where we can finally show strong double precision performance to complement our already impressive single precision speeds. Users of older GPUs will also see performance improvements as well as new routines and increased accuracy. As we continue tuning our CULA library for Fermi, users can expect to see even better performance as well as new features in the next few months,” said Eric Kelmelis, CEO of EM Photonics.
You can grab the CULA in three different versions. For those interested in trying out the interface, there is a Basic version available for free that includes six routines. They also have Premium and Commercial versions available with much more functionality.
If you’re interested in more info, check out the CULA website here.