* 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

* Refactor conv_kernel and conv_grad_kernel to provide interface for CUDNNv8 implementation

* Fix macro

* Add implementation for conv_kernel and conv_grad_kernel

* Modification after rebase onto latest develop

* Modify plan cache to comply with the API of phi::autotune

* Refactor to reduce duplicate code

* Review fix:
- move functions in  conv_kernel_impl_v8.h and conv_grad_kernel_impl_v8.h to conv_kernel.cu and conv_grad_kernelk.cu
- add const specifier for input tensor
- add logging when plans fail to execute
- move CudnnConvBwdFilterV8 and CudnnConvBwdDataV8 to conv_cudnn_frontend.h

* - move plan building outside of cache

* Fix ROCM build

* remove "gpu_primitives.h" in fluid namespace

* fix PR-CI-GpuPS fail

* fix PR-CI-GpuPS fail

* [NPU] add _npu_identity op and api, test=develop

* fix doc

* address comments

* standard api

* fix xpu bugs

* Implement a common dims simplifier.

* Fix the include position error.

* Reduce the cpu overhead of broadcast computing.

* rm "paddle/fluid/operators/math.h" in phi

* rm "paddle/fluid/operators/math.h" in fluit

Support bfloat16 for adamw and adam optimizer. Fit the lr for pure bf16 training with tensor fusion. (#48041)

* add bfloat16 for adamw

* set lr not to bfloat16 for pure bf16 training

* update the logic

* update the adamw optimizer

* support bfloat for adam

* add vectorized bfloat16 atomicAdd

* fix compile error

* fix compile error again

* fix V100 compile error

* fix V100 compile again

* [NPU] update npu prop, test=develop

* remove ddim.h

* remove diff

* update storage prop, test=develop

* simplify depthwise_conv2d phi kernel selection

* fix depthwise_conv2d

* Enable bf16 in oneDNN bilinear_interp kernel

* Fix bilinear_interp_v2 not enabled in models

* Remove unnecessary checks

* add stat tool

* add roll and roll_grad kernels and strided_slice and strided_slice_grad kernels, test=kunlun

* embedding and embedding_grad add int32 input, test=kunlun

* opt error message when selecting kernels under phi

* fix for loop

* polish error message

* polish error message, split into 3 error condition

* polish error message

* 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

* rm "paddle/fluid/platform/complex.h" in phi

* fix codestyle with pre-commit

* rm "paddle/fluid/operators/elementwise/xxx.h" in phi

* fix bugs

* add LaunchElementwiseCudaKernel in phi

* Revert "add LaunchElementwiseCudaKernel in phi"

This reverts commit 588f45bbdad2372ec7bff0c567a29bff675d22e1.

* rm indirect dependence to "elementwise_op_impl.cu.h"

rm indirect dependence to "elementwise_op_impl.cu.h"

Revert "add LaunchElementwiseCudaKernel in phi"

This reverts commit 588f45bbdad2372ec7bff0c567a29bff675d22e1.

add LaunchElementwiseCudaKernel in phi

fix bugs

* rm LaunchSameDimsElementwiseCudaKernel and LaunchElementwiseCudaKernel in phi

* [Zero-Dim] support input 0D Tensor as scalar attribute for some api

* fix doc

avoid copying