* unfinish sgemmc4

* finish armv8 sgemmc4

* arm add sgemmc4 with deal with remain

* [ARM] add sgemmc4 small kernel, test=develop

* fix pooling bug and speed

* fix build error

* delete VLOGin pool, test=develop

* add openmp, test=develop

* fix lite/kernels/arm/pool_compute_test basic_pooling compute error bug, test=develop

* update pooling 2-pad to 4-pad, test=develop

* fix 2-pad to 4-pad in operators/pool_op.h, AttachKernel will set param, so 2-pad to 4-pad funcs should put in AttachKernel. test=ddevellop

* put 2-pad to 4-pad in AttachImpl, test=develop

* according to reviews, fix some format error. test=develop

* fix format errorr, add (). test=develop

* change paddings type to support dynamically modify, test=develop

* update padding type int other devices, test=develop

* fix x8d build error on shared_ptr, test=ddevelop

* fix formmat in operators pool_op.cc, test=develop

* fix cuda building, test=develop

* remove sequence_pool from cmake because build error, test=develop

* [ARM] sgemv support transA, test=develop

* add sgemv ut, test=develop

* add x86 op and kernel : search_fc and sequence_topk_avg_pooling   for content-dnn model test=develop

* Fix bug target for kHost and kARM not equal. test=develop

* Fix license. test=develop

* add debug -g option. test=develop

* enable opencl demo. test=develop

* Fix model_optimize_tool found no opencl kernel. test=develop

* add more vlog. test=develop

* remove macro LITE_WITH_OPENCL, LITE_WITH_FPGA in passes. test=develop

* Fix valid_places in mobilenetv1_test. test=develop

* Fix bug of find no real output of fetch, after tool OPs of optimzer passes. test=develop

* Fix vlog as log message in model_optimize_tool. test=develop

* fix miscs. test=develop

* fix comment. test=develop

* Fix misspell of opencl, fpga kernels name in lite/api/CMakeLists.txt. test=develop

* add opencl macro in full_api of demo. test=develop

* add cuda match_matrix_tensor op and test, test=develop

align the lite nearest， bilinear op to fluid on arm and cuda

* fix pooling bug and speed

* fix build error

* delete VLOG in pool, test=develop

* add openmp, test=develop

* fix lite/kernels/arm/pool_compute_test basic_pooling compute error bug, test=develop

[LITE][NPU] Add fusion_elementwise_add_activation bridge, remove the limitation of the dimensions of input tensors in the graph compute kernel, and refine log message (#2395)

test=develop

fix jit::matmul bug. Input x shape is (m, k), weight shape is (k, n). When k < 512, m==1, and n is a multiple of 16, the weight pointer is not correctly updated in the group calculation in the implementation of jit::matmul, resulting in the result diff 

* add tanh op in x86 platform and its unittest, test=develop

* add gelu op on x86 platform and add its unittests, test=develop

* update depends for math_function for activation for gelu, test=develop

* Add supporting for Huawei offical DDK
* Fix the param of graph op in NPU graph computing kernel

* Initial support for XPU
* Fix compiling errors of XPU
* Move XPU op kernel bridges from backends to kernels to fix deps order
* Change the namespace and directory of XPU bridges
* Add XPU SDK
* Fix header files and namespace of XPU SDK
* Add unit tests for relu and conv2d ops
* Restore the modification of paddle_api_test
* Supports simple model which contains only a relu layer
* Add compiling scripts for XPU
* Fix compiling errors of XPU
* Add comments for XPU LoadModel and BuildModel

* remove log in reshape, fix conv error when padding size=4, test=develop

* fix style, test=develop

* remove useless code, test=develop

* remove redundant model test file, test=develop

* change cluster to power_mode, test=develop

* fix build error, test=develop

* change cluster to power_mode, test=develop

* change opt_nb to use_optimize_nb, test=develop

* null, test=develop

* add gemv-int8 test, fix clang build error, test=develop

* fix gemv-int8 error when build with clang, test=develop

* modify yolobox_cuda to support multiple runs test=develop

* enable pool2d op on x86 and add its unit tests, test=develop

* enable dropout op and add its unit tests, test=develop

* add tranpose, transpose2 op and add their unit tests, test=develop

* [python api] init add python api test=develop

* feat: add beam_search_special function for support nlp model

* fix: add beam_search_compute kernel input and output

* feat: add assign op & copy_compute kernel

* feat: add fill_const_batch_size_like op & kernel

* feat: add layer_norm op and kernel and ut

* fix: fix some bugs
    fix mul_op infer_shape bug when x_dim_idx = 2, x_dims.size()=3 & y_dim_idx = 1, y_dims.size()=2
    fix elementwise_compute bug when y axis is all 1
    fix beam_search choose math_func wrong bug
    fix layer_norm get attr bug
    fix fill_constant_batch_size_like shape_set bug

* feat: add gather op and kernel & and transform ut

* feats: add ops and fix bugs to support transformer op
       fix type_cast passes to skip `while`
       fix elementwise infer_shape bug when x.dims=3 and y.dims={1} & axis=0
       fix lookup_table compute bug
       fix read_from_array/beam_search/increment/compate/gather ops data_type problems

* fix:
    transfomer ut add word read inferface
    fix copy/gather/norm/layer_norm include path problem

* fix:debug info

* fix: fix input reshape bug

* fix: fix norm bug

* style: style fix & test=develop

* style: fix operators cmakelist

* style: fix operators cmakelist; test=develop

* fix and test=develop

* fix and test=develop

* style: style fix; test=develop

* add static libraries of cuda, test=develop

* update cuda make

* add gpu kernel mul pool relu scale softmax dropout bilinear_interp and can run in tx2

* rm GREATER_EQUAL

* move lite/backends/npu/bridges --> lite/kernels/npu/

test=develop

* fix namespace for npu

test=develop

* mv npu runtime file to lite/backends/npu

test=develop

* update con_dw

* update

* add conv_depthwise_3x3s1.cc and conv_depthwise_3x3s2.cc

* add conv_depthwise_3x3s1_fp32 and conv_depthwise_3x3s2_fp32

* add new conv_dw

* only support conv_dw pad=0, 1

* add conv_dw_s1 conv_dw_s2 fp32

*     //conv2_func _impl2{nullptr};
update conv_dw, add conv_3x3s1 and conv_3x3s2, pad=[0,1]

* fix format, test=develop

* fix formmat, test=develop

* init: delete feed and fetch op, using zero copy
test=develop

* delete the unused test
test=develop

[LITE][OPENCL] Fix layout, target pass for OpenCL, add macro of CONVERT_TYPE_TO and READ/WRITE image, memory reuse in ResetLazyImage2D (#2170)

* add macro of CONVERT_TYPE_TO and READ/WRITE image. test=develop

* add data type control. test=develop

* fix io op as general layout and precision. test=develop

* Fix memory reuse strategy for opencl image2d. test=develop

* remove std::array, std::map in about opencl backend. test=develop

* [NPU] Fix the bug of loading multi NPU models
test=develop

* [NPU] Use lite tensor to store NPU model, fix the management of multi NPU models, support loading NPU model from memory and reduce the modification of framework
test=develop

* [NPU] Remove redundant header files for NPU bridges,
test=develop

* [NPU] fix NPU deps
test=develop

* [NPU] refine the compiling script for NPU
test=develop

* [NPU] remove redundant subdirectory in lite/CMakeLists.txt
test=develop

* [NPU] Fix and refine NPU test case
test=develop

* [NPU] revoke the modification of other non-NPU modules
test=develop

* [NPU] Remove NPU bridges if target is tiny publish
test=develop

test=develop

* fix asr modle related kernel bugs test=develop

* add conv int8 support(in condition which the input or output channel not be the times of 4)
add add_kernel for cuda.

* can run yolov3 fp32
test=develop

* 1. fix bug with yolov3 run
test=develop

* can run yolov3 int8 test=develop

* [LITE][OPENCL] support image2d. test=develop

* add context changed with consider image*. test=develop

* add layout, relu image kernels. test=develop

* replace image_data with data, mutable_image_data with mutable_data, test=develop

* comment unused var. test=develop

* remove unused var. test=develop

* fix yolobox_cuda bug 
* update code format

*  imporve prepack_input func speed in int8 3x3s1 dw conv

* fix code style

* fix code style

* improve 3x3s1 dw fp32 conv speed a little

* arm add 5x5s1 int8 dw conv, test=develop

* add conv int8 support(in condition which the input or output channel not be the times of 4)
add add_kernel for cuda.

* can run yolov3 fp32
test=develop

* 1. fix bug with yolov3 run
test=develop

* add full_api_static target and fix building errors, test=develop

* fix build errors, test=develop

* fix code style, test=develop

* fix lite/model_parser/pb/var_desc.cc, test=develop

* fix building errors, test=develop

* modify lite/tools/debug/CMakeLists.txt, test=develop

* fix building model_optimize_tool error on mac, test=develop

* fix model_optimize_tool build error, test=develop