cherry-pick

* fix model_opt_tool bug : judge WITH_MKL to choose whether to compile MKL (#2320)

test=develop

* Fix conv bn bug. test=develop

* Fix bug in pattern_matcher. test=develop

* Fix compiling bug in android_armv7_demo : cxx demo can not compile properly because demo' android version is different from that of library file (#2308)

link armv7 demo to android-23 to make sure the demo can compile properly
cxx demo can not compile properly because demo' android version is different from that of library file, we fix this bug by linking armv7 demo to android-23

* Add 'inference' folder into build.lite.x86, 'inference' folder contains head files、library files and demo of x86 compiling (#2301)

Add inference folder into build.lite.x86, build.lite.x86/inference folder contains head files、library files and demo of x86 compiling

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

* Fix license. test=develop

* we can build x86 dynamic library by `build.sh x86`  (#2270)

* remove dynamic library compiling from `ci_build.sh  build_test_server` (#2275)

test=develop

test=develop

* cherry-pick model-tailoring into release/v2.1.0 test=develop

* make inceptionv4, resnet50, googlenet can run on x86 paltform and fix the compare part in x86 unittests, test=develop

* fix googlenet tests for benchmark record, test=develop

* [framework][profile] fix profile dump bug when op is feed and fetch test=develop (sangoly)

* optimise conv 1x1 ,test=develop

* add test_performance test

* 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

test=develop

* [python api] add armlinux supported and publish paddle-lite python lib & demo

* add cuda build
test=develop

* modify yolobox_cuda to support multiple runs test=develop

* fix: fix fc batch bug

* fix:fix fc bug;test=develop

* update framework.proto

* add compatibility check, test=develop

* remove head files, test=develop

* 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

* 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

* fix python3 build error, test=develop

* fix ci, test=develop

* Make armlinux compile libpaddle_light_api_shared.so
test=develop

* modify parse_op_registry. When REGISTER_LITE_OP and op_name not in the same row, it also can obtain op_name, test=develop

* Add DeleteQuantOpFuser
* Add fake_quantize_dequantize_moving_avg_abs_max_op
* Add DeleteQuantDequantOpFuser

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

* cuda add softmax and pool op

* * fix armlinux can find sys/system_properties.h
* conv add padding_algorithm
test=develop

* delete padding_algorithm in op param, test=develop

* fix bugs, test=develop

Fix ‘Large memory usage of Naive model loading’  (#2175)

fix yolobox_cuda test precision error