The source code for an efficient solver and matrix inversion for small matrices using partial pivoting, is now available to all registered developers.

On sm_2x GPUs (48KB shared memory), the maximum dimensions for the matrices are:

Â Â Â Â DP Â Â Â Â Â solver, non-batched matrix inverse: Â 2…76

Â Â Â Â DP complex Â solver, non-batched matrix inverse: Â 2…53

Â Â Â Â DP Â Â Â Â Â batched matrix inverse: Â Â Â Â Â Â Â 2…77

Â Â Â Â DP complex Â batched matrix inverse: Â Â Â Â Â Â Â 2…55

The code has been released under BSD license.

It is available from the CUDA registered developer web site:

https://nvdeveloper.nvidia.com