Cond_op with dynamic if-else checked-in

Fix enforce test failed and demangle stack info

Using LoDTensor instead of Tensor in every operator.

Add MKLDNNConvLayer

auto generate USE_OP() in pybind.cc

Note: If no symbol with a suitable value is found, both this field and dli_saddr shall be set to NULL.

Delete unused Op dependence in CMakeList

fix shape of output tensor of cross_entropy_op.

Fix unitest of pad_op

Add broadcasting support (e.g. matrix-vector) for cos sim operator.

* init add

* add topk op

* someupdate

* fix style check

* add test py file

* update top k cuda kernel

* follow comments

* remove debug print

* accuracy_op

* fix casting error

* fix casting error

* fix casting error

* fix rename bug...

* make it smaller

* update cast

* add rnn design

Fix CI test

"better format"