* add warp transducer code

* move dropout_impl from fluid to phi

* move cuda_graph_with_memory_pool from fluid to phi

* update namespace

* remove cuad_graph in fluid

* fix mac-build

* fix bugs

* correct CodeStyle

* fix mac-build

* fix mutable_data

* fix stl include

* fix copy param

* nullptr bugfix for XPU pg mode

Also a few kernels is added to xpu whitelist

* increase error msg length

* fix codestyle

* add double complex<float> complex<double> dtype support for syevj_batched

* fix use_syevj flag for precision loss when input dtype of syevj_batch is complex128 in some case

* optimize eigh in different case

* fix missing ; bug

* fix use_syevj bug

* fix use_cusolver_syevj_batched flag

This is a PR to catch up with latest xpu white list strategy
(https://github.com/PaddlePaddle/Paddle/pull/48606)
, since original list only include 'fluid' fashion names, but new list
must include 'phi' fashion as well.
Refer to paddle/phi/core/kernel_factory.cc for more details.

* [XPU] add load op into oplist.

* remove test_sampling_id_op_xpu.py

* move cuda_graph from fluid to phi

* move device_memory_aligment from fluid to phi

* Revert "move device_memory_aligment from fluid to phi"

This reverts commit b92fcd39a0a50fdac13278f49be0237a85f3a13f.

* update xpu cmake

*test=kunlun

*test=kunlun

* migrate transpose_op.cu.h and gpu_utils.h

* format code style

* fix some problems

* format code

* reset tranpose_op.cc

* test commit

* recover transpose_op.h

* delete transpose_op.h

* adjust header files order in transpose_op.cc

some legacy code still use xpu_wait() for stream sync -- it only syncs
default stream. this PR replaces them with dev_ctx.Wait() to ensure
that correct stream is always used

* traspose2 kernel migrated

* Got rid of mutable_data

* x modification added

* ops added in extra info file

* Formatting fix

* 2 fuse passes with tanpose2 commented

* nr of outs changed in 2 passes, passes uncommented

* Changes in passes reverted

* transpose chnaged in operator.cc

* MKLDNN check in operator.cc

* Transpose fixes

* Fix deleted from operato

* template corrected
Co-authored-by: NPaulina Gacek <paulinagacek@intel.com>

* migrate enforce_custom.h from fluid to phi

* move to backends/custom/

* cleanup unused code

* unify is_int8 is_bfloat16

* Simplify matmul_v2 FWD kernel

* remove RunKernel methods

* remove import namespace

* remove headers

* clean fluid/phi cross imports

* remove fluid axpy_handler

* delete fluid methods

* activations

* OneDNNMemDesc

* MKLDNNFormatForSize

* MatchShapeToLayout

* MKLDNNMemoryFormat

* MKLDNNFormat

* ReorderMKLDNNHandler

* to_void_cast

* review suggestions

* interpolate

* remove fluid depedency

* init

* ExecuteMatMulV2

* rm fluid kernel

* matmul_grad

* remove mutable_data

* mul_grad

* matmul fwd

* add extra attr

* temp disable passes

* re-enable passes

* workaround for matmul+act

* fix for matmul+eltwise_add

* fix typo

* merge bugfix #48364

* remove merge conflict

* decouple cudnn_desc.h from fluid

* move cudnn_desc.h from fluid to phi

* fix bugs

* decouple cudnn_helper.h from fluid

* fix bugs

* move cudnn_helper.h from fluid to phi

* add fluid cudnn_helper.h

* move miopen_desc.h from fluid to phi

* move miopen_helper.h from fluid to phi

* fix bugs

* move gpu_dnn.h from fluid to phi

* fix bugs

* update copyright year

* simplify gpu_dnn.h in fluid

* fix bugs

* fix xpu build bug

* fix compile bug

* fix bug

* Fix onednn kernel bugs

* fix gpu bugs

* rm fluid “xpu_header.h” deps in phi

* move part of xpu_op_list.h from fluid to phi

* add fluid xpu_op_list deps

* add glog deps for xpu_op_list in phi

* fix PR-CI-Kunlun

* for xpu multi thread bug test

* make bfloat16 implicit convert to float/double

* fix bfloat16_test ut compile

* cleanup unused code

* unify is_int8 is_bfloat16

* Simplify matmul_v2 FWD kernel

* remove RunKernel methods

* remove import namespace

* remove headers

* clean fluid/phi cross imports

* remove fluid axpy_handler

* delete fluid methods

* activations

* OneDNNMemDesc

* MKLDNNFormatForSize

* MatchShapeToLayout

* MKLDNNMemoryFormat

* MKLDNNFormat

* ReorderMKLDNNHandler

* to_void_cast

* review suggestions

* interpolate

* remove fluid depedency

* init

* ExecuteMatMulV2

* rm fluid kernel

* matmul_grad

* remove mutable_data

* mul_grad

* cleanup unused code

* unify is_int8 is_bfloat16

* Simplify matmul_v2 FWD kernel

* remove RunKernel methods

* remove import namespace

* remove headers

* clean fluid/phi cross imports

* remove fluid axpy_handler

* delete fluid methods

* activations

* OneDNNMemDesc

* MKLDNNFormatForSize

* MatchShapeToLayout

* MKLDNNMemoryFormat

* MKLDNNFormat

* ReorderMKLDNNHandler

* to_void_cast

* review suggestions

* interpolate

* remove fluid depedency

* init

* ExecuteMatMulV2

* rm fluid kernel

* matmul_grad

* remove mutable_data

* move "paddle/phi/backends/gpu/gpu_device_function.h" to phi

* update copyright years

* rm "fluid/platform/device/gpu/gpu_device_function.h" in phi

* fix rocm-complie bugs

* correct sync behavior for XPU distributed training

XPU support event mechanism similar to cuda event, so it is advisable to
use an event to sync compute/comm streams for performance. However this
mechanism is never fully tested, and inconsistent loss/ending_epochs are
reported. Therefore, this PR replaces event sync with stream waiting as
a temporary solution.

* remove compile warning