* fix A100 CUDA12 ut

* fix ci uts

* fix test_sync_batch_norm_op

* fix sync bn op ut again by separating 2 files

* fix codestyle ci

* combine other PRs

* fix codestyle

* fix codestyle ci

[IR&PASS] part 3-2: add PatternApplicator and FrozenRewritePatternSet, refine PatternMatch code, add some api for Builder (#54492)

* [IR&PASS] add PatternApplicator and FrozenRewritePatternSet, refine PatternMatch code, add some api for Builder and TypeId

* fix comment

* “update”

* update

* update

* update

* update

* test

* update

* test

* fix_c++17_bug

* fix coverage compile error

* test

* test

* test

* fix C++17 error

* fix c++17 error

* fix c++17 error

* test

* test

* test

* test

* fix cinn compile error

* compile to compiler

* set cinn c++14

---------
Co-authored-by: huangjiyi <947613776@qq.com>
Co-authored-by: Nhuangjiyi <43315610+huangjiyi@users.noreply.github.com>

* construct dist tensor

* move constructor to header

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* Enable check_cinn on atan2, tile, top_k and where

* Update cmakelists in legacy_test

* Reformat code

* Enable check_cinn on op take_along_axis legacy test

* Enable check_cinn on pool2d

* Remove check_cinn=False

* Try fix tile test error

* Rename enable_cinn to test_cinn

* Refactor test_tile_op

* Replace all enable_cinn to check_cinn

* Revert pool2d test timeout

* Remove check_prim and use enable_cinn

* fix a100 cuda12 timeout

* fix cuda12 pickle loads problem

* fix ist_sharding_save ut

* mutiply_triple delete

* add case

* add timeout

* use global group to pass meta

* use batch isend irecv

* add partial send/recv

* remove communication group

* remove p2p on npu and xpu

* remove virtual pp ut

* add kernel dialect

* change DenseTensorTypeStorage to DenseTensorType

* add test case`

* add first pd_op to kernel dialect

* lower pd op to kernel dialect

* update

* update

* remove useless code

* add attrite print test

* fix bug

* polish code

* layer_norm op with dynamic shape support INormalizationLayer in TRT8.6

* Using trt layer to make layers_norm op in lower than trt8.6
layer_norm op with dynamic shape support INormalizationLayer in TRT8.6

* adapt_startup_program

* refactor program translator

* polish

* add custom op printer hook

* fix merge conflicts

* fix top level op printer

* adapt full int array op

* modify by reviews

* fix

* fix for log xxx

* add int32/int64 for cpu/gpu; add float16/bfloat16 for cpu forward

* fix docstring

* fix bug

* fix bugs

* fix bugs

* fix bugs

* fix bugs

* fix bug

* using cast

* fix test

* fix api

* fix other bugs

* fix ci bug for not using dygraph guard

* add bfloat16 test

* fix ut

* bf16

This reverts commit 8b1839be.

* “update”

* update

* update

* update

* update

* test

* update

* support add(x_float32, bfloa16_) or add(x_float32, y_float16)

* polish

* fix test

* auto generate code for elementwise_max

* auto generate code for elementwise_max

* fix composite ops

* fix bug of fmax

* adapt_startup_program

* refactor program translator

* polish

* refine code

* refine code

* refine code

* refine code

* refine code

* refine code

* refine code

* fix bug

* refine code

* refine code

* refine code

* refine code

* refine code

* delete unused code

* delete unused code

* refine code

* bump ruff to 0.0.271 and update config

* exclude third_party

* bump ruff to 0.0.272

* refine config

* remove redunant

* [CINN] add paddle.device.is_run_with_cinn() api for running check

* for pass ci converge

* add check whl should compiled with cinn

* fix ci coverage bug

* remove exposed API

* import is_run_with_cinn explicitly

* support some prim ops bf16 dtype

* fix cmake