* [ROCM] update fluid operators for rocm (part3), test=develop

* fix clang format error, test=develop

* Modify relu native implementation

* fix GPU performance

* added external reorder to profiler

* resolved conflict

* added enable_static

* initial version of lstm, not working yet

* added lstm to operators.cmake

* added vanilla lstm mkldnn op

* added peephole weights integration

* minor changes

* added formatting

* added fusion_lstm_mkldnn to static_whitelist

* added formatting

* removed comment

* moved use_peepholes attribute inside is_cached block

* reverted wrong changes

* minor formatting change

* minor changes

* changed stream handling

* minor change

* added datatype to GetExpectedKernelType()

* added reading stream from TLS

This reverts commit d834f4e6.

* added external reorder to profiler

* resolved conflict

* added enable_static

* initial version of lstm, not working yet

* added lstm to operators.cmake

* added vanilla lstm mkldnn op

* added peephole weights integration

* minor changes

* added formatting

* added fusion_lstm_mkldnn to static_whitelist

* added formatting

* removed comment

* moved use_peepholes attribute inside is_cached block

* reverted wrong changes

* minor formatting change

* minor changes

* More precise mkldnn kernel choice in GetExpectedKernelType

* Fixes after review

* Refresh develop for CI

* CI experiment

* get back from CI exper

reduce the  occupied size  of memory for the fused pattern of elementwise_add Op and activation Op(relu Op for example) (#29885)

* add gru op_register_version; test=op_version;

* Update fc,mul version;test=op_version;

* Compiling operator libraries with Unity Build on Windows CPU.

* Compiling operator libraries with Unity Build on Windows GPU, no_test, test=windows_ci

* Add option in windows ci script, no_test, test=windows_ci

* Optimize parallel compiling, test=develop

* remove limit of parallel compile and skip some ops in UB, test=develop

* remove changes of header file, test=develop

* remove changes of header file, test=develop

* fix test_eye_op unittest failed, test=develop

* Compiling operator libraries with Unity Build on Linux, test=develop

* set default WITH_UNITY_BUILD=OFF, test=develop

* Move unity build rules into a single file and add comment, test=develop

* optimize parallel compilation, test=develop

* fix undefined reference error on coverage ci, test=develop

* Add multi_gru op and tests

* removed redundant disable_dygraph()

* skip_layernorm_op done

* add unittest

* slice op convertor support trt < 6

* skip_layernorm only work in ernie

* add fuse_bn_add_act pass

* polish some error message

* add white list

* revert shell script change

Polish the error message of fc, fused_fc_elementwise_layernorm and fused_embedding_seq_pool. (#27692)

* Polish the error message of fc_op.

* Polish the error message of fused_fc_elementwise_layer_norm op.

* Polish an error message in fused_embedding_seq_pool_op.

* use iwyu clean include, test=develop, test=win

* compilation error, test=develop

* fix compilation error2, test=develop

* fix compilation error3, test=develop

* fix compilation error4, test=develop

* fix compilation error5, test=develop

* fix compilation error6, test=develop

* fix compilation error7, test=develop

* fix compilation error8, test=develop

* fix compilation error8, test=develop

* fix compilation error10, test=develop

* fix compilation error11, test=develop

* [bug fix]:Memory increases after adapting the cudnn version to 8

* [bug fix]cudnnGetConvolutionForwardAlgorithm not defined

* add fused_bn_add_relu op

* fix bug sequececonv_eltadd_relu_fuse_pass, output error when sequence_conv's padding_start > 0

* fix seqconv_eltadd_relu_fuse_pass unitest error

* Finished ChannelWiseQuantDequantAbsMaxOp and Passed unittests.

* Finished channel-wise quantize strategy in imperative quantization.

* Added Cuda code of ChannelWiseQuantDequantMaxAbsOP
Add Cuda code of ChannelWiseQuantDequantMaxAbsOp

* Add quant_axis for channel_wise quant.

* fixed a bug in unnitests, which will not trigger axis = 1 case and cannot meet the coverage rate requirement.

* Added some assert infomation and fixed some coding style mistakes.

* Add int8 GRU kernel with UTs

* Lint fixes

* More lint fixes

* Fix the lookup_table_v2 failed on GRU mkldnn kernel issue
test=develop

* fix according to reviews, removed x_num_col_dims
test=develop

* update gru model. change according to reviews
test=develop

* change according to reviews
test=develop

test=develop

* Add oneDNN fusion_gru kernel and fix fc+gru pass
test=develop

* Formatting changes
test=develop

* Lint fixes
test=develop

* Add memory::format_tag::any to GRU weights
test=develop

* Fix build with CUDA

* Fix build with CUDA v2

* cunn8 support
test=develop

* fix ci error
test=develop