* [MLU] add mlu new profiler

* fix format

* regist elementwise_xxx

* support multi layer and bidirection of lstm_grad, *test=kunlun

* support multi layer and bidirection of lstm_grad, *test=kunlun

* update sign op on xpu. test=kunlun

* fix typo. test=kunlun

* init commit no push

* collect comile errors

* bitwise UT

* fix compile problem

* cancel comments

* restore miss deletion

* fix compilation

* fix UT

* NO stash in multiple branch at the same times

* fix error

* combine .cu from gpu and kps

* replace gpu by kps

* fix by Chen-weihang

* Revert "Fix kps compile error in Junhui logic compare bitwise"

* fix backend test

* rm comments
Co-authored-by: NChen Weihang <chenweihang@baidu.com>

* fix_paddle_numel_check

* fix_paddle_numel_check

* Using the maximum workspace_size of all alogirhms to limit the workspace size in exhaustive search mode.

* Use the system cudaMalloc and cudaFree to allocate workspace during searching.

* Enable switch of two kind of workspace setting methods.
Co-authored-by: NLiu Yiqun <liuyiqun01@baidu.com>

* ignore some failed test for KL2
*test=kunlun

* minor
*test=kunlun

* minor
*test=kunlun

* remove paddle_ipu shared library

* fix unique_name

* limit grid dim for index select

* mv LimitGridDim into gpu_launch_config.h

* fix conflicts

* fix conflicts

* fix code style

* set block to 256

* fix grid setting

* set dtype of block_dim to unsigned int

* support pinned, test=develop

* support async_write, test=develop

* refine, test=develop

* refine, test=develop

* refine, test=develop

* refine,test=develop

* refine, test=develop

* refine, test=develop

* refine, test=develop

* refine, test=develop

* support multi_layer of bilstm,*test=kunlun

* support multi_layer of bilstm, *test=kunlun

* support multi_layer of bilstm, *test=kunlun

* support multi_layer of bilstm, *test=kunlun

Add new APIs for GPU memory monitoring (max_memory_allocated, max_memory_reserved, memory_allocated, memory_reserved) (#38657)

* Add new API memory_reserved

* Add memory_allocated, max_memory_reserved and max_memory_allocater

* Fix CI error

* Fix CI error

* Enhance UT

* Add FLAGS_memory_stats_opt

* Add STATS macro functions

* Add StatAllocator

* Fix CI errors

* Add UT

* Fix CI errors

* add bilinear interpolate v2 to xpu list and unitteset, *test=kunlun

* Delete ps_usr_print_log

* Delete ps_usr_print_log

* Delete xpu_op_test

* swish and pow op for xpu. test=kunlun

* fix code style. test=kunlun.

* use pow_grad xdnn api. test=kunlun.

* add maximum limit for grid of reduce, elementwise and gather

* add {} after if

* [NPU] add npu support for conv3d and conv3d_grad

* [NPU] delete failed unittests due to Ascend not support

* [NPU] delete debug codes

* [NPU] optimize codes, notest

* [NPU] remove const_cast

* [NPU] optimize for remove const_cast

* [NPU] fix written errors

* add more ops

* add authors
Co-authored-by: NXiaobing Wang <xiaobingw@graphcore.ai>
Co-authored-by: NAllen Guo <alleng@graphcore.ai>
Co-authored-by: NZhixin Yao <zhixiny@graphcore.ai>
Co-authored-by: NZhaorui Chen <zhaoruic@graphcore.ai>
Co-authored-by: NHan Zhao <hanzhao@graphcore.ai>

* rm ipu_strategy.check()

* fix UT fail

* fix typo
Co-authored-by: NXiaobing Wang <xiaobingw@graphcore.ai>
Co-authored-by: NZhixin Yao <zhixiny@graphcore.ai>
Co-authored-by: NZhaorui Chen <zhaoruic@graphcore.ai>
Co-authored-by: NHan Zhao <hanzhao@graphcore.ai>

* sync changes

* copy sOpNamescope

* fix UTs

* add authors
Co-authored-by: NXiaobing Wang <xiaobingw@graphcore.ai>
Co-authored-by: NAllen Guo <alleng@graphcore.ai>
Co-authored-by: NZhixin Yao <zhixiny@graphcore.ai>
Co-authored-by: NZhaorui Chen <zhaoruic@graphcore.ai>
Co-authored-by: NHan Zhao <hanzhao@graphcore.ai>

* fix code-format

* fix compile error

* add comments for feed_op
Co-authored-by: NXiaobing Wang <xiaobingw@graphcore.ai>
Co-authored-by: NZhixin Yao <zhixiny@graphcore.ai>
Co-authored-by: NZhaorui Chen <zhaoruic@graphcore.ai>
Co-authored-by: NHan Zhao <hanzhao@graphcore.ai>

[KP] Add unittests for brelu,ceil,celu,elu,floor,hard_shrink,hard_sigmoid,log1p,logsigmoid,relu6,silu,soft_relu,softsign,swish (#40448)

* solve unexecuted UT

* add 24 activation op UT

* append swish&thresholded_relu to kpfirst_list

* rm thresholded_relu

* add tril_triu for xpu, *test=kunlun

* add tril_triu for xpu, *test=kunlun

* add tril_triu for xpu, *test=kunlun

* add tril_triu for xpu, *test=kunlun

* add tril_triu for xpu, *test=kunlun

* add pg_hccl

* 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 softmax log_softmax

* refine rocm

* refine unittest

* add scale gather sum

* refine CUDA_ATOMIC_WRAPPER ADD for bf16

* add gather unittest

* solve conflict

* add scale uinttest

* add sum unittest

* solve conflict

* refine gather unittest

* refine unittest

* rename pten_utils to phi_utils

* rename pten_utils target

* rename Pten to Phi

* replace pten with phi

* resolve conflict

* [KP] Unify .cu and .xpu files with .kps files

* fix CI bug in GPU and modify the list

* fix conflict

* modify the date

* Fix compile error on cuda_arch less than 700.