* [LITE][OPENCL] Add depthwise_conv_3x3 opencl kernel

* [LITE][OPENCL] Add depthwise_conv_3x3 opencl kernel. test=develop

* [LITE][OPENCL] Add Pool opencl kernel. test=develop

* update profiler, test=develop

* warm up times of profiler, test=develop

[LITE][NPU][XPU] Refine subgraph pass, and support NPU/XPU model generation at execution time (#2576)

* add 3 layout for opencl image. test=develop

For multiple-use parameters, only copy once

修改了选kernel的逻辑，默认从模型文件中读取出lod_tensor的data type，在static_kernel_pick pass中如果kernel输入输出的类型与读取的data type完全一致，则选择该Kernel的概率增大。

- 增加 从模型文件__model__读取lod_tensor的data type到cpp::vardesc

- program中增加unordered_map<string, type>字段，并在 Program::PrepareWorkspace中对该字段赋值

- 修改了node.h文件，将const Type* 更改为Type*，并在SSAGraph::Build过程中为符合条件的type*赋值

- static_kernel_pick_pass中添加新规则，如果kernel的输入类型输出类型与__model__中存储的类型的一致，则score*=2。

- 支持模型中用到sequence_reverse_float kernel（输入输出均为float）和sequence_reverse_int64 kernel（输入输出均为int64），能够根据输入输出type选kernel

* add arm split lod tensor, test=develop

* add arm merge lod tensor, test=develop

* update split merge lod tensor, test=develop

* add reduce_prob op, test=develop

* support mask_rcnn succeed, test=develop

update cuda kernels to run content-dnn model

* init resnet cuda int8 support
test=develop

* refine cuda unit test
test=develop

* add the forgeted file.
test=develop

test=develop

[LITE][PASS] Fix static kernel pick pass, if op is not int8, but kernel is int8. test=develop (#2526)

* [NPU] add reduce_mean op bridge and unit test

test=develop

* refine xpu_pass place order; add bridges use

test=develop

* [XPU] update conv padding

test=develop

* [XPU] exclude xpu for passes

test=develop

* fix conv padding compute

test=develop

* [NPU] update 2-pad to 4-pad for conv and conv_transpose

test=develop

* reuse UpdatePadding code

test=develop

[LITE][ALL] Refine NPU and XPU passes, fix the pass matching based on the bound targets and excluded targets (#2477)

* add nhwc to nchw

* add layout in funcs

* change layout as extra, test=develop

* change make, test=develop

* use template class method to update layout NNCHHW and NHWC transform, test=develop

* fix cmake error, set layout to extra, test=develop

* fix test_layout_compute_arm test, its extra

* layout is extra, test=develop

* fix error in kernels/arm/layout_comput.cc when register kernel, DataLayout must be NCHW, test=develop

* delete extra note, test=develop

* delete extra test

* delete layout_test, test=develop

, its in tests/math/layout_comput_test

* delete extrat test, test=develop

* fix cuda building, test=develop

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

* support build C++ cuda shared lib

* 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 CUDAContext assignment operator to fix cuda compile bug

[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

mv deviceinfo.workspace and other relative member to thread_local_storage

* add channel_wise_dequantized_max_abs op and ChannelWiseDequantOpFuser, test=develop

test=develop

* fix step rnn model run bugs test=develop

* Fix conv bn bug. test=develop

* Fix bug in pattern_matcher. test=develop

* [LOG] macro for vlog. test=develop

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

* Fix license. 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

* add shell file to automatically build and collect publish result test=develop
* modify API inference of model_optimize_tool and add option for tiny&full publish test=develop

Fix conv_bn fuser with no elemwise op added, Fix conv_elem with original conv with conv_bias (#2211)

* Fix conv_bn fuser with no elemwise op added. test=develop

* fix match not bug. test=develop

* Fix conv-bn pass. test=develop

* Fix conv-bn pass. test=develop

* Fix conv-bn pass. test=develop

* Fix conv-bn pass. test=develop

* Fix conv-bn pass. test=develop

* Fix conv-bn fuse pass. test=develop

* Fix conv-bn fuser consider the case: enable_int8=true without conv_bias. test=develop

* Fix back, consider enable_int8. test=develop

* Fix Bug for conv-bn quant pass. test=develop

* Fix conv-elemwise considering origin conv with conv_bias. test=develop

* Fix code format. test=develop

* simplify. test=develop

* simplify. test=develop

* Fix conv_elem. 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)