The latest version of scikits.cuda can be downloaded from the
Bionet Code Repository.
scikits.cuda requires that the following software packages be
installed:
- Python 2.5 or later.
- setuptools 0.6c10 or later.
- NumPy 1.2.0 or later.
- SciPy 0.7.0 or later.
- PyCUDA 0.94rc or later.
- NIVIDIA CUDA Toolkit 3.0 or later
Most linear algebra functionality relies on CULA:
- CULA (single precision version of the library is free-of-charge; requires registration).
To build the documentation, the following packages are also required:
The software has been tested on Linux; it should also work on other platforms supported by the above packages.
To build and install the toolbox, download and unpack the source release and run:
python setup.py install
from within the main directory in the release. Sample code
demonstrating how to use different parts of the toolbox is located in
the demos/ subdirectory. Many of the high-level functions also
contain doctests that describe their usage.
To rebuild the documentation, run:
make
from within the doc/ subdirectory and follow the directions.