* Merged LoDTensor with Tensor,test=allcases

* Patched python level LoDTensor

* Patched python level LoDTensor

* Merge Tensor into DenseTensor

* Fixed namespace issues,test=allcases

* Fixed merge issues

* Fixed inference issues

* Fixed NPU test issues

* Fixed merge issues

collecting input variables that only shape needed of each subgraph that compiled by CINN in build_cinn_pass, and expose them to memory optimization of framework passes by declaringDECLARE_INPLACE_OP_INFERER in cinn_launch op.

As the title.

complement deps of cmake files under WITH_CINN compilation

cinn_launch_op： cache scope and place on CinnLaunchContext to skip duplicate alloc/free callback construction

1. add a subdirectory named `cinn` in `paddle/fluid/operators` directory and move releated files into it
2. seperate CinnLaunchContext class from `cinn_launch_op.h` and put it in a  new independent file named `cinn_launch_context.h`, so that it can be included by others clearly.