trunk,cuda: fixing CuMatrix::AddMat(.) to use 2strides; adding...

trunk,cuda: fixing CuMatrix::AddMat(.) to use 2strides; adding CuMatrix::EqualElementMask(.) which produces per-element equality mask (handy for backpropagation through max-pooling)



git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@3400 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8