[cherry pick] Support optional residual add in fused ops and slice large tensor for cudnn_softmax (#43719)

 [cherry pick] Support optional residual add in fused ops and slice large tensor for cudnn_softmax

cherry-pick #43635 #43681 #43474

* Rename dropout is test (#43098)

* replace dropout_is_test with is_test.
* improve atol on a100.

* fused_attention fused_feedforward api support Model Tensor Parallel (#42985)

* fix is_test bug in fused_feedforward. (#43508)
Co-authored-by: NLi Min <11663212+limin2021@users.noreply.github.com>

删除Broadcast function中rank例化以及Elementwise调用，降低编译时间。
从develop分支中的#42645 PR修改而来，由于develop分支与release分支相差较大，无法实现cherry-pick，因此针对release2.3重新提交PR.
Broadcast中关于rank的例化会导致底层模板展开较多，造成reduce_sum_grad_kernel.cu.o文件体积过大，修改后可以降低.o体积及编译时间

* Fix test_cudnn_norm_conv and test_cudnn_bn_add_relu in CUDA11.2

* no throw in V100 for some cases

* fix FusedResidualDropoutBias nan in v100 (#42344)

* fix lod_tensor_array gc (#42377)

[cherry-pick 2.3] Add fused_multi_transformer op to optimize transformer generation performance (#42311)

* Add fused_multi_transformer op to optimize transformer generation performance (#41814)

* fix fused_multi_transformer compile failed in cuda arch < sm53 (#42315)

* fix ci timeout

Cherry-pick #40338 #41741 #41313

* add fused_seqpool_cvm op;test=develop

* add infer meta; test=develop

* add histogram infer meta; test=develop

* fix unitest bug; test=develop

* format; test=develop

* format; test=develop

* bn not use new infer meta; test=develop

* add infer meta; test=develop

* fixbug; test=develop

* fix bug;

* recover unitest; test=develop

* update

* fix bugs; test=develop

* update; test=develop

* fix test compile error; test=develop

* fix cpu compile error; test=develop

* fix test error; test=develo

* fix layer_norm_op plugin error; test=develop

* fix error; test=develop

* fix test bug; test=develop

* update; test=develop

* polish code; test=develop

* fix bugs; test=develop

* remove unused depency; test=develop

* polish code; test=develop

* remove needless deps in unittests

* add gpu marco

* fix other unittests

* fix kernel name error

* fix test_prepare_op

* fix failed dygraph unittests

* fix gpu failed tests

* fix cinn test failed

* fix cinn test failed

* fix dropout tests

* move dropout to phi; test=develop

* fix xpu, npu compile error; test=develop

* Add throw for norm_conv when platform is not supported

* fix format

* 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.

move cpu_vec.h to phi/kernels/funcs.

* 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

* 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

* add pad forward

* fix error

* transfer pad and pass the test_pad_op

* add bn cpu version; test=develop

* move batch norm to pten

* move batch norm to pten; test=develop

* fix bug; test=develop

* fix func::tranpose depend bug; test=develop

* fix compile bugs; test=develop

* fix use_op batch_norm bug; test=develop

* fix cudnn bn add relu test; test=develop

* fix pten context build and double grad bug; test= develop

* remve useless code; test=develop

* add batch norm gpu fp16 support; test=develop

* fix test bn op bug; test=develop

* remove output dtype set; test=develop

* fix bug; test=develop

* fix bug; test=develop

* fix applay pass to program bug; test=develop

* revert to develop; test=develop

* fix rocm bug; test=develop

* revert operator to develop; test=develop

* fix pre_commit; test=develop

* fix statci check error; test=develop

* resolve conflict; test=develop

* ana batch norm bug;

* revert batch norm op

* resolve conlict

* fix nan inf and speed bug; test=develop

* fix bug; test=develop

* fix error; test=develop

* test expand op; test=develop

* fix bug; test=develop

* resolve confilct

* resolve confilct; test=develop

* polish code; test=develop

* polish code; test=develop

* change mutable data to ctx alloc; test=develop

* make format same with ci; test=develop

* fix format error with ci; test=develop

* move sequence2batch

* move lstm and gru

* Add phi/kernels directory into exclusion to stop using hipcc to compile non .cu files in it.

* rename pten_utils to phi_utils

* rename pten_utils target

* rename Pten to Phi

* replace pten with phi

* resolve conflict

* support cudnn kernel moving

* polish cmake rules

* add unittest for coverage

* remove orig kernel

* remove softmax cudnn kernel

* fix softmax test failed

* fix npu func error

* resolve conflict

* rename gpu dnn kernels

* fix name rule error

* fix compile error

* update fp16 namespace

* change Vector to std::vector and provide MixVector class as a helper wrapper class

* solve the multi-gpu hang problem

* remove the duplicate template instantialize

* Copy vector to cpu

* add CopyToCPU

* xxx

* final version: fix the problem of all reduce

* remove mixvector dependence

* fix

* merge

* fix code

* fix by CI

* rename pten dir to phi

* rename namespace to phi

* rename infrt pten dir to phi

* resolve conflict

* rename pten to phi in cmake

* revert all infrt change

* change needed files

* fix infrt failed

* fix inference failed

* Unify paddle/pten::framework::ddim into pten::ddim

* fix paddle namespace

* compile sucessfully

* fix npu src file

* fix conflict

* fix conflict

* fix tensorrt compiler error

* fix conflict

* fix conflict

* fix tesst file conflict

* fix conflict

* fix mlu file conflict

* fix mlu file conflict

* fix cinn header file conflict

* fix conflict

* fix conflict

* fix conflict

* fix conflict

* move blas related files
* move lapack related files

* move paddle/operators/math/functors.h
* move paddle/operators/math/compound_functors.h

* #1 migrate dist-related type()-> dtype()

* move datatype function from pten -> fluid/framework

* change type() in imperative into convert(dtype())

* modify xx_tensor->type into xx_tensor->dtype

* change the set_type interface and the caller

* modify xx_tensor.type into xx_tensor.dtype

* fix mutable_data(place, dtype())

* change caller of mutable_data in pten and distributed

* change the caller of mutable_data in fluid/framework

* change the caller of mutable_data in imperative directory

* mutable_data: inference

* update the call of mutable_data

* transfer MakePenScalarArray MakePtenScalar ResetHolderWithType

* pass the compile. the next step is remove VarType in Pten

* fix all and remove VarType from pten. success in linux. Next task is other platform

* fix conflict with develop

* fix compiled error

* Fix reset conversion

* fix conflict

* fix compiled problem

* fix typo

* Fix << in tensor_utils.cc

* fix type->dtype

* fix unittest

* fix tensor init constructor

* fix DataTypeSize for BFloat16

* fix code style

* fix npu compiled error

* fix npu

* compile npu sucessfully

* fix conflict

* fix conflict
Co-authored-by: Nxiongkun <xiongkun03@baidu.com>

* move operators/math/math_function_* to pten/kernels/func
* namespace from `paddle::operators::math` to `pten::funcs`

* Add fp16 support for scale/bias for fused_layernnorm_residual_dropout_bias op.

* Remove useless code.

* Remove useless code.

* Optimize layer_norm fwd when cols is 1024.

* Remove useless code.

* Minors.

* Minors.

* Modifications accordding to reviews.

* Minors.

* Optimize layer_norm bwd kernel when cols is 1024.

* Polish layer_norm_bwd_1024 kernel.

* Limit ln_bwd_1024_kernel to paddle_with_cuda.

* Fix double type compile error.

* Add optimization of ln bwd for fused_dropout_add_ln op.

* Polish codes.

* update cmake file to remove fluid kernel

* add pten declaration.h to where pybind.h used

* fix sync_bn and tensorrt_engine

* refine detection_library

* fix interpreter_core

* support eager legacy

* fit eager legacy for pten

* fall back to cpu if not found kernel

* fix compile problem

* fix compile problem

* refine fallback logic

* fit operator.run()

* fix xpu compile

* fit for new_exec

* add REGISTER_OP_WITHOUT_GRADIENT

* un-cache pt_kernel_context

* fix compile

* fix cudnn

* fix compiling with on_infer

* fix mkldnn

* fix isfinite_v2

* fix xpu problem

* fix op_device

* refine fallback for xpu

* fix xpu compile

* merge develop

* refine code format

* fix compile

* fix compile

* add data_transfer

* fix PreparePtenData

* fix cpu context

* merge develop

* fix compile

* fix error device context

* fix xpu

* fix dev_ctx

* Optimize layer_norm fwd when cols is 1024.

* Added selected_rows and rw_lock to pten

* Renamed the unit test target to fix CI

* Removed Class SelectedRows in Fluid, changed include/cmake relationship, use pten::SelectedRows in Fluid

* Remove rw_lock.h,rw_lock_test.cc in fluid

* Use pten::RWLock and pten::AutoRDLock, fix CI

* Use pten::SelectedRows

* Use pten::SelectedRows

* Fix to pass NPU CI

* Use pten::SelectedRows, to pass NPU CI

* To fix NPU CI

* To fix NPU CI again

* - more unlikely

* - compilation fix

* - removed redundant definition

* - fix

* - Fixes

* - compilation fix for windows