cherry pick 2109, 2008, 2098, 2102

1. the split op's bug will triger memory optimize pass failed.
test=develop

* Bug fix for model save and load (#1992)

* fix: fix model parser and save bug

* style: delete debug code

* fix: fix light_predictor program run model with subblock bug

* test=develop

* modify dynamic library: libpaddle_cxx_api.so (#2057)

(1)modify tiny publish dynamic_library to make it excutable
(2)modify the bug of compiling in armlinux

* test=develop

[Java API] add getVersion() interface to get c++ lib's version information test=develop (#2063) (#2072)

* checkout if passes match targets and kernels, test=develop

* add pass_utils, test=develop

* fix lite/core/mir/pass_registry.h, test=develop

* improve code styles, test=develop

* fix spell error, test=develop

* add opencl  depthwise_conv_trans_op

* test=develop

* Optimal OPENCL conv_3x3S2 Performance

* test=develop

* Optimal OPENCL conv_trans_3x3s2 Performance , test=develop

* add opencl conv_trans_op, test=develop

fix bilinear-interp unit test for more cases

test=develop

add math function: lstm  and selected_rows into lite/x86/math
add selected_rows and rw_lock into lite/fluid
add lstm_cpu_kernel and  lstm_kernel into lite/x86/detail

* add unsqueeze and range op. modify concat op test=develop

* modify exception in range_test_x86

add transpose kernel for cuda

* add opencl  depthwise_conv_trans_op

* test=develop

* Optimal OPENCL conv_3x3S2 Performance

* test=develop

* Optimal OPENCL conv_trans_3x3s2 Performance , test=develop

* make passes related to the device type, test=develop

* improve tips, test=develop

add slice op, reshape op,  reshape2 op, squeeze op and squeeze2 op and their unittests for x86

test=develop

* add assign_value op, arm kernel and test, add fluid_type, test=develop

* add hard_sigmoid, test=develop

* use image and new imple to test detection model, delete faster_rcnn_test, test=develop

fix model_optimize_tool error when using host kernel, fix reshape op build error on ios, test=develop (#1984)

* add opencl  depthwise_conv_trans_op

* test=develop

* Optimal OPENCL conv_3x3S2 Performance

* test=develop

* fix vector out of range crash test=develop

* fix style test=develop