* [Core][ARM] Fix beam_search, eltwise_mul supports broadcast and int64_t data type, add print op and kernel, add exeception
test=develop

* Fix the dims of parent idx of the arm kernel of beam_search op

* elementwise_mul supports int64_t data type with broadcasting

* Add print op and kernel for debugging

* Support throwing the exception when the internal error occurs

* Refine while and conditional_block op kernel

* Support the graph optimization on subblocks

* Pass program_desc and block_idx into the kernel of the control flow ops(while/conditional_block/subgraph), and create the RuntimeProgram online, it make it possiable to call the control flow ops recursively

*Add unit test for masked transformer model

* update desc interfaces, test=develop

* update desc interfaces, test=develop

* update compatible_pb.cc, test=develop

* fix build errors, test=develop

* remove the fstream to shrink the size of library, test=develop

* [LITE][PASS] Add pass for removing uesless reshape2 / squeeze2. test=develop

* 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][OPENCL] Enhance Profiler for OpenCL with in/out/filter shape, macs/macs_ps, real backend kernel etc. (#3641)

* [LITE][OPENCL] Enhance Precision Profiler for OpenCL. test=develop

lite cuda support exec multi-stream

Optimize the execution of RuntimeProgram by saving the bool whether the op is feed/fetch op. (#2703)

test=develop

* update profiler, test=develop

* warm up times of profiler, test=develop

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

* 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)

* Add precision and persistable attrs for the tensor. And fix cxx light and full api demo.

* update precision2string methods. test=develop

* move the save logic to the front of the run in mobilenetv1_full_api.cc, test=develop.

* add comments for UpdateVarsOfProgram. test=develop