* move dot_dev api into dot_kernel.h

* add infermate header

* modify to dotkerel in dot_op.h

* mvoe conj dev api into complex_kernel.h

* move sign dev api into  sign_kernel.h

* move scale dev api into kernel.h and remove infermete.h

* rm paddle/pten/include/math.h

* rm paddle/pten/include/math.h

* rm include dir

* rm paddle/pten/include/math.h

* fix conflict with develop branch

* rm devContext in conj_op.h

* add the missing complex_kernel header

* init elem_max_grad op

* optimize code and reply review comments

* ternary functors

* apply new reduce func

* move functor to .h

* multi-outputs init

* rearrange code

* modifed functors

* optimizer code

* pass nullptr

* revert the last change as seg fault occurs

* optimize code

* remove inplace

* remove comments

* ini commit

* multi-outputs init commit

* optimize code

* remove inplace

* refactor the impl of elementwise grad kernel

* refactor impl of elementwise grad kernel(cuda)

* fix compile bugs

* first commit

* fix wrong filename

* fix the wrong spell name

* fix gpu config warper

* modify according to pr advices

* fix GpuLauchConfig1D api bugs

* change the config for dropout grad

* fix bugs

* modification according to pr advices

* modification according to pr advices

* fix bug when inplace strategy

* fix

* fix

* fix

* fix

* fix

* fix the wrong filename

* first commit

* first commit

* remove rest useless headers

* for ci approval

* support vs2019 compilation in windows

* not modify pow_op's original compute logic

This reverts commit c0e2b98e.

* fix the wrong filename

* first commit

* move gpu_impl of elementwise kernel

* change copyright to 2022

* init commit: new elem_mul_grad

* add template speciallization for complex in multiply

* reply review comments

* correct dx and dy computation when T is complex

* reply review comments

* update to new ReduceRunctor

* mul-output broadcast

* call functions

* call functions with comments

* remove comments

* add elementwise div

* move mul and div grad functor

* Combine multiple CUDA kernels

* Update the reduce interface call

* add multi-output

* add multi-output div

* add branch judge

* Package branch

* Combine the x and y functions into one

* change 'math' to 'math_kernel'

* fix compile bugs

* merge develop

* fix compile bugs

* move cpu_impl of elementwise kernel to new directory

* change 'math' to 'math_kernel'

* fix compile bugs

* merge develop

* fix compile bugs

* first commit

* pass ctest of  elementwise_div_grad

* support FP16 for more ops

* add amp list tests

* refine reduce_mean_grad

* fix OP benchmark ci

* fix fp16 reduce_mean

* updat ut, but still have some problems

* remove mean/reduce_mean fp16 kernel

* add complex op and `paddle.complex`.

* fix_bugs_for_elementwise_branch_selection

* fix merge_dims bugs

* fix all influenced file

Add elementwise_fmax and elementwise_fmin operators

* Add the transformop parameter in TensorReduceFunctorImpl

* Reduce reshape kernel functions in pten

* delete notes

* fix bugs when compile

* modify register name

* fix compile bugs

test=document_fix

* add alias kernel name

* modify code as suggestions

* add boardcast_sub

* add boardcast_sub

* refine structure for cuda and rocm

* update

* update

* update

* update

* [NPU] reorganization for device API abstraction

* [NPU] delete old files

* [NPU] fix npu_collective_helper

* [NPU] fix collective_helper

* [NPU] fix ut

* [NPU] mod memory allocation and hccl_helper

* [NPU] fix place_type

* [NPU] split enfoce.h

* move acl* call into npu_info

* merge conflict

* fix merge

* merge conflict

* merge conflict

* elementwise_mul refactor

* perfect code in test

* delete redundant code

* fix bugs when run test_multiply

* adjust the location of macro

* fix bugs when run ci

* elementwise_div refactor

* fix compile bugs in windows ci

* disable copying of datatype when sharing buffer between two tensors.
* fix for mkldnn operator kernels (elementwise_add, sum, softplus, softmax, scale, activation), mannually set the data type when reusing memory by ShareBufferWith.

* elementwise_add kernel refactor

* fix compile bugs in elementwise_add refactor

* fix compile bugs when run in npu/xpu

* fix bugs when run unit test

* fix bugs when run ci-windows

* modify code as recommended

* code format adjust

* fix bugs when run ci

* fix compile bug when run in ci-windwos

* elementwise_sub refactor

* add PD_DLL_DECL for elementwise_sub

* fix bugs when compilei

* Change first batch of mkldnn headers and namespace names to dnnl

* Revert changes to tensor.h, which require approval

* Format changes with pre-commit

* Add int32 tests

* Fix int32 tests and call GetDataFromTensor for int32

* Fix test

* Add elementwise_mul triple grad kernel

* Removed InplaceInferer and polished code