* Add conv transpose BF16

* Share function GetWeightsTz

* Adjust to review and fix op compatibility

* Add bias to unique handler name

* Remove errors related to paddle enforce

* Add conv2d_transpose to bf16 list and kernel refator

* update eigen version on Windows, test=develop

* add /bigobj for cl, test=develop

* Update Xbyak and add bf16 fast performance verification

* Fix formating

* Change LOG message

* Trigger an update of a new tag

* use iwyu clean include second time, test=develop

* support xpu inference with analysis predictor, test=develop

* merge the cmake of the xpu toolchain, test=develop

* add c-apis, test=develop

* fix a bug in extern_xpu, test=develop

* fix malloc L3 failed bug for kunlun

* minor

* [ROCM] update fluid platform for rocm35 (part1), test=develop

* address review comments, test=develop

* add abs test case

* use std::abs to fix abs bug

* fix the abs bug

* fix abs bug

* delete empty line of pybing.cc, test=develop

* use nvtx push pop in timeline, test=develop

* change year, test=develop

* add #ifdef PADDLE_WITH_CUDA, test=develop

* add #ifndef WIN32, test=develop

* is_pushed to is_pushed_, test=develop

* rewrite abs op

* rewrite abs op and remove abs in activation

* remove abs register in old codes

* fix abs_grad type error

* fix abs double_grad output name error

* modify abs_grad, abs_grad_grad functor for windows building

* format code style

* fix the bug of result is nan when the divisor is zero

* add missing abs attr and add abs for float16

* unify calling cudaSetDevice

* fix compile

usleep function in <unistd.h> only takes argument less than 1,000,000. Current call can exceed this limit, we have to fix it. This PR can fix random CI error.

* optimize memcpy perf for kunlun

* remove useless unitest for kunlun mean

* minor

* - Added UT for testing elementwise_mul caching

* lint fixes

* Polish and Optimize the print/repr message of all layer

* fix some code format

PADDLE_RETRY_CUDA_SUCCESS used wrong sleep time so it can cause timeout in unittest. This PR fixed it.

After we searched the doc in https://pubs.opengroup.org/onlinepubs/7908799/xsh/unistd.h.html, the time unit of sleep in unistd.h takes "seconds", usleep takes "microseconds", Sleep in windows.h takes "milliseconds".

* flush denormals to zero, test=develop

* add comments, test=develop

* Support MIPS arch.

* enable bilateral_slice unittest on windows platform

* reduce max threads

* add support for complex grad accumulated

* add unittest for coverage

* update test dtype

* remove useless blank line