* Revert "Revert "【Hackathon No.67】remove operator.h in blas.h (#50989)" (#51467)"

This reverts commit b9d91531.

* remove cout

* add header

* fix missing header

* fix refer fluid error

* fix missing header

* 更新 repeat_interleave_grad_kernel_impl.h

Change to phi style datatype.

* 更新 repeat_interleave_grad_kernel_impl.h

Fix missing header

* datatype fluid -> phi

* paddle::experimental -> phi

* fix reference error

* fix reference error

* fix reference error

* fix errors

* fix missing FLAGS

* fix missing headers

* fix missing headers

* fix missing headers

* fix missing headers

* fix missing header

* fix missing header

* fix errors

* Enable matmul + bias fusion in fused_gat_attention.

* Add a variable to control whether using fused matmul + bias.

* support int64 non-broadcast

* support broadcast case for int64 index

* fix bug

* support more Arity

* remove some codes

* upgrade patchelf to v0.15.0 to pass CI build

* fix bug

* fix patchelf installation

* add debug flags

* remove useless codes

* fix viterbi_decode and set_value op uts

* remove always enable int64

* rename pten dir to phi

* rename namespace to phi

* rename infrt pten dir to phi

* resolve conflict

* rename pten to phi in cmake

* revert all infrt change

* change needed files

* fix infrt failed

* fix inference failed

* refine structure for cuda and rocm

* update

* update

* update

* update

* add get_cublas_handle() api

* update format

* add unittests

* alter function name

[BUG FIX] Fix softmax cross entropy overflow problem.

Add Retry Logic to CublasHandlerHolder to avoid random unittest failure.

Modify CublasHandleHolder from using PADDLE_ENFORCE_CUDA_SUCCESS to PADDLE_RETRY_CUDA_SUCCESS to fix random unittest failure. We checked that the unittest log showed CUDA allocation error at this file, which may due to GPU not enough. We fixed similar failure in the past, so we applied PADDLE_RETRY_CUDA_SUCCESS here.

* fix softmax_with_cross_entropy cuda kernel overflow bug, test=develop

* replace old macro & for condition, test=develop

* polish details, test=develop

* Optimize the error messages of paddle CUDA API, test=develop

* fix the error messages of paddle CUDA API, test=develop

* Refactoring PADDLE_ENFORCE_CUDA_SUCCESS, and apply to curand/cudnn/cublas/NCCL,test=develop

* remove build_ex_string,test=develop

* merge conflict,test=develop

* fix warnings oof gcc 8 compilation, test=develop

* fix boost::bad_get, test=develop

* refine PADDLE_ENFORCE, test=develop

test=develop

test=develop

test=develop

test=develop

* "re-commit "

* "picked up"

* "fix ci"

* "fix pdb hang up issue in cuda 9"

* add cuda_device_functions.h

* move reduceSum to elementwise_op_function.h

* Support int64 for sum op

* Refine code

* refind accuracy_op

* follow comments

* follow comments

1. finish lookup table CPU and GPU kernel
2. Add some cuda helper
3. Add some math funtor