* base changes for mul reimplementation

* empty commit

* tmp save

* full implementation of mul bf16/fp32 fwd bwd

* CI fix

* CI rerun

* changed unity build cmake to avoid gpu issues

* removed mul mkldnn from unity build

* added skipping tests if not cpu_bf16

* CI fix

* CI fix

* CI fix

* fix mkldnn invalid infershape

* add unittest for mkldnn in new executor

* add import os

* Support test_imperative using_non_zero_gpu and Add a TODO comment

* Change GPU number to 0

* Modify the cuda device selection method

* code clean

* [part 3]change type of function args

* support more ops

* Co-authored-by: Xiaobing Wang <xiaobingw@graphcore.ai>
Co-authored-by: NAllen Guo <alleng@graphcore.ai>
Co-authored-by: NZhixin Yao <zhixiny@graphcore.ai>
Co-authored-by: NHaicheng Jiang <haichengj@graphcore.ai>
Co-authored-by: NHan Zhao <hanzhao@graphcore.ai>

* 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: NHaicheng Jiang <haichengj@graphcore.ai>
Co-authored-by: NHan Zhao <hanzhao@graphcore.ai>

* update date
Co-authored-by: NXiaobing Wang <xiaobingw@graphcore.ai>
Co-authored-by: NZhixin Yao <zhixiny@graphcore.ai>
Co-authored-by: NHaicheng Jiang <haichengj@graphcore.ai>
Co-authored-by: NHan Zhao <hanzhao@graphcore.ai>

* delete gloo connect retry

* the_one_ps dirs reconstruct

* .

* .

* create the_one_ps dirs

* create the_one_ps dirs

* create the_one_ps dirs

* create the_one_ps dirs

* create the_one_ps dirs

* create the_one_ps dirs

* the one ps dirs modify

* the one ps dirs modify

* the one ps dirs modify

* the one ps dirs modify

* fix conv act int8 scale

* add unit test for conv+hard_swish

* support 5d for nearest

* update nearest3d unittest, test=develop

* fix approve ci, test=develop

* fix approve ci, test=develop

* auto parallel sharding base

* chmod

* add unitest

* set unitest cmake dist label

* revise code according to rewiew

* chmod

* bugfix for grad_clip and param broadcast

* chmod

* update unitest

* chmod

* add clip

* chmod

* add amp pass

* chmod

* add unitest

* remove grad update

* fixed bug

* fixed bug

* fixed typose

* fixed typoes

* init elem_max_grad op

* optimize code and reply review comments

* ternary functors

* apply new reduce func

* move functor to .h

* multi-outputs init

* rearrange code

* modifed functors

* optimizer code

* pass nullptr

* revert the last change as seg fault occurs

* optimize code

* remove inplace

* remove comments

* remove hybird dir

* resolve conflit

* ini commit

* multi-outputs init commit

* optimize code

* remove inplace

* move dot_dev api into dot_kernel.h

* add infermate header

* modify to dotkerel in dot_op.h

* mvoe conj dev api into complex_kernel.h

* move sign dev api into  sign_kernel.h

* Add pten change file check for op benchmark

* fix style format

* test

* revert

* refactor the impl of elementwise grad kernel

* refactor impl of elementwise grad kernel(cuda)

* fix compile bugs

* update readme test=document_fix

* update conll05 docs

* update conll05 docs test=document_fix

* first commit

* fix wrong filename

* fix the wrong spell name

* fix gpu config warper

* modify according to pr advices

* fix GpuLauchConfig1D api bugs

* change the config for dropout grad

* fix bugs

* modification according to pr advices

* modification according to pr advices

* add align for WorkQueue

* add spinlock

* merge develop

* merge

* Add EventsWaiter

* Revert "Add EventsWaiter"

This reverts commit e206173aa9be7401b83a53581627bfaf557c8fb2.

* os_info update

* update

* update

* update

* update

* update

* fix

* update

* update for windows

* fix windows

* update

* update
Co-authored-by: Nliutiexing <liutiexing@google.com>

* add args check and comment for exp,polynomy decay

* modify according to zhouwei's comment

* refactor matmul directory in pten

* fix merge conflict

* add dot_grad kernel

* add dot_grad kernel in pten

* add matmul_grad kernel

* update the code

* delete useless code in fluid

* fix some bug of running matmul grad kernel

* fix merge conflict

* refactor some code

* refactor code

* fix bug when inplace strategy

* fix

* fix

* fix

* fix

* fix

* add pten::Place data structure.

* update ci problem

* fix ci problem

* update

* update dist tensor

* add unitest

* update unitest

* refactor dist tensor

* update dist tensor and unitest

* check amp.decorate and DataParallel

* refine coverage

* fix layer dtype

* refine code

* fix the wrong filename

* first commit

* first commit

* remove rest useless headers

* for ci approval

* support vs2019 compilation in windows

* not modify pow_op's original compute logic

* Pre-save hooks of jit.save

1. Added pre_save_hooks features to jit.save.
2. Added related unittests

* Added jit pre_save_hooks functions's alias to paddle.jit and copyright.

* Make jit.save_pre_hook style be consisent with Paddle's rule.

* Fixed arguments passing bug in run_save_pre_hooks

* Added API Documents

* Move clear and run_pre_save_hooks as internal methonds only.

* Made register_save_pre_hook as an internal function.

* Rearranged Eager AutoCodeGen directory structure

* Removed USE_OP in Eager AutoCodeGen

* Enabled generation for Operators without Grad/Inputs/Outputs

* Resolved operators without input

* Fixed merge conflicts

* Enabled Eager AutoCodeGen for 10+ more operators

* Refactored Eager AutoCodeGen with more organized helper objects

* Enabled Eager AutoCodeGen for operators with multiple OpBases

* Adjusted Eager AutoCodeGen to Enable Passing Output Tensor as Input Argument

* Handled Dispensable Inputs/Outputs in Eager AutoCodeGen

* Adjusted function generation/call between Python-C API & Dygraph API

* Synchronized auto-generated Python-C API with Dygraph Forward Functions

* support more eager tensor api

* fix merge compile error

* fix compile error and fit develop code

* support pure CPU

* fix some logic error in eager_mode

* support _varbase_creator in eager mode

* Added safe_initialized interface to EagerTensor for use in processing dispensable inputs

* for eager mode

* refine

* support multiple constructor for eager tensor

* add place related code

* polish code

* specific randint with dtype of int64

* Support pure cpu test

* eager logic

* refine test in pure cpu

* eager logic

* eager logic

* eager logic, test=develop

* skip core.eager when in inference, test=develop

* refine, test=develop

* refine, test=develop

* call RetainGrad after run forward kernel, test=develop

* refine, test=develop

* support dygraph util, meta, guard test

* eager test case

* support inference test

* refine test and fix initializer failed

* modify eagertensor patch method

* add eagertensor.clear_grandint, test=develop

* refine, test=develop

* refine, test=develop

* refine, test=develop

* support create varbase and fix retain grad error

* call monkey_patch_varbase in _test_eager_guard, test=develop

* fix windows error

* split clear_gradient to clear_gradient and zero_grads, test=develop

* refine, test=develop

* refine, test=develop

* support test_imperative_basic test in eager mode

* remove additional log in variable.h

* remove additional log in variable.h

* remove additional code create in merge

* eager

* fix some eager logic, test=develop

* refine, test=develop

* refine, test=develop

* refine, test=develop

* refine, test=develop

* refine, test=develop
Co-authored-by: Njim19930609 <jim19930609@gmail.com>
Co-authored-by: NJiabinYang <360788950@qq.com>