* link IR graph to analysis graph

* add clean code and update

* add infer_clean_pass

* add ir_pass_manager

* support fc fuse executation

* fix ir circle

* Adding more details to cluster_train

* Update copyright for notest_dist_image_classification

* Fixed copyright

* Updating the copyright year and content

It will be used for LoD information in LoDTensor since LoD is a copy
on write field.

It is pretty slow for copying LoD information between operators. For
resnet it will cost roughly 10% time of whole time, including reading
data.