* migrate truncated_gaussian_random kernel to phi, test=kunlun

* reuse CPU kernel, test=kunlun

* debug kernel, test=kunlun

* migrate truncated_gaussian_random kernel to phi, test=kunlun

* split truncated_normal, test=kunlun

* try fix error from CI, test=kunlun

* move label_smmoth XPU kernel to PHI,test=kunlun

* delete label_smooth_op_xpu.cc and modfied label_smooth_kernel.cc,test=kunlun

* delete add_label_smooth.cc,test=kunlun

* test=kunlun

* test=kunlun

* test=kunlun

* test=kunlun

* test=kunlun

* test=kunlun

* migrate compare op(E/NE/LE/LT/GE/GT) from fluid to phi

* fix compile error

* fix memory alloc; test=kunlun

* refine code; test=kunlun

* replace PADDLE_ENFORCE with PADDLE_ENFORCE_XDNN_SUCCESS

* [OpAttr]output_size of unpool support Tensor type

* fix coverage

* fix contain_var

* fix coverage

* Move XPU momentum to phi, test=kunlun

* Fix mu type, test=kunlun

* [XPU]Migrate argsort and arg_max XPU kernel into Phi

* test=kunlun

* test=kunlun

* transfer concat kernel

* test=kunlun

* test=kunlun

* test=kunlun

* test=kunlun

* move pool/pool_grad xpu kernel to phi, test=kunlun

* replace mutable_data() with DeviceContext::Alloc()

* replace PADDLE_ENFORCE_EQ with PADDLE_ENFORCE_XDNN, test=kunlun

* adjust function param name & update include header

* remove pool_op_xpu.cc

* fire r200 test

* minor, test=kunlun

* fix split bug

* solve function redefine

* fix fluid.layers.split and add unit test

* delete splitInferMeta register in unary.cc

* modify test_split_op GPU unit test

* modify test_split_op GPU unit test place param

* refactor split op and fix infershape bugs

* add () in && and ||

* fix split C++ unit test

* fix split infershape

* Move XPU mean and mean_grad to phi, test=kunlun

* Fix stream, test=kunlun

* Replace ENFORCE, test=kunlun

* support selected_rows kernel for multiply in dygraph

* refine SetKernelOutput

* [NPU] fix pool_op, interpolate_op

* fix slice_op_npu

* fix test_mixed_precision_npu

* add coalesce_tensor kernel

* polist coalesce_tensor kernel

* add sig and InferMeta

* add testcase

* add legacy_api.yaml

* fix infermeta

* fix yaml

* fix kernel implementation

* add compile dependency of phi/kernels

* fix MetaConfig

* add python api

* add and fix testcase

* rnn.py add import

* change _C_ops.coalesce_tensor

* remove useless comments

* add SetBackend

* restore XPU kernel temporarily

* fix code according to PR comments

* move huber_loss xpu kernel to phi, test=kunlun

* fix, test=kunlun

* fix paddle_enforce, test=kunlun

* Adapt tensor axis for argmin/max

* Add UT

* Polish UT

* move layer_norm xpu kernel to phi, test=kunlun

* fix, test=kunlun

* [OpAttr]Adapt tensor axis for reduce_min/max/mean/sum/prod

* add runtime config in phi

* add runtime attr for op desc and op

* fix no proto error

* adjust opdesc set_attr impl

* try to remove conv_op extra attrs

* add init runtime attr map

* change extra header path

* fix runtime_attr

* fix trace_op

* fix bug of pass

* fix merge conflict

* fix dygraph attrs

* fix bug of pass

* fix dygraph bug

* fix unittest module

* delete extra attr default

* fix dropout kernel

* polish code

* fix extra output of instance_norm

* fix merge confilct

* fix op_desc bug

* add extra attr in yaml for conv3d_transpose

* don't remove extra input and output

* fix save_inference_model

* fix bug of batch_norm

* revert some change

* polish log

* polish code

* add code comment
Co-authored-by: NChen Weihang <chenweihang@baidu.com>

fix missing keep_dim variable

    fix missing grad check in unittest

    add new test case

* [OpAttr]padding_value of Pad support Tensor type

* fix unittest

* fix unittest

* fix coverage

add constant folding pass， for some model，it will get less latency；

* fix memcpy_h2d bug related to cuda stream setting when allocate memory

* add header file

* fix compile error for cpu only

* move xpu kernel to phi

* delete fluid file

* fix compile

* add guard, test=kunlun

* xpu set constant

* fix xpu error, test=kunlun