* add clip_by_norm on kunlun, *test=kunlun

* opt matmul and matmul_v2 on kunlun, *test=kunlun

* optimize unity build, test=develop

* fix compilation error on Windows, test=develop

* fix compilation error, test=develop

* fix code style error, test=develop

* Optimized the adaptive_avg_pool2d op when output_size == 1

* update, test=develop

* fix windows for optimization of elementwise_add Op

* Unification of bfloat16 enablement process and refactor

* Remove unnecessary function

* Standardize the output name search

[BUG FIX] Fix softmax cross entropy overflow problem.

add squeeze_op/unsqueeze_op on kunlun;fix conv op and parallel executor;optimize lookup_table op (#31056)

* add squeeze_op/unsqueeze_op on kunlun; fix conv op and parallel executor on kunlun; optimize lookup_table op on kunlun

* update squeeze/unsqueeze op

* [static setitem] support the index step > 1. tensor_a[::3] = value

* [static setitem] support the index step < 0. Eg: tensor_a[::-3] = value

* [static setitem] support the index is Tensor. eg: tensor_a[tensor_3:0:-1] = value

* Add op version.

* - added Reshape grad bf16

* - Added reshape grad bf16

* - cosmetics in py

* Modify relu native implementation

* fix GPU performance

* add  parameter in roi_align op

* enable exhaustive_search for input_grad when dtype is float16

* enable exhaustive_search for forward algos

* 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

* use iwyu clean include second time, test=develop

fix the broadcast for the large second input