* reduce .so size. test=develop

* compile all targets when LITE_ON_TINY_PUBLISH=OFF

* unordered_map is more convenient when key is customized class

* test=develop

* [LITE][DOC] Add kernel profiler doc for add operation. test=develop

* add argmax profiler info. test=develop

* fix pooling bug and speed

* add 2x2s2p1 pooling. test=develop

* fix conflict, test=develop

* [LITE][PROFILE] Enhance ARM CPU profiler with real backend kernel. 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

* add scale+relu/relu6/leakyrelu test=develop
* fix format， test=develop

* improve 3x3s1 direct profile

* fix format, test=develop

* Optimize matmul for size(x_dims)=2  size(y_dims)>2

* [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

* Add hard_swish, ctc_align and reciprocal op, test=develop
* Move some activation ops to extra, test=develop

 fix sequence_pool bug

* rename elementwise_sub_grad, test=develop

* rename Grad to GRAD, test=develop

* deal with case that Y@GRAD is empty, test=develop

* 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

* fix clang v7 error
* change ut, test=develop
* fix conv ut, test=develop

* add mean op, test=develop

* split forward and backward, test=develop

* fix v7 clang bug. test=develop

* fix format, test=develop

* fix .a build bug, test=develop

* set arm_lang default is off. test=develop

* fix resize error, test-develop

* add lookup_dequant_op