* Update the content of `test_parallel_executor_run_cinn.py`.

* Fix some bugs in the topological sort and `CreateNewSubGraph`.

* Update the CINN commit id used by Paddle.

* Update the unit test to `add+relu`.

* Update according to reviewers' suggestion.

* add eigvalsh with is_test

* add eigvalsh op

* fix backward bug

* forward and backward, float and complex, unittest

* remove eigvalsh_helper.h

* remove changes of cusolver.h

* fix unittest

* fix unittest bug

* update code following eigh

* fix test

* update lapack

* pull develop

* update funcor

* fix unittest bug

* fix details

* add tensor_method_func

* fix notes

* add some ops to train ssd on kunlun

* add some ops to train ssd on kunlun

* add some ops to train ssd on kunlun

* update cast op unittest

* update cast op unittest

* update cast op unittest

* update xpu cmake

* update cast unittest

这个PR只包含fused_feedforward前向的代码。

相关kernel实现：fused_dropout_act_bias, fused_residual_dropout_bias, fused_layernorm_residual_dropout_bias

fused_feedforward是一个融合算子，该算子对transformer模型的feed forward层的算子进行融合和封装，使得前端只呈现一个接口，通过融合减少部分访存和kernel launch的时间，以此提升性能。

This PR added some changes to match the CINN change for compilation. It also tried to fix JiangCheng's Problem in PR: https://github.com/PaddlePaddle/Paddle/pull/36100

These changes include:
1. Set `CINN_GIT_TAG` to a newer tag
2. CINN now just `make cinnapi -j`
3. We have to add `-DPY_VERSION=${PY_VERSION} -DWITH_TESTING=ON` to CINN cmake args
4. For CINN's third party dependencies, we could just include headers without target_link_libraries
5. Moved `cinn.cmake` from `paddle/cmake` to `paddle/cmake/external` to match old style. External folder contains `lite`, which is the same level of `cinn`
6. CINN added `-DNAMESPACE=cinn_gflags` in `gflags.cmake` to have different gflag namespaces between CINN and Paddle. It solved re-define problem.
7. Change namespace of `::google::` in gflags to `::GFLAGS_NAMESPACE`

功能：本PR的目标是提高attention模块的计算性能。
为了减少框架层对op的调度开销，本PR通过在C++层手动实现attention模块，对外提供attention 大op；
为了减少防存开销，本PR采取了两种优化方法：
（1）在q,k,v计算时通过共享输入X，将该处的gemm，transpose和bias add从三次调用减少为一次；
（2）使用kernel融合优化技术，在不同cuda kernel之间通过寄存器传输数据；

Add Tokenizer related functionalities for Transformer model in order that the process of training and predicting is consistent.

* support the text string as an input Tensor
* support the "VOCAB"unordered_map<wstring, int> as an input Tensor to lookup tokens
* Tokenizer used for BERT. This tokenizer applies an end-to-end, text string to wordpiece tokenization.
* It first applies basic tokenization, followed by wordpiece tokenization.

Add CINN compile option in CMake.

Now you can use CINN in Paddle by `-DWITH_CINN=ON` when `cmake`

To test it, you can run `make cinn_lib_test -j` and `ctest -R cinn_lib_test`. 

Note:
1. You should set
```
export runtime_include_dir=${CINN_SOURCE_DIR}/cinn/runtime/cuda 
```
When run test, the `${CINN_SOURCE_DIR}` should be set based on your CINN directory.

2. CINN is under developing now, you may have to change `CINN_GIT_TAG` to the git commit you need.

* [NPU] update inference cmake, test=develop

* address review comments, test=develop

* fix compile error when WITH_ASCEND_CXX11 ON, test=develop

* Add QR decomposition op

* Change codes to adapt to new svd_helper

* Update linalg.py

Restore the deleted comma

* Restore the deleted line

* Update linalg.py

* Update linalg.py

* Improve the qr code by reviews

* Update QR based on CI results

* Update qr doc, test=document_fix

* Change unsafe and ill-formed codes

* support bert when exists matmul_v2

* update

Add sparse_attention OPs, python api will be added in next pr

* add argmax and iou_similarity for kunlun

* add argmax and iou_similarity for kunlun

* add argmax and iou_similarity for kunlun

* support extern third_party lapack on Linux/Windows/Mac

* fix ci

* 1. add interface for fft;
2. add data type predicate;
3. fix paddle.roll.

* add fft c2c cufft kernel

* implement argument checking & op calling parts for fft_c2c and fftn_c2c

* add operator and opmaker definitions

* only register float and double for cpu.

* add common code for implementing FFT, add pocketfft as a dependency

* add fft c2c cufft kernel function

* fix bugs in python interface

* add support for c2r, r2c operators, op makers, kernels and kernel functors.

* test and fix bugs

* 1. fft_c2c function: add support for onesided=False;
2. add complex<float>, complex<double> support for concat and flip.

* 1. fft: fix python api bugs;
2. shape_op: add support for complex data types.

* fft c2c cufft kernel done with complie and link

* fix shape_op, add mkl placeholder

* remove mkl

* complete fft c2c in gpu

* 1. implement mkl-based fft, FFTC2CFunctor and common function exec_fft;
2. change the design, add input and output typename as template parameter for all FFTFunctors, update pocketfft-based implementation.

* complete fft c2c on gpu in ND

* complete fft c2c on gpu in ND

* complete fft c2c backward in ND

* fix MKL-based implementation

* Add frame op and CPU/GPU kernels.

* Add frame op forward unittest.

* Add frame op forward unittest.

* Remove axis parameter in FrameFunctor.

* Add frame op grad CPU/GPU kernels and unittest.

* Add frame op grad CPU/GPU kernels and unittest.

* Update doc string.

* Update after review and remove librosa requirement in unittest.

* Update grad kernel.

* add fft_c2r op

* Remove data allocation in TransCompute function.

* add fft r2c onesided with cpu(pocketfft/mkl) and gpu

* last fft c2r functor

* fix C2R and R2C for cufft, becase the direction is not an option in these cases.

* add fft r2c onesided with cpu(pocketfft/mkl) and gpu

* fix bugs in python APIs

* fix fft_c2r grad kernal

* fix bugs in python APIs

* add cuda fft c2r grad kernal functor

* clean code

* fix fft_c2r python API

* fill fft r2c result with conjugate symmetry (#19)

fill fft r2c result with conjugate symmetry

* add placeholder for unittests (#24)

* simple parameterize test function by auto generate test case from parm list (#25)

* miscellaneous fixes for python APIs (#26)

* add placeholder for unittests

* resize fft inputs before computation is n or s is provided.

* add complex kernels for pad and pad_grad

* simplify argument checking.

* add type promotion

* add int to float or complex promotion

* fix output data type for static mode

* fix fft's input dtype dispatch, import fft to paddle

* fix typos in axes checking (#27)

* fix typos in axes checking

* fix argument checking (#28)

* fix argument checking

* Add C2R Python layer normal and abnormal use cases (#29)

* documents and single case

* test c2r case

* New C2R Python layer normal and exception use cases

* complete rfft,rfft2,rfftn,ihfft,ihfft2,ihfftn unittest and doc string (#30)

* Documentation of the common interfaces of c2r and c2c (#31)

* Documentation of the common interfaces of c2r and c2c

* clean c++ code  (#32)

* clean code

* Add numpy-based implementation of spectral ops (#33)

* add numpy reference implementation of spectral ops

* Add fft_c2r numpy based implementation for unittest. (#34)

* add fft_c2r numpy implementation

* Add deframe op and stft/istft api. (#23)

* Add frame api

* Add deframe op and kernels.

* Add stft and istft apis.

* Add deframe api. Update stft and istft apis.

* Fix bug in frame_from_librosa function when input dims >= 3

* Rename deframe to overlap_add.

* Update istft.

* Update after code review.

* Add overlap_add op and stft/istft api unittest (#35)

* Add overlap_add op unittest.

* Register complex kernels of squeeze/unsquuze op.

* Add stft/istft api unittest.

* Add unittest for fft helper functions (#36)

* add unittests for fft helper functions. add complex kernel for roll op.

* complete static graph unittest for all public api (#37)

* Unittest of op with FFT C2C, C2R and r2c added (#38)

* documents and single case

* test c2r case

* New C2R Python layer normal and exception use cases

* Documentation of the common interfaces of c2r and c2c

* Unittest of op with FFT C2C, C2R and r2c added
Co-authored-by: lijiaqi <lijiaqi0612@163.com>

* add fft related options to CMakeLists.txt

* fix typos and clean code (#39)

* fix invisible character in mkl branch and fix error in error message

* clean code: remove docstring from unittest for signal.py.

* always convert numpy array to paddle.Tensor to avoid comparing numpy dtype with paddle dtype. (#40)

* always convert numpy array to paddle.Tensor to avoid comparing numpy dtype with paddle dtype.

* fix CI Errors: numpy dtype comparison, thrust when cuda is not available (#41)

1. always convert numpy array to paddle.Tensor to avoid comparing numpy dtype with paddle dtype.
2. promote floating point tensor to complex tensor ior fft_c2c and fft_c2r;
3. fix unittest to catch UnImplementedError and RuntimeError;
4. fix compile error by avoid using thrust when cuda is not available.
5.  fix sample code, use paddle.fft instead of paddle.tensor.fft

* remove inclusion of thrust, add __all__ list for fft (#42)

* Add api doc and update unittest. (#43)

* Add doc strings.
* Update overlap_add op unittest

* fix MKL-based FFT implementation (#44)

* fix MKL-based FFT implementation, MKL CDFT's FORWARD DOMAIN is always REAL for R2C and C2R

* remove code for debug (#45)

* use dynload for cufft (#46)

* use std::ptrdiff_t as datatype of stride (instead of int64_t) to avoid argument mismatch on some platforms.

* add complex support for fill_zeros_like

* use dynload for cufft

* Update doc and unittest. (#47)

* Add doc of frame op and overlap_add op.

* Update unittest.

* use dynload for cufft (#48)

1. use dynload for cufft
2. fix unittest;
3. temporarily disable Rocm.

* fix conflicts and merge upstream (#49)

fix conflicts and merge upstream

* fix compile error: only link dyload_cuda when cuda is available (#50)

* fix compile error: only link dyload_cuda when cuda is available

* fix dynload for cufft on windows (#51)

1. fix dynload for cufft on windows;
2. fix unittests.

* add NOMINMAX to compile on windows (#52)

 add NOMINMAX to compile on windows

* explicitly specify capture mode for lambdas (#55)

 explicitly specify capture mode for lambdas

* fix fft sample (#53)

* fix fft sample

* update scipy and numpy version for unittests of fft (#56)

update scipy and numpy version for unittests of fft

* Add static graph unittests of frame and overlap_add api. (#57)

* Remove cache of cuFFT & Disable ONEMKL (#59)

1. replace numpy.fft with scipy.fft as numpy<1.20 not support ortho norm
2. remove cache of cufft plans;
3. enhance error checking.
4. default WITH_ONEMKL to OFF
Co-authored-by: Njeff41404 <jeff41404@gmail.com>
Co-authored-by: Nroot <root@bjyz-sys-gpu-kongming9.bjyz.baidu.com>
Co-authored-by: NKP <109694228@qq.com>
Co-authored-by: lijiaqi <lijiaqi0612@163.com>
Co-authored-by: NXiaoxu Chen <chenxx_id@163.com>
Co-authored-by: Nlijiaqi0612 <33169170+lijiaqi0612@users.noreply.github.com>

* new function: share third party cache among servers to fasten build speed

* modified code according to zhouwei25's comment

* add wget install step, move cd build to the last of if condition

* block note and error of third_party share; change bce upload method

* change third_party sub_dir in bos, since third party in different cuda version cant share

* set sub_dir by get nvcc version

* change third_party local path to be same with bos path

* init matrix_rank op, add matrix_rank CPU code and test

* add GPU kernel, remove svd_eigen.h

* add CPU kernel when tol is tensor

* add cpu and gpu code when tol is tensor

* fix CI-ROCM error

* add matrix_rank API describe, fix PR-CI-Py3 error

* fix PR-CI-Windows error, add matrix_rank API test

* delete useless comments

* fix review

* add my code in svd_helper.h

* update doc commets

* remove spaces

* [NPU] add int64 kernels, test=develop

* update ci scripts to be able to trun WITH_ASCEND_INT64 on, test=develop

* Add SVD Op and it's GPU and CPU kernel

* Remove CUDAPlace in test_svd_op, make the test available in CPU package

* modfity the file

* fix windows bug/ fix ROCM / fix test timeout

* for pass the CIs

* improve error report

* for code review

* some modification to test_svd_op

* change python code style

* expose the svd interface for document

* support KL label smooth

* update UT for KL label_smooth

* Revert "Revert "Add copy from tensor (#34406)" (#35173)"

This reverts commit 32c1ec42.

* add template instantiation

[Background]
Expansion in code size can be irreversible in the long run, leading to huge release packages which
not only hampers user experience but also exceeds a hard limit of pypi.

In such, NV_FATBIN section takes up 86% of the compiled dylib size, owing to the vast number of GPU
arches supported.

This PR aims to prune this NV_FATBIN.

[Solution]
In the new release strategy, two types of whl packages will be involved:

Cubin PIP package:
PIP package maintains a smaller window for GPU arches support, containing
sm_60, sm_70, sm_75, sm_80 cubins, covering Pascal - Ampere arches

JIT release package:
This is a backup for Cubin PIP package, containing compute_35, compute_50, compute_60,
compute_70, compute_75, compute_80, with best performance and GPU arches coverage.

However, it takes around 10 min to install due to the JIT compilation.

[How to use]
The new release strategy is disabled by default.
To compile for Cubin PIP package, add this to cmake: -DCUBIN_RELEASE_PIP
To compile for JIT release package, add this to cmake: -DJIT_RELEASE_WHL

* fix CI skip cc test error, test=develop

* remove test code, test=develop

This reverts commit ac33c0ca.

* add api

* temp save

* revert

* copytocpu async ok

* fix style

* copy sync ok

* fix compile error

* fix compile error

* api done

* update python async api

* fix compile

* remove async python api; add c++ async unittest

* remove python async api

* update unittest

* update unittest

* add C++ unittest for copytensor

* add unittest

* update namespace utils to class TensorUtils

* add unittest

* update unittest

* update unittest

* update code style

* update code style

* update unittest