* move layout.h & layout.cc from relay to tvm

* change ConvertLayout in relay to bijectiveLayout->Forward/backward

* add first test case

* add LayoutAxis

* add LayoutAxis struct and compiles

* simplify BijectiveLayout rule consturct

* polish func name for Layout, move impl to .cc, remove Layout::defined(), add defined() checker

* partially add layout py support

* add layout test cases

* add doc for tvm.layout & tvm.bijective_layout

* fix lint

* fix lint

* fix layout name generation bug

* fix layout typo

* address comments and add topi.layout_transform

* layout.h->data_layout.h, test_lang_layout.py->test_lang_data_layout.py

* Add sptialpack schedule for arm cpu depthwise convolution

* Supply comments.

dtype of count is the same as dtype of inputs[0] when created, but its type may
  change when multiplied by inputs[0]->shape[i]. Which causes dtype of
  output is not same as dtype of input.

Dtype of output of pad should follows input, but if dtype of input is not float,
  output will still be float becase pad_value is float.

* [COMPILER][BUG] Fix out of bound access.

* 	* Review comments.

* Add mean and product operators

* Fix typo

* Fix lint

* fix test

* Fix gpu schedule

* Update doc

* remove mean from topi

* Add nnvm test

* Fix cuda schedule

* Remove cuda schedule

* Improve x86 pooling and concat

* Fix

* Fix test concatenate correct layout

* Add conditional vectorize

* Fix lint

* Modify schedule for global pooling

* Fix

* Fix warning

* Fix alter layout test

* Remove vectorization for pooling when using 4D layout

* Remove vectorization for 4D concat

* Fix concatenate layout

* Fix concatenate schedule

* Fix concat

* Fix lint

* Fix concat

* Simplify pooling logic

* Update docstring

* Fix test topi pooling

* Small changes

* Yolo and Upsample frontend support

* Lint fix

* Mac support added

* Code clean and trigger CI