Merge pull request !984 from Tinazhang/hwc2chw

Merge pull request !1019 from cathwong/ckw_dataset_ut_cleanup2

Merge pull request !983 from Jamie/colmaps

clang format updates

self-review cleanups

cpplint fix

review updates

ci fixes

Merge pull request !998 from guozhijian/enhance_format_func_name

Merge pull request !1010 from wukesong/remove_datasetlink

Merge pull request !1007 from chengxb7532/master

Merge pull request !1008 from liyanliu96/master

Merge pull request !993 from huanghui/mul-add-fusion-pass-enhancement

Merge pull request !1009 from zhaozhenlong/adapt-lamb-next-mv-ir-fusion

Merge pull request !980 from guozhijian/add_example_for_aclImdb

Merge pull request !1002 from meixiaowei/master

Merge pull request !989 from kisnwang/fix-assignc-ir-inconsistency

Merge pull request !986 from chengxb7532/master

Merge pull request !992 from amongo/fixCodex0508

Merge pull request !988 from ZPaC/gpu-kernels-adapt-with-special-dimensions

Merge pull request !976 from zhaozhenlong/adapt-lamb-nextmv-with-decay

Merge pull request !952 from thlinh/dev_May6th_improve_zero_fill_like_zero

Merge pull request !990 from casgj/gaojing

new subtree with 9 nodes and after that a Renormalize pass is needed to simplified it back to a tensor. The new algorithm will
create the tensor while visiting in the pass, therefore only a single node is created and no Renormalize will be needed for this pass
(if other passes requires then Renormalize will still be called but no further infer is needed for the created tensor)

Signed-off-by: Hoai Linh Tran h00472437 <hoai.linh.tran@huawei.com>

Code review

Merge pull request !985 from jjfeing/master

Merge pull request !971 from Simson/push-to-opensource

Merge pull request !956 from zjun/optimize_host_trans

Merge pull request !975 from Etone.Chan/master

Merge pull request !973 from huanghui/enhance-add-memcpy-async-pass

Merge pull request !978 from xulei/filter_op

Merge pull request !979 from ms_yan/rename_columns