* [ARM] Add op pixel_shuffle for arm kernel. test=develop

* Delete OpenMP pragma clause

Delete OpenMP pragma clause because openmp not support well for now on windows and Mac OS.

* Just trigger CI. test=develop

* [LITE][BM] Fixed dependency path issues for compiling third-party libraries. test=develop

* Update CMakeLists.txt

* add new ops for ernie, test=develop

* drop lookuptable, test=develop

* update cast compute, test=develop

* add slice gather op, test=develop

test=develop test=xpu

* optimize conv_dw profiler

* fix build conv_dw_3x3s1 bug

* update conv_dw_3x3s2

* fxi foormat test=develop

* fix compute error

* fix format, test=develop

* speed up vector assignment, test=develop

* update op_desc with c-string, test=develop

* add transpose reshape flatten op, test=develop

* address review comments, test=develop

* update compatible_pb.cc, test=develop

* using unique_ptr in fbs::desc, test=develop

* add fbs to compatible_pb, test=develop

* update model_parser functions, test=develop

* fix bugs, test=develop

* [Ascend] add fc op

* [Ascend] fix fc test

* [Ascend] fix code format

* [Ascend] modify the comment

* fix sequence pool grad compute error, test=develop

* fix sequence pool grad run, test=develop

* fix format test=develop

[Core] Fix the missing of the input and output scale after the lite_elementwise_activation_fuse_pass is applied (#4066)