* enable opencl kernel tune by default. test=develop

* fix typo

* [LITE][XPU] accomodate crmm(variant 20200608)

* refine lite/tests/api/test_mmdnn_lite_xpu.cc

* more comments, test=develop test=xpu

* bugfix in crmm pattern match

* pr comments, test=develop test=xpu

* add XPU_CALL and retval check, test=develop test=xpu

* update sequence_conv profile

* delete extra file, test=develop

* update sequence_pool and sequence_conv profiler, test=develop

* fix compute error, test=develop

* delete warning and extra info, test=develop

add act grad ops

* [LITE][BM] modify interpolate if,test=develop

* [LITE][BM] add include math.h, test=develop

remove conv redundant's for opencl kernel.

* [LITE][XPU] accomodate resnet_cbam

* [LITE][XPU] accomodate content-dnn

* fix pr comments test=develop

* fix pr comments test=develop

* fix pr comments test=develop test=xpu

* fix compilation error, test=develop test=xpu

* [X86] Fix the unit test of slice op
test=develop test=xpu
Co-authored-by: Nhong19860320 <9973393+hong19860320@users.noreply.github.com>

* [NPU] apply npu cache offline model to other devices, test=develop

* [NPU] address review comments, test=develop

* [NPU] enhance cache offline model, test=develop

add op lrn  norm  gather

add mlu kernels  argmax, flatten, slice, transpose

add mlu kernel dropout split squeeze reshape

* fix opencl fc kernel caused int16 model weight abnormal. test=develop

* fix ttfnet miscs. test=develop

* fix conv int8 kernel choose and sooftmax compute bug

* change axis_size = 4 kernel choose, test=develop

* fix format. test=develop

* Update quantization, scale save in op attrs by  <inputname_index, scale_value>, test=develop
Co-authored-by: Nhong19860320 <9973393+hong19860320@users.noreply.github.com>

* 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