* add reduce op on arm. test=develop

* fix format. test=develop

* fix acccording to comments. test=develop

* add scatter op on arm. test=develop

* fix cmake error. test=develop

* test=develop

* add sequence_expand_as op on arm. test=develop

* fix format. test=develop

* [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

* fix sequence pool grad compute error, test=develop

* fix sequence pool grad run, test=develop

* fix format test=develop

* [Core][ARM] Fix beam_search, eltwise_mul supports broadcast and int64_t data type, add print op and kernel, add exeception
test=develop

* Fix the dims of parent idx of the arm kernel of beam_search op

* elementwise_mul supports int64_t data type with broadcasting

* Add print op and kernel for debugging

* Support throwing the exception when the internal error occurs

* Refine while and conditional_block op kernel

* Support the graph optimization on subblocks

* Pass program_desc and block_idx into the kernel of the control flow ops(while/conditional_block/subgraph), and create the RuntimeProgram online, it make it possiable to call the control flow ops recursively

*Add unit test for masked transformer model

add act grad ops

* add op affine_grid. test=develop

* add grouup_norm

* fix format. test=develop

* fix xiaodu crash. test=develop

* add deformable Conv op 

* fix ut, test=develop

* fix format. test=develop

* test=develop

* delete unuseful message. test=develop

movs unsqueeze frm arm to host.

[OPs] [ARM Kernel]move assign_value op into basic ops, while moving fake ops about quantization into extra to balance lib size (#3518)

* fix:modify quant_op to extra and add one basic op&kernel

* fix: move fake op to extra

* [NPU] add shape bridge

move shape arm kernel to host

* enhance compare arm kernel

* [NPU] add gather op bridge

* enable reshape arm ut

* [NPU] add lookup_table bridge

* rm grad code

* add mul_grad, test=develop

* add sgd op, test=develop

* test=develop

* add backend

* add kernel

* add grad kernel

* [NPU] subgraph's precision register to kAny

* add mean op, test=develop

* split forward and backward, test=develop

* add lookup_dequant_op

* enhance gather, lookup_table arm kernel uts

* enhance beam_search, beam_search_decoder, increment rigster

* add sequence_conv op and arm kernel

* add test, test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* modify code style. test=develop

* fix ut, test=develop

* delete unused code, test=develop

* feat: add lstm op && kernel
      test=develop

* Support Mask RCNN2 (#2588)