PyCULA is a module providing transparent PyCUDA and ctypes based Python bindings for CULAtools LAPACK by Louis Theran and Garrett Wright of Temple University. It provides support for mixing PyCUDA-style kernel code with CULA device functions and also has a complete set of ctypes wrappers for CULA.

Key Features Include:

• Reduce Memory Leaks by using Automatic Memory Management (via PyCUDA)
• Utilize both simple Numpy style and GPUArray manual device style interfaces.
• Supports mixing LAPACK via CULA with your Custom Kernels.
• Combine seamlessly with handy Python modules like SQL, gzip, SciPy, R, etc.
• Develop, Debug, Optimize, and Get Help right at the interactive command line.

The PyCULA0.9a4 alpha release is avaiable at http://pypi.python.org/pypi/PyCULA/0.9a4. PyCULA was developed as part of the ASU/Temple Zeolite Project, which is supported by CDI-I grant DMR 0835586 to Igor Rivin and M. M. J. Treacy.

EM Photonics announced today the general availability of CULA 2.0, its GPU-accelerated linear algebra library. The new version provides support for NVIDIA GPUs based on the latest “Fermi” architecture.

CULA contains a LAPACK interface comprised of over 150 mathematical routines from the industry standard for computational linear algebra, LAPACK. EM Photonics’ CULA library includes many popular routines including system solvers, least squares solvers, orthogonal factorizations, eigenvalue routines, and singular value decompositions. CULA offers performance up to a magnitude faster than highly optimized CPU-based linear algebra solvers. There is a variety of different interfaces available to integrate directly into your existing code. Programmers can easily call GPU-accelerated CULA from their C/C++, FORTRAN, MATLAB, or Python codes. This can all be done with no GPU programming experience. CULA is available for every system equipped with GPUs based on the NVIDIA CUDA architecture. This includes 32- and 64-bit versions of Linux, Windows, and OS X.

More information is available at www.culatools.com.