* Optimize perf of softmax_with_cross_entropy

* fix

* fix

* fix accuracy error

* 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

* fix bugs

* fix bugs

* Fix compile error on cuda_arch less than 700.

* rename pten to phi

* fix infrt compile failed

* resolve conflict

* Update IpuStrategy Python Part

* add docs

* add add_custom_op for ipu_strategy

* fix build warning

* rm unneeded part

* clean api

* fix typo

* update option names

* update IpuStrategy doc

* fix plugin: special slice for ernie

* migrate increment addmm multinomial cholesky kernels to phi

* test pr39869

* test pr39869

* fix style and ci

* move randint to phi

* use host generator

* build a Paddle Graph from CINN compiled program for execution with PE

* update names of some variables

* fix random fail in build_cinn_pass_test and update some comments

* fix compiler error by merging phi pr

* nearest_interp_bw init

* optimize kernel config

* optimize kernel config

* fix struct init

* optimize code

* rm duplicated struct

* fix eigh test

* modify atol and rtol

* 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

* fix maxunpool2d example, test=document_fix

* fix maxunpool2d example, test=document_fix

* Migrate poisson op into phi

* fix CI

* fix comment

* added nearest interp v2 bf16

* disabled bilinear interp nhwc test

* added skipping UT for gpu

* added NHWC support

* removed unnecessary statements

* minor change

* CI fix

* added appropriate changes to interpolate_v1

* fix after review

* minor change

* minor change

* revert unwanted deletions

* CI fix

* Refactored GradNodeAccumulation data structure and behaviour

* Fixed CI issues

* Fix compilation issues

* Fixed minor issues

* Reverted changes for intermediate and OverwriteOutput

* fixed minor issue

* Fixed code format issues

* Fixed CI-Coverage issue

* Fixed CI issues

* fix 'invalid escape sequence'

* fix assert error

* [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

Add note for Place of Executor in parallel environment

* eager, test=develop

* fix bug, test=develop

* eager, test=develop

* merge legacy to fluid

* eager, test=develop

* eager, test=develop

* Refactor TensorAdd func by template and remove gradient_accumulation in eager

* Remove needless target name

* eager, test=develop

* eager, test=develop

* Use overload instead of template

* Remove legacy code

* Remove legacy code

* selectedrows, test=develop

* Remove DataType test

* eager, test=develop

* eager, test=develop

* support gan, test=develop

* Using Tensor directly instead of using EagerTensor

* support gradient_accumulation

* make test_imperative_lod_tensor_to_selected_rows longer

* make test_imperative_lod_tensor_to_selected_rows longer

* refine code

* ptb, test=develop

* Rename all EagerTensor to Tensor

* Rename some EagerTensor to Tensor

* rename EagerTensor to EagerVariable

* eager, test=develop

* eager, test=develop

* eager, test=develop

* eager, test=develop

* add more test

* eager, test=develop

* Support copiable selected rows and merge develop

* save load, eager, test=develop

* save load, eager, test=develop

* refine, test=develop

* refine, test=develop

* refine, test=develop

* revert static_runner, test=develop

* EagerTensor to Tensor, test=develop

* refine, test=develop

* refine, test=develop

* clear grad, test=develop

* merge, develop

* merge, develop

* merge, test=develop

* merge, test=develop
Co-authored-by: NJiabinYang <360788950@qq.com>
Co-authored-by: NWeilong Wu <veyron_wu@163.com>

* optimize block config  and fp16 atomicAdd perf for lookup_table_v2_grad.