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

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)

* 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

[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

* 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

* 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

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

* 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 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

* [framework][place] remove prefered_place, use place order in valid_place array instead test=develop

* remove kHost from valid_places test=develop

* fix bug for accessing the removed node, 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

* optimize quant_dequant_fuse_pass, 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

* 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

* fix compiling and fix code style test=develop

test=develop