* refactor matmul directory in pten

* fix merge conflict

* add dot_grad kernel

* add dot_grad kernel in pten

* add matmul_grad kernel

* update the code

* delete useless code in fluid

* fix some bug of running matmul grad kernel

* fix merge conflict

* refactor some code

* refactor code

* refactor flatten grad kernel

* fix bugs when run ci unittest

* fix bugs when use default GetExpectedPtenKernelArgs

* xshape sometimes is has null holder ,fix this bugs

* move mid api and rename kernel

* use empty kernel

* move eigen/reduce.h imple into cpu/reduce.h

* ctx to dev_ctx

* adjust the full kernel

* remove creation.h

* use Empty to create tensor in full

* move gpu_impl of elementwise kernel

* change copyright to 2022

* change 'math' to 'math_kernel'

* fix compile bugs

* merge develop

* fix compile bugs

* fix compile bugs

* move reduce files by new rule

* add set header

* format code style

* merge develop and fix conflict

* merge develop and fix conflict
Co-authored-by: NYuanRisheng <yuanrisheng@baidu.com>

* polish infermeta filename

* polish infermeta filename

Add OpFunctor and replace cast, scale, clip, bce_loss and abs_grad with elementwise_no_broadcast (#38500)

* change 'math' to 'math_kernel'

* fix compile bugs

* merge develop

* fix compile bugs

* move cpu_impl of elementwise kernel to new directory

* move inner cast api to cast_kernel.h

* resolve conflit

* change 'math' to 'math_kernel'

* fix compile bugs

* merge develop

* fix compile bugs

* first commit

* pass ctest of  elementwise_div_grad

* refactor matmul directory in pten

* fix merge conflict

* remove intype arg in cast kernel

* modify conj config in api.yaml by dictionary order

* rm unused code in cast_kernel.cu

* move reshape

* fix compile bugs

* delete manipulation file

* fix compile bugs

* No harm to KP

* Pass the compile stage

* change the WriteData function

* fix template bugs and pass ctest of current elementwise

* for passing partial template specialization of tempalte function in CI-ROCm

* To make 'WriteData' funtion flexible.

* a less harmful way to support multi-output

* a less harmful way to support multi-output

* rename to api to copy_to

* revert needless change

* polish format

* add register general kernel marco

* move copy kernel impl

* revert needless change

* polish details

* fix xpu compil faild

* fix xpu compile failed

* polish format

* combine reduce_cuda codes

* support float16 in pten redcue_mean

* replace ReduceCudaKernel impl with pten reduce impl

* mv reduce funcs into reduce_cuda_impl

* rm unsed codes and headers

* mv GetReduceDim into reduce_cuda_impl

* recover GetReduceDim in reduce_op.h

* add new dispatch macro

* fix pool op output not inited and cause transform to pten::denseTensor error

* fix output tensor not initialized error

* rename new dispatch macro and format code style

* rm reduce_functor_op.h file

* add empty and empty_like kernel in pten

* add empty dev_api

* move dot kernel impl

* remove needless cmake items

* change functions to funcs

* remove useless code

* add pten kernel cmake

* add pten kernel cmake function

* fix compile error

* add enforce include for full kernel

* fix compile failed

* change cuda to gpu

* fix cmake function error

* move flatten

* fix bugs of test

* modify header file

* add copy declare

* fix compile bugs

* rename cuda to gpu

* revert CMake change

* resolve conflit

* rename other cuda to gpu

* poish details

* fix when out_dtype is same with x.dtype and still transform type error

* fix spell error

* remove eigen and blas dir

* fix declare error