* support selectedrows allreduce in multi-cards dygraph, test=develop

* remove useless import modules in unittests, test=develop

* add nccl cmake to get nccl version, test=develop

* add if-condition to compiled correctly, test=develop

* add detail version parseing for old nccl, test=develop

* polish camke details, test=develop

* fix remove test cmake error, test=develop

* fix cmake condition, test=develop

* change unittest camke list, test=develop

* fix unittest cmake rule, test=develop, test=framep0

* remove REPLACE_ENFORCE_GLOG compile option & add ci rule prohibit LOG(FATAL) using, test=develop

* remove ci test case, test=develop

* replace all LOG(FATAL) & polish message, test=develop

* fix typo, test=develop

* polish error info detail, test=develop

* fix negative framework overhead, test=develop

* use overhead summary, test=develop

* simply C++ error stack once again, test=develop

* refactor code remove string pointer and recursive, test=develop

* Add isCached() mechanism for BatchNorm and LRN oneDNN operators
test=develop

* Formatting fix
test=develop

* Update PADDLE_ENFORCE in DNNL related ops
test=develop

* Abstract macro of OP_GET_PLACE_CHECK
test=develop

* update according to reviews

* update GET_PLACE_CPU_CHECK

* fix typo
test=develop

* revert macro
test=develop

* Update isCached() to be thread freindly
test=develop

* Add isCached() check inside Softmax handler
test=develop

* Fix PaddleEnforce() message
test=develop

* Add the check for whether CUDA Driver and NVRTC is available for the runtime system.

* Call cuInit to initialize the CUDA Driver API before all CUDA callings.
test=develop

* Change the behavior when libnvrtc.so can not be found, printing a warning instead of exiting.
test=develop

* Do not initialize CUDA Driver API for windows and macos.
test=develop

* Remove the call of cuInit when entering paddle and enable the test_code_generator.
test=develop

* Add some built-in functions for __half.
test=develop

* Change save_intermediate_out to false in unittest.
test=develop

* Fix error reference to tempropary variable when seting including path for device_code.
test=develop

* Add isCached() mechanism to elementwise_add
test=develop

* Hide code inside handler
test=develop

test=develop

* add new macro BOOST_GET_SAFELY & unittests, test=develop

* add different macro type, test=develop

* fix get macro type in executor, test=develop

* four macro part change backup

* using one macro for all case, test=develop

* revert attribute change, test=develop

* change to three func to solve gcc4.8 bug, test=develop

* polish some details, test=develop

test=develop
test=win_gpu

* Fix cusolver loader for Windows in dynamic_loader.cc. test=develop

* Fix missing CUSOLVER_ROUTINE_EACH_R1.
test=gpu
test=develop

* Add unsupprot for cusolver on Windows temporarily. test=develop

* Fix GetCusolverDsoHandle error message. test=develop

* update the analysis predictor, test=develop

* update the unit test, test=develop

* no priority set before the inferface determined, test=develop

* interface name generalization, test=develop

* Add cholesky_op forward part. test=develop

* Complete cholesky_op forward part. test=develop

* Add cholesky_op backward part. test=develop

* Complete cholesky_op backward part. test=develop

* Refine cholesky_op error check and docs. test=develop

* Add grad_check unit test for cholesky_op. test=develop

* Fix sample code in cholesky doc. test=develop

* Refine some error messages of cholesky_op. test=develop

* Refine some error messages of cholesky_op. test=develop

* Remove unused input in cholesky_grad. test=develop

* Remove unused input in cholesky_grad. test=develop

* Fix stream for cusolverDnSetStream. test=develop

* Update PADDLE_ENFORCE_CUDA_SUCCESS from cholesky_op to adapt to latest code.
test=develop

* Add CUSOLVER ERROR in enforce.h
test=develop

* Fix the missing return value in cholesky. test=develop

* add the thread_local_allocator, test=develop

* refactor the thread_local_allocator, test=develop

* provides option setting strategy, test=develop

* Optimize the error messages of paddle CUDA API, test=develop

* fix the error messages of paddle CUDA API, test=develop

* Refactoring PADDLE_ENFORCE_CUDA_SUCCESS, and apply to curand/cudnn/cublas/NCCL,test=develop

* remove build_ex_string,test=develop

* merge conflict,test=develop

* update eigen, test=develop

* remove patches, test=develop

* add definition of -fabi-version, test=develop

* add patch for TensorBlock.h, test=develop

* test windows, test=develop

* only update eigen for Linux, test=develop

* add code comments, test=develop

* supports thread-binding stream, test=develop

* avoid using thread_local variables in dtor, test=develop

* modify the stream priority enum, test=develop

Correct the name [`FLAGS_sync_nccl_allreduce`](https://www.paddlepaddle.org.cn/documentation/docs/zh/advanced_guide/flags/others_cn.html#flags-sync-nccl-allreduce) based on the information from our official website.

eagerly release cuda resources before cuda enviroment destroying
test=develop

* Initial FP32 DNNL MatMul Implementation

* Implement int8 DNNL MatMul

* Unify in-kernel-naming, clean UTs

* MatmuL: Introduce op caching

* Final adjustments

test=develop

* Remove dy_graph disablement

test=develop

* Change dnnl header name to new one

test=develop

* Contrain multi head check to prevent fails

test=develop

* Resolve dnnl header problems on MAC CI

* Variable namings to kernel and skip_grad_ci added

test=develop

* Prevent MAC CI from failing

* Prevent windows build from failing

test=develop

* Modify UTs to conform to the rules

* Modify MatMul aux functions namings

test=develop

add addmm op