* fix shared memory over usage in embedding grad kernel on determistic mode

* use IdT as interger dtype

* add deterministic embedding grad kernel

* minor change

* minor change

* Add new FLAG to enable deterministic embedding

* Update embedding deterministic kernel

* [enforce.h Decouple logging.h] Delete glog/logging.h from enforce.h

* Add logging.h for profiler.cc

* Add logging.h for gloo_utils.h

* Add logging.h for addmm_kernel_impl.h

* Add logging.h for addmm_grad_kernel_impl.h

* Add logging.h for p_send_kernel.cu

* Add logging.h for determinant_grad_kernel_impl.h

* Add logging.h for p_recv_kernel.cu

* Add logging.h for elementwise_grad_base.h

* Add logging.h for transfer_layout_kernel.cc

* Add logging.h for eigvals_kernel.cc and index_select_impl.h

* Add logging.h for all files in kernel directory

* Add logging.h for xpu_info.cc

* Add logging.h for xpu

* [enforce.h Decouple gflags.h] Move gflags.h from enforce.h to enforce.cc

* Add gflags.h for other files

* Add gflags.h for other files

* Add gflags.h for blas_impl.hip.h

* Add gflags.h for miopen_helper.h

* decouple memory copy

* fix ci bugs

* fix ci compile bugs

* fix rocm compile

* fix ci bugs

* support pure bfloat16

* support bf16 linear

* update PR to pass CI

* tiny fix where_grad_kernel.cu

* add bfloat16 to selu_grad to pass CI

* fix selu grad compilation error

resort .cu headers, set clang-format not sort include block and consider .cu as main source file (#43633)

* move embeding to phi;

* update sig; test=develop

* move reset impl to phi; test=develop

* remove old register; test=develop

* fix cpu bf16 bug; test=develop

* fix lookup speed error

* polish code

* fix paddle throw type