Added the tri-gamma function.

Params for Gemm, CGer, CGemv

Gradient for matrix pseudoinverse

Work around erroneous dnn_conv results with algo small an large batches

Buildbot testsuite names

removed part of _optcheck_fgraph and called std_fgraph instead

(replace algo `small` by `none` if necessary).

No need of big input.

Allow fallback on GpuCorrMM if cuDNN is not there

Use FAST_RUN for reference version.

Fix parameter types in ave_pool kernels, remove static_cast, add GLOBAL_MEM

This should speed up the FAST_COMPILE buildbot

Fail if output memory not allocated

Fix elemwise ValueError message (printf formatting)

This fixes a compilation issue on Pascal GPUs.

instead of segfaulting like a barbarian.

Update documentation and config flags about supported cuDNN algorithms.