* Fix scale kernel for low precision, cherry pick #50998.

* Fix the FP16 precision problem of add_n. (#50129)

* Change squared_l2_norm to reuse ReduceKernel, and register fp16 and bf16 kernel, which is cherry pick #48315.

* Cherry-pick the fix of MPTypeTrait in KP, which is implemented in #50993.

* Cherry-pick the multi-precision support of AdamW for bf16, #48041.

* Fix compiling error.

* Cherry-pick the fix of CubTensorReduceImpl for bfloat16 in #50993.

* Fix unittest.

---------
Co-authored-by: Nliuruyan <44316842+liuruyan@users.noreply.github.com>

* Cherry-pick the register of bfloat16 for amp_kernel, pull request #45541.

* Cherry-pick the master_grad support of adamw, pull request #51141.

* add bf16 for some ops in static mode (#51582)

* Add bfloat16 support for some api in static mode.

* Fix codestyle.

* Revert the change of layer_function_generator.py.

---------
Co-authored-by: Shaojie WANG <wsjmessi@163.com>

* Register exp/expm1/logit bf16 activation op kernels (#48702)

* register more bf16 ops

* update to register coresponding backward ops

* Addition of bf16 type support for Compare OP  (#46413)

* first commit

* clarify the quotes

* change code style format

* support bfloat16

* add bfloat16 support for more ops (#48272)

* [Bfloat16]register bfloat16 datatype for squared l2 norm (#50908)

* Sync the pull request #51903.

* Add some header files back.

* modify cmake file for cuda11.8 compile (#49020)

* modify cmake file for cuda11.8 compile

* add op_library(fused_embedding_eltwise_layernorm_op DEPS bert_encoder_functor)

* Fix compling error.

* Cherry-pick pull request #51396.

---------
Co-authored-by: Nsneaxiy <32832641+sneaxiy@users.noreply.github.com>
Co-authored-by: Nlimingshu <61349199+JamesLim-sy@users.noreply.github.com>
Co-authored-by: Shaojie WANG <wsjmessi@163.com>
Co-authored-by: Nzqw_1997 <118182234+zhengqiwen1997@users.noreply.github.com>

* cherry-pick 45860

* [BUG FIX]Fix MetaTensor's bug when run infermeta (#46265)

* fix sum bug

* fix ci bugs

* fix ci bugs

* update code according comment

* Fix bug of reduce_sum op. When input.numel() > INT32_MAX, its result
is wrong.

* support pure bfloat16

* support bf16 linear

* update PR to pass CI

* tiny fix where_grad_kernel.cu

* Support bfloat16 type for reducer and sharding.

* Fix some bug.

* Polish code.

* Polise code.

* Add bfloat16 datatype in fill_grad kernels.
Co-authored-by: Nsneaxiy <sneaxiy@126.com>
Co-authored-by: Nsneaxiy <sneaxiy@126.com>

Add value check & error message for gather_tree
cherry-pick #47051

support pure bfloat16 for more ops

Optimize performance of depthwise_conv

Config: input[2048, 1024, 4, 4], filter[1024, 1, 4, 4], stride=1, pad=0, dilation=1

为了提升性能，将label的边界检查从python端转移到kernel内，减少额外op的调用，如min、max和同步拷贝等
    当前的模板参数IgnoreIndex仅在ignore_index取值范围在[0, dim)时才生效，但是当某个label值超出了边界，ignore_index等于该label，这种情况下是应该仍然能正常计算。虽然当前的计算逻辑在结果上不会出错，但逻辑上仍是有问题的，且模板参数IgnoreIndex是没有必要的

Add FP16 support for uniform in dygraph mode on Nvidia GPU
Dev PR link PR46212

* polish code comments

* polish data_device_transform.cc

* [Eager] Fix ocr (#46124)

* fix linspace error in amp

* fix log

* fix amp error

* fix ocr error which caused by amp

* add more check

* rename dtype ns

* [Eager Bug fix]Fix Detection (#46147)

* fix linspace error in amp

* fix log

* fix amp error

* Revert "Simplify size op impl (#45808)"

This reverts commit c252b1de.

* fix_seg

* fix detection
Co-authored-by: NChen Weihang <sunny_cwh@163.com>
Co-authored-by: NChen Weihang <sunny_cwh@163.com>

[vision.ops.nms] Fix return order error and duplicate results with specific inputs (#46148) (#46193)

* fix return order error and duplicate results with specific inputs

This reverts commit c252b1de.

修复cuda11.7编译出错的问题

* simplify size op

* trans to cuda manuly

* fix copy error

Adapt tensor output_size for conv2d_transpose and depthwise_conv2d_transpose

* fix amp kernel

* update to remove PADDLE_WITH_XPU macro

* fix grad error of grounorm op when cuda version==11.7

* add dist cuda kernel

* reuse some funcs in phi

* 使用pnorm

* fix code style - explicit

* fix code sytle

* fix bug

* remove unused headers

* copy kernel file to phi

* delete some code

* migrate uniform_random, test=kunlun

* fix input error, test=kunlun

* fix gpu register error, test=kunlun

* add include file, test=kunlun

* try fix error from CI, test=kunlun

* polish other PR

* fix CI-coverage error, test=kunlun

* refine cmake of framework

* add deps for dense tensor

* fix deps

* remove alloc(ctx)

* add depends on mkldnn

* [OpAttr]output_size of unpool support Tensor type

* fix coverage

* fix contain_var

* fix coverage

* fix split bug

* solve function redefine

* fix fluid.layers.split and add unit test

* delete splitInferMeta register in unary.cc

* modify test_split_op GPU unit test

* modify test_split_op GPU unit test place param

* refactor split op and fix infershape bugs

* add () in && and ||

* fix split C++ unit test

* fix split infershape

* Adapt tensor axis for argmin/max

* Add UT

* Polish UT

* [OpAttr]Adapt tensor axis for reduce_min/max/mean/sum/prod