* move bincount OP to phi

* fix dtype

* set_dtype by weights or x

* fix conflicts

* Added cuBlasLtHandle_t to device context.

* Added fused_gemm_epilogue op.

1. Added fused_gemm_epilogue op to leverage cuBlastLt Epilogue.
2. Support fusion Act(X*Y + bias), X'dims >=2 and Y'dims shoule be 2.
2. Act currently only be supported ReLU. (Will add GeLU in the future).

* Added UT to fused_gemm_epilogue op.

* Added LinearAct Pattern

1. Added LinearAct into graph_pattern_detector.* to define (2.)'s
pattern.
2. LinearAct is used to detect act(element_add(matmul_v2(x, w), bias)).
3. act currently only support ReLU (Will support GeLU in the future).

* Added FuseGemmEpiloguePass

1, Added FuseGemmEpiloguePass to handle nn.Linear + Act{ReLU}
fusion (GeLU will be supported in the future).
2. Only support matmul_v2 from nn.Linear.

* Added pybind to BuildStrageter.fuse_gemm_epilogue_.

* Added UT for fuse_gemm_epilogue_pass.

* GeLU support and EpilogueSingleton

1. Added GeLU support to fused_gemm_epilogue op.
2. Added EpilogueSingleton to cache auxiliary pointer.
3. Added related UTs.

* Rename cublaslt_epilogue_opto gemm_epilogue_op.*.

* Added both train and infer pattern to LinearAct.

1. Added support of fwd graph with grap_ops linking to LinearAct.
2. Added related changes to fuse_gemm_epilogue_pass for above
modification.

* Changed CUDA requirement from 11.4 to 11.6 for fuse_gemm_epilogue_pass.

* Added identity activation support to gemm_epilogue_op.

* Added Linear Fusion (matmul_v2 + ele_add)

1. Added matmul_v2 + ele_add pattern to LinearActPattern.
2. Added matmul_v2 + ele_add support to fuse_gemm_epilogue_pass.

* Rename gemm_epilogue_op.* to fused_gemm_epilogue_op.*

* Add fused_gemm_epilogue_grad op.

1. Added fused_gemm_epilogue_grad to support backward epilogue fusion.

* Add UTs to fused_gemm_epilogue_grad_op.

* Change attribute name in fused_gemm_epilogue_grad_op for clearing.

* Allow DX and DBias be dispensable to fused_gemm_epilogue_grad op.

* Added ElementwiseAdd+Matmul+Act graph pattern detection.

* Fuse backward of Linear( Act(x))

1. Added backward fusion pass to Linear( Act(x)).
2. Added backward fusion pass to Linear(x).

* Added UTs to backward fusion of Linear(Act(x)).

* Complete document of arguments to fused_gemm_epilogue_op.

* Made arguments of some functions pass by reference.

* Modify code with review comments.

1. Made arguments of some function pass by reference.
2. Removed redundant code.
3. Followed Google code style to change code.

* Made 'const' code style be consistent

* Fixed random seed of python UTs.

* Set Compiling constrains to cuBlasLt

1. Require CUDA 11.6+
2. Remove fuse_gemm_epilogue related tests when CUDA < 11.6.

* Code Reivew from Paddle

1. Changed arguments name is_first_gemm to without_x_gradient for
clearing.
2. Applied PADDLE_THROW in fused_gemm_epilogue_op.

* Remove EpilogueSingleton

1. Applied ReserveSpace to replace Epilogue for passing auxiliary
pointers between FWD and BWD.

* Fix a logical error and enhance UTs.

1. Added act op count checking in UTs.
2. Fix issue to fuse backward or ReLU(Linear(X)).
3. TODO: solve GELU fusion issues.

* Fix Linear and GeLU fusion issues.

1. Modified graph_detech_pattern to fit with both linear wiht gelu or
relu.
2. Modified data range in Uts to allow negative values.

* Removed fused_gemm_epilogue_op.h.

* Rename namespace pten to phi.

* Rename name of arguments in fused_gemm_epilogue_op

1. bias -> Bias.
2. out -> Out.
3. reserve_space -> ReserveSpace.

* Change EpiloguePassActivationCache as local variable.

1. Removed singleton in EpiloguePassActivationCache.
2. Made EpiloguePassActivationCache as an argument to each pass
functions.

* Add is_empty

* fixed for CI

* fixed code style

* resolve conflict

* deal with comments

* replace pt by pd

* move elementwise_div grad

* change mutable_data to alloc

* fix compile bugs

* remove storage deps of empty

* remove invalid empty method

* remove error empty using

* fix test_sparse_utils_dev_api

* revert some sparse change

* add memset for conv grad

* resolve conflict

* resolve conflict

* resolve conflict

* add gaussian random

* add full

* refine reduce

* refine code

* refine gaussian_random unittest

* add unittest for fill_any_like fill_constant

* [phi] move multi_dot OP

* fix the segment bug

* fix bug

* delete useless comment

* fix CI bug

* add activ

* refine unittest

* refine unittest

* refine unittest

* refine unittest

* refine code

* [Phi]Migrate Adamax into phi

* Add adadelta kernel

* replace prefix pt by pd

* replace added kernel

* revert util change

* pd kernel to phi

* resolve conflict

* resolve conflict

* move dist op to phi

* fix

* fix

* fix as reviews

* Migrate triangular_solve op into phi

* fix CI

* move MatrixReduceSum to phi funcs

* move MatrixReduceSum to phi funcs

* fix comment

* fic CI

* remove eig dep for svd helper

* fix win failed

* [Phi] move infershape for mv

* [Phi] delete extra codes for mv

* add yolo box kernel; test=develop

* fix comile error; test=develop

* move selected_rows kernel head to selected_rows dir

* update license

* add sr namespace

* refacter selected_rows kernel funciton name

* fix bug

* move gather_nd/scatter/scatter_nd_add

* fix npu/xpu ci

* follow comments

* small fix

move cpu_vec.h to phi/kernels/funcs.

[Phi] move gaussian_random, fix fp16

* move sigmoid cross entopy with logits to phi

* fix ci

* move log_loss to phi

* move cumsum to phi

* revert infershape

* fix xpu ci

* move auc to phi

* remove comment

* update sigmoid_cross_entropy_with_logits_op.cu

* update sigmoid_cross_entropy_with_logits_op

* Update log_loss

* add digamma, abs, trunc; test=develop

* fix bug and add diagonal; test=develop

* add name coverter; test=develop

* update tracer.py; test=develop

* add test case; test=develop

* fix bugs; test=develop

* fix bug caused by split infershape

* revert infer_shape of split

* revert split

* remove cholsky solve deps with svd helper

* fix shape infer bug

* Migrate bitwise_and/or/xor/not op into phi

* fix CI

* clean distribution_helper, index_impl, aligned_vector code in fluid

* fix conflicts

* move reduce gpu impl funcs into pten/kernels/funcs

* change reduce header name and namespace

* fix spell word error

* change mutable_data to dev_ctx.Alloc

* modify place to devcontex

* format code style

* fix build error

* fix build error

* fix conflict

* change input vec tensor to pointer

* update input between

* fix format error

* resolve conflict

* resolve conflict

* move conv to pten

* move conv to pten; test=develop

* fix bug;

* add conv cudnn impl; test=develop

* update

* update operator; test=develop

* fix bug; test=develop

* move operator and prepared_operator to develop; test=develop

* resolve conflict; test=develop

* remove useless code;test=develop

* add depency ; test=develop

* fix bug;

* add sig.cc ; test=develop

* fix use_op error; test=develop

* fix bug; test=develop

* fix bug; test=develop

* add conv3d register; test=develop

* fix star gan and conv_nn_grad test failed; test=develop

* add header; test=develop

* manul to recover to develop;

* resolve confilct; test=develop

* remove useless code

* fix bug;

* remove conv2d_cudnn; test=develop

* fix bugs; test=develop

* fix cpu rocm compile bugs; test=develop

* fix blas error; test=develop

* fix compile bug; test=develop

* fix windows compile error; test=develop

* fix windows error; test=develop

* resolve confilct; test=develop

* Move compare OPs to phi

* Fix bug

* Use BroadcastKernel and ElementwiseKernel in phi

* delete elementwise_sub kernel registry

* fix compile bugs in xpu ci

* fix bugs when run inference ci

* add pad forward

* fix error

* transfer pad and pass the test_pad_op

* suppport sparse api in yaml

* support auto-gen code of sparse api

* do some refactor

* add unittest test_sparse_conv_api

* add unitest file
Co-authored-by: Nzkh2016 <zhangkaihuo@baidu.com>

[Phi] move gaussian_random kernel

1. set xpu2 block_size = 64
2. fix a bug when reduce_num is too large

* sparse conv3d: gpu code