* remove bf16

* remove comments

* remove wrong return

* fix UT

* add conv_gelu_mkldnn_fuse_pass

* add post ops

* Reduce reshape kernel functions in pten

* delete notes

* fix bugs when compile

* test_mkldnn_depthwise_conv_pass

* test: add TimeOut

* sset TIMEOUT

* fix:add random num for dilation and group

* add layer_norm_fuse_pass test case

* restore cmakelist code

* Merge branch 'develop' into layer_norm_fuse_pass

* Merge branch 'develop' into layer_norm_fuse_pass

* add bad case test

* reshape+transpose+matmul_v2

* in_name->input_name

* fix pr-ci-static-check

* update 3 tests

* fix typo error

* disabled bad case

* int to size_t

* fix single card 8 unittests in new executor

* fix

* fix

complement deps of cmake files under WITH_CINN compilation

* add fc_elementwise_layernorm_fuse_pass

* fix name conflictn

* rebuild CI

* fix Ran Programs=0 bug

* optimize cache key

* add cinn cache key by graph address

* perfect cache key test script

* rename GraphHashProto to GraphHashStrategy

* optimize graph_serialize_str_ to graph_hash_val_ and other change by review advices

cinn_launch_op： cache scope and place on CinnLaunchContext to skip duplicate alloc/free callback construction

* add transpose_flatten_concat pass

* modify skip func to ignore_pass_case func

* delete input_shape limit

* modify get node order

* default accessor and multi table config

* add unittest

* add unittest

* delete print

1. add a subdirectory named `cinn` in `paddle/fluid/operators` directory and move releated files into it
2. seperate CinnLaunchContext class from `cinn_launch_op.h` and put it in a  new independent file named `cinn_launch_context.h`, so that it can be included by others clearly.

* add alias kernel name

* modify code as suggestions

* Debug

* Fixed issue with reset_grad_inplace_version when used with clear_gradient & cross-batch accumulation

* Rearranged interfaces

* Fixed ci issues

* fix heter service. test=develop

* fix heter section worker in debug mode

don't exit if requested_size < size

* quantize slice op

* correct test

* fix code formatting

1. Modify git tag for CINN
2. Support compile option "-DWITH_CINN=ON, -DWITH_TESTING=OFF"

* add test_unsqueeze2_eltwise_fuse_pass

* fix name conflictn

* rebuild CI

* update

* update. test=develop

* fix. test=develop

* fix ut. test=develop

* fix ut. test=develop

* fix ut. test=develop

* update. test=develop

* fix ut. test=develop

* fix ut. test=develop

* fix sample code. test=develop

* fix ut. test=develop

* fix ut. test=develop

* fix ut. test=develop

* fix ut. test=develop

* fix paddle.rot90 doc. test=develop

* update ut. test=develop

* fix. test=develop

* fix .test=develop

* fix .test=develop

* fix doc. test=develop

* enable sequential_run for standalone_executor

* add ut

* fix ut

* refine structure for cuda and rocm

* update

* update

* update

* update

* use sync h2d copy

* use stream safe allocator in memcpy_h2d

* remove wait

* add guard