* rename kernel

* delete sig

* modify code according comment

* fix ci bugs

* Implement a common PointerArray.

* Polish codes.

* Add including of header file.

* Add the branch of kFix8.

* Fix compiling error.

* Add alignas hint to fix the performance drop.

* Optimize the H2D copy in stack_grad.

* Rename the macro.

* Fix align hint for different compilers.

* Polish the define of PADDLE_ALIGN.

* Fix compiling error.

* Remove the align hint on windows.

* add stack grad kernel optimization

* add basic optimization kernel for stack_grad_kernel

* optimization of stack_grad_kernel for last dim stack and change code format with pre-commit

* try sequence_padding

* fix cant use mutable_data

* fix mistake fluid_sequence_scale.hh/CMakeLists.t include

* fix namespace bug

* fix framework::ToAbsOffset not found

* fix codestyle

* add concat optimization

* refine

* remove annotation

* use alignas instead of aligned_storage

* migrate shaple sgd, split,sign xpu kernels to phi, test=kunlun

* fix dlrm throughput problem, test=kunlun

* add xpu einsum, fill_diagonal, and diagonal kernels, test=kunlun

* add bitwise and, bitwise not, bitwise or and bitwise xor

* correct typo

* add 0-d support for paddle.kthvalue

* add 0-d support for paddle.mode

* fix coverage test for device

* fix check-bug in windows

* change axis check from LT to LE

* add shape & value check for grad when input is 0d tensor

* support 0D for paddle.sort/argsort

* support 0D tensor for paddle.sort/argsort in xpu

* fix bug

* fix grad and add value assertion

* execute use kernel_key first

* change OpKernelType->KernelKey

* fix py3 compile error, remove redundant header files

* fix build_strategy_test

* fix DataType::RAW

* fix custom_type test: operator_test.cc

* fix transform place

* fix backends_are_same_class

* try fix place TransDataDevice

* support all KernelKey

* fix TransformData

* fix place_are_same_class

* fix merge

* fix test_params_no_grad

* fix specific place of GetExpectedKernelType

* fix specific place of GetExpectedKernelType

* fix GetKernelTypeForVar

* fix dtype error

* fix fetch_v2

* change GetKernelTypeForVar

* fix interpreter

* fix typo error

* polish codes

* polish codes

* polish codes

* fix conflict

* Implement conv2d_fusion NHWC format using CUTLASS
* Add unit testing for CUTLASS Conv in inference
* Add experimental API for CUTLASS.

* Use BroadcastKernel and ReduceKernel to optimize expand and expand_grad.

* Correct the axis when there is only 1 input in BroadcastKernel.

* Add the calculate of output's shape.

* 1219

* temporarily change the num_diff_files limit, test=document_fix

* Revert "temporarily change the num_diff_files limit, test=document_fix"

This reverts commit 8e70f00ef468d2dad0e38b3da06295ed62990d20.

* for codestyle

* remove duplicate license

* `static mode` -> `static graph mode`

* Update hybrid_parallel_inference.py

* Update layer_function_generator.py

* Update manipulation.py

* reset
Co-authored-by: NLigoml <39876205+Ligoml@users.noreply.github.com>
Co-authored-by: NSigureMo <sigure.qaq@gmail.com>

* fix fold for large bs

* fix fold for large bs

This reverts commit e1e8bf72.

* migrate shaple sgd, split,sign xpu kernels to phi, test=kunlun

* fix dlrm throughput problem, test=kunlun

* revert concat and change concat to stack

* let stack kernel support int8, uint8 and bool type

* fix matmul double and triple grad

* remove some comment

* add matmul_double_grad unit test

* fix matmul triple grad

* fix dot triple grad and add unit test

* modify codestyle

* fix dot_grad

* refactor dot triple grad

* disable some unit test

* fix unit test

* fix unit test in double grad

* add warp transducer code

* register half datatype

* register roll grad fp16 kernel

* Optimize performance of batch_norm_bwd with NHWC layout and infer mode

* fix