* [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

* read-only modification of cppDesc, test=develop

* update io.cc, test=develop

* fix the code style, test=develop

* refactor register mechanism, current so size: 1.20MB. test=develop

* fix KernelRegistry::Global().Create. test=develop

* fix cpplint errors. test=develop

* fix test_subgraph_pass bug. test=develop

* register kernel with target,precision,datalayout combination. test=develop

* fix test_paddle_api no op found bug. test=develop

* enhance comment

* fix lite/kernels/arm/elementwise_compute_test.cc. test=develop

* fix code style

* revert format of unchanged files. test=develop

* fix code format according to cpplint 1.5.1. test=develop

* remove redundant include header. 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

refactor(*): reduce Wsign-compare warning

1. clean code;
2. change `cl::Kernel` from unique to shared ptr;
3. `reset` `cl::Program` and `clear` `device_info_` in destroyed of CLRuntime;
4. remove clFlush in destroyed of CLRuntime.

* Optimize weight quantizaion, test=develop

* [LITE][OPENCL] fix OpenCL global static resources. test=develop

* Fix Cxx and light api. test=develop

* add weight quant for combined model after optimized, test=develop

* optimize quant_dequant_fuse_pass, test=develop

* update, test=develop

* update, test=develop

* fix bug for accessing the removed node, test=develop

* set the bias of int8 conv as float, test=develop

* support weight quantization, test=develop

* up, test=develop

* up, test=develop

* up, test=develop

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

* add shell file to automatically build and collect publish result test=develop

* modify codestyle of getInputNames test=develop

* test=develop

* rm publish.sh

* remove copy of func param

* test=develop

* test=devcelop

* test=develop

* test=develop

* const & test=develop

* modify variable defination test=develop

* test=develop

* test=develop

* test=develop

* test=develop

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

* delete the unused test
test=develop

* add GetInputNames and GetOutPutNames and GetInputByName method test=develop

* fix: fix model parser and save bug

* style: delete debug code

* fix: fix light_predictor program run model with subblock bug