* add new profiler components

* fix bug

* [Phi] Add ClearHolder when re-alloc on new place in DeviceContext

* fix hostAlloc

* foix inferRT unittest

* remove dev_ctx ptr

* remove SetAllocationForOutputTenosr

* add place param for copy kernel

* recover SetAllocationForOutputTenosr

* polish code

* fix empty_dev api bug

* test=allcases

* test=allcases

* fix bug

* recover empty

* recover modify

* Move GumbelSoftmax OP to phi

* platform::errors -> phi::errors; GumbelSoftmaxGradInferMeta -> backend.h/cc

* Use axis util in kernel impl

* Remove namespace platform::errors

* Use GetCPUEngine in Device Context

* Support custom implement for C++ API

* rename api_invoke_impl to api_custom_impl

* remove manual_api

* delete mutable_data in copy_to api

* fix problem of copy_to

* add unittest for infer_meta_fn_factory

* fix split cofig in yaml

* fix split cofig in yaml

* modify sum api yaml

* add copy_to wrapped infermeta

* rollback copy impl

* Move BilinearTensorProduct OP to phi

* Set dtype for Infermeta

* move eye OP to pten

* move size OP to pten

* merge develop

* fix merge

* move files

* move erfinv OP to phi

* remove comment

* move pixel_shuffle OP to phi

* remove comment

* fix PT_REGISTER

* fix NPU

* fix CR

* remove size_sig.cc for PR-CI-Coverage

* [phi]migrate increment addmm multinomial cholesky InferShapes to phi

* set_dtype and mod MultinomialFunctor

* add ele_add

* add ele_mul

* add ele_sub

* sovle conflict

* fix npu

* refine ele_add

* add ele_mul unittest

* refine ele_sub

* refine ci

* refine unittest

[Phi] mv kernel 

* refine randint kernel

* refine randperm kernel

* refine unbind kernel

* support op seed

* support cudnn kernel moving

* polish cmake rules

* add unittest for coverage

* remove orig kernel

* remove softmax cudnn kernel

* fix softmax test failed

* fix npu func error

* resolve conflict

* rename gpu dnn kernels

* fix name rule error

* fix compile error

* update fp16 namespace

* rename pten to phi

* fix infrt compile failed

* resolve conflict

* migrate increment addmm multinomial cholesky kernels to phi

* test pr39869

* test pr39869

* fix style and ci

* move randint to phi

* use host generator

* move cross forward OP

* move cross grad op to phi

* move infershape

* refine infershape

* rename ctx

* set dtype and layout in InferMeta

* refine code

* move bce_loss to phi

* refine PADDLE_ENFORCE

* revert PADDLE_ENFORCE

* fix ci

* Migrate poisson op into phi

* fix CI

* fix comment

* [Phi] Fix XPU OP segmentation Fault problem

* fix cast_op_xpu in kunlun1

* fix cast_op_xpu in kunlun1

* modify infershape by args_def

* add optional type for infermate

* add optional type for infermate

* add optional type for infermate

* support scalar type

* change OptionalInputAt function to none template

* support phi::DataType

* Fix for split bf16 inference

* added test for pass

* changes after review

* Optimize the where_op by the elementwise_op funtion

* Modified where_op & abs_grad_op by elementwise interface

* move randperm to phi

* fix npu

* fix memory::Copy

* change CUDA implementaion of bernoulli OP

* fix CI

* move unbind to phi

* revert infer shape

* add header file

* move concat_and_split to phi

* [KP] Add elementwise add xpu, test=develop

* modify the File Permissions

* modify the copyright time

* modify code style

* modify code style

* [Phi] Migrate lable_smooth_op into Phi

* fix PT->PD

* add elementwise_div

* refine rocm

* refine code

* refine op register

* solve conflict

* refine unittest

* refine unittest precision

* add rocm

* remove fill_any_like kernel in fluid and fix data transform bug

* support scalar in infershpe

* recover infershape in fill_and_like

* [custom kernel]Delete useless

* change RegType enum names

* mod notes

* merge

* update

* Move Real OP to phi

* Move Imag OP to phi

* Move Real and Imag InferShape to phi

* Move Real and Imag to complex_kernel

* Change PT_REGISTER_XXX to PD_REGISTER_XXX

* change Vector to std::vector and provide MixVector class as a helper wrapper class

* solve the multi-gpu hang problem

* remove the duplicate template instantialize

* Copy vector to cpu

* add CopyToCPU

* xxx

* final version: fix the problem of all reduce

* remove mixvector dependence

* fix

* merge

* fix code

* fix by CI

* [Phi] Migrate unfold_op into phi

* fix im2col CPUContext template instantial

* fix unfold_op.h header include problem

* fix unittest

* fix PT->PD