* commit

* del inplace op in memory_optimize_pass.cc

* check code style

* [autograd] add copy-from; test=document_fix

* [autograd] add copy-from; test=document_fix

* fix

* Fix bugs of dropout and dropout_grad. test=kunlun

* Modify the code style of dropout_grad_kernel. test=kunlun

* skip flash attn ut on Hopper

* minor change

* add clip_grad_value_ api

* add test for ClipGradByValue

* typo fix

* refine and modify clip_grad_norm_

* no_grad

* clip_

* remove g=p.grad

* bug: AssertionError: When Variable is used as the condition of if/while , Variable can only contain one element.

* fix prim add fill_any_like bug

* polish code

* add layernorm spmd rule

* add ut

* follow comments

Pcard-72384
paddle with cinn的情况下支持cinn的c++ ut。 统一了cinn和paddle的third_party的c++版本，cinn third party不使用C++17

* optimize expr operator = implementation

* fix codestyle

* add ir output check in OpTest

* add ir grad check in op test

* add more unittest

* fix

* fix bug

* fix bug

* refien code

* refien code

* fix bug

* refine code

* remove allreduce before c_allgather

* update reshard insert_fill_constant_op func

* insert_fill_constant_op add shape arg

This reverts commit 15c87528.

* modify eular_beam

* modify matmul infermeta

* add test

* modify timeout

* modify mutiply_double nullptr

* modify tanh_triple_gradnode create

* tanh_triple

* [NewIR]Fix VLOG Ptr display problem and decrease amp log level

* fix codestyle

Co-authored-by: NSigureMo <sigure.qaq@gmail.com>

* Refactor op test mul

* Fix test error for mul

* add local scope

* refine code

* refien code

* refine code

* support local scope for BuildFuncList

* fix bug

* add log

* fix bug

* polish code

* fix bug

* masked select forward support broadcast

* cpu forward and backward

* gpu support mask broadcast

* fix comment

* x support broadcast

* fix comment