* support bert when exists matmul_v2

* update

Check detail PR description at https://github.com/PaddlePaddle/Paddle/pull/36116

Remove RunFromCinn method in PE because We Will Call CinnRunner in Compute method of SubgraphOp

* add_int_pass

* add_int8_flag_pass

* add_int8_flag_pass

* fix CMakeLists.txt

* fix test_trt_fc_fuse_quant_dequant_pass.py

* fix python/paddle/fluid/tests/unittests/ir/inference/test_trt_fc_fuse_quant_dequant_pass.py

* fix test_trt_fc_fuse_quant_dequant_pass.py

This reverts commit 7e60cc63.

* add FLAGS_allreduce_record_one_event

* add more comments

* fix ut

* improve coverage

* fix ut, improve coverage

* add mish trt plugin, compile & install success, run error. test=develop
* modify code according to review
* add TRT_NOEXCEPT for mish trt plugin
* add unittest for mish trt plugin
* remove unnecessary check of mish in op_teller.cc
* fix some problem of trt8
* add check and modify unittest while converting mish to trt plugin
Co-authored-by: Ndengkaipeng <dengkaipeng@baidu.com>

Add use_cinn flag and use it to control whether we run PaddlePaddle using CINN.

Also add:

Replace PaddlePaddle graph with a CINN graph in a pass
PE Method to feed data and run the graph by CINN

* add const OpDesc id()

* add const for VarDesc::id()

支持C++开发注册GeneratePass，简化针对fusion等子图优化场景开发方式。

* support CUDA Graph on PE

* add ut, fix CI compile

* reduce memory consumption

* fix CUDA 10 CI

* improve coverage

* improve python coverage

* add align for WorkQueue

* add spinlock

* merge spinlock

* ps gpu dump

* remove log

* fix dygraph double grad dtype error when calling for high differential senario

* reinvoke ci

* add test for partial_engine.cc

* Add Basic CINN Runner Class

* Add CinnCacheKey

* Add Cache logic and improve CinnCacheKey


* Modify as reviewer commented

* Implement hash_combine to fix MAC build.

* gloo hdfs set check & gloo connect retry

* add vlog

* print gloo connect addr & add vlog

* .

* modify vlof

* modify vlog

* modify vlog

* Polish multi-thread schedule strategy

* fix atomic_deps

* modify into lambda function

* add and run

* set file_num in one shard

* format

* add multihead_matmul trt converter test case

* move attribute check to op_teller

* add align for WorkQueue

* WorkQueue update

* Revert "WorkQueue update"

This reverts commit 14ce793dbb204f8ddec63c34b3b72a73c7cdb93a.

* optimize WorkQueue

* Fix copy elision warning

* Remove redundand code

* refine gc for new_executor, test=develop

* refine, test=develop

* refine, test=develop

* merge, test=develop

* Modify H2D and D2H as kQueue::Sync

* fix interface error

Add basic Cost Model, it uses executor to run program and profile it to get op time.

This is an early basic version, we will add more functions in the future.