* Add bfloat16 softmax and gelu

* Add pass attr bfloat16_enabled_op_types

* Changes from review

* - Added sum bf16 oneDNN

test=develop

* - Fix to UT of sum bf16

test=develop

* add conv_bias pass version test

* update according to reviews

* enhance the op_version_registry, test=develop

* add unittests, test=develop

* enhance the op_version_registry, test=develop

* fix bugs, test=develop

* revert pybind_boost_headers.h, test=develop

* fix a attribute bug, test=develop

* add fuse_bn_add_act pass

* add compile limit for paddle enforce

* polish elementwise_op_function.cu.h

* fix failed unittest

* fix windows compile failed

* detail polish

* revert no type constructor

* conv dilated mkldnn support: forward and backward pass

* add mkldnn conv_transpose dilation UT
test=develop

* remove unnecessary PADDLE_ENFORCE

* add int8 and bf16 dilated conv UT

* update according to reviews

* Implement the function of OueScaleForTraining/OutScaleForInference in dygraph

test=develop

* Add pass compatibility check for four mkldnn pass, test=develop

* use iwyu clean include, test=develop, test=win

* compilation error, test=develop

* fix compilation error2, test=develop

* fix compilation error3, test=develop

* fix compilation error4, test=develop

* fix compilation error5, test=develop

* fix compilation error6, test=develop

* fix compilation error7, test=develop

* fix compilation error8, test=develop

* fix compilation error8, test=develop

* fix compilation error10, test=develop

* fix compilation error11, test=develop

* fix bug sequececonv_eltadd_relu_fuse_pass, output error when sequence_conv's padding_start > 0

* fix seqconv_eltadd_relu_fuse_pass unitest error

* support use add instead of sum to do gradient accumulation

* add inplace addto pass

* add grad_add op and inplace addto pass

* remove debug code

* code refine

* fix bug when sereral sum ops inserts at same op_idx

* fix Flags type

* add addto attribute for conv3d

* fix ut

* code clean

* fix type

* pass compatibility

* add compatibility registry

* add unittests for different padding

* add assert

* drop errmsg

* Fix cpu quantize placement pass

* Include string lib

* Conv2d_transpose and mul support channnelwise quantization, test=develop
* Skip collecting out threshold for output tensor of which the type is not fp32 or fp64, test=develop
* Fix error in test_user_defined_quantization, test=develop
* Add depthwise_conv_bn_fuse, test=develop
* Add conv_transpose_bn_fuse_pass for post_training_quant, test=develop

* Change use_quantizer attribute name and data type

* Fix problem with setting attribute

* Add changes due to review

* Small change in function

* Restore use_quantizer attr for compatibility

* Added DNNL cache management for DyGraph

* move FLAGS_use_mkldnn to more general CMakeLists, getu use of the flag in ClearGradients

* missing file

* Fixes after review

* Bringing back original idea of place for 'use_mkldnn' flag to be accessible from platform nad imperative.

* Removed duplicate and added docs

* Fixes for CI

* fix error msg report in ir/, about 19 files, test=develop

* modified some unclear descriptions, test=develop

* modified some unclear descriptions, test=develop

* modify unit test pass_test.cc, because the error report in pass.cc is used by pass_test.cc, test=develop

* fix error msg report in ir/, about 5 files, test=develop

* fix error msg report in ir/, about 5 files, test=develop

* fix error msg report in ir/, about 5 files, test=develop