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

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

Cherry-pick 46541
保证Reset50 TSM deeplabv3模型零修改下实现Layout自动调优

* [Check]Enhance pooling output_size type check

* add unittest

* polish code comments

* polish data_device_transform.cc

cherry-pick from #45826
LayoutAutotune 支持 inplace 类型的OP
 根据 Add eager layout autotune #45409 修改意见调整UseAutotune
将LayoutAutotune判断放到controller中，与AMP 判断保持一致

Adapt tensor output_size for conv2d_transpose and depthwise_conv2d_transpose

* fix doc of max_pool_2d

* dbg

* fix format

* [Eager] fix pool2d interface under eager mode

* add use_gpudnn for pool2d

* fix pool2d yaml conflicts

* fix pool2d yaml

* [Eager, Performance optimization] fix pool3d under eager mode

* polish code

* [Eager] Cast,uniform_random,assign_value use final state

* fix mistake

* fix mistake

* fix CI errors

* add dygraph test for unform

* add fp16 test case for bilinear_initializer

* [OpAttr]ksize of pool2d support Tensor type

* fix unittest

* add unittest

* [Eager] fix max_pool3d_with_index interface under different mode

* fix mistake

* Add tests under legacy and supplement comments

* enhance grid_sampler cpu kernel to 5D input

* fix bug when 5D input tensor running on the cudnn kernel

* [OpAttr]output_size of unpool support Tensor type

* fix coverage

* fix contain_var

* fix coverage

* add coalesce_tensor kernel

* polist coalesce_tensor kernel

* add sig and InferMeta

* add testcase

* add legacy_api.yaml

* fix infermeta

* fix yaml

* fix kernel implementation

* add compile dependency of phi/kernels

* fix MetaConfig

* add python api

* add and fix testcase

* rnn.py add import

* change _C_ops.coalesce_tensor

* remove useless comments

* add SetBackend

* restore XPU kernel temporarily

* fix code according to PR comments

* [OpAttr]padding_value of Pad support Tensor type

* fix unittest

* fix unittest

* fix coverage

* update PixelShuffle and PRelu api in vision.py and activation.py

* update activation.py, using paddle replace numpy

* update format issue

* update foramt issue

* irfftn; test = docutment_fix

* fft; test=document_fix

* fft; test=document_fix

* fft; test=document_fix

* subdata; test=document_fix

* adaptive_avg_pool2d; test=document_fix

* adaptive_avg_pool3d; test = document_fix

* ftt; test=document_fix

* ftt; test=document_fix

* AvgPool1D; test=document_fix

* avg_pool1d; test=document_fix

* test=document_fix

* test=document_fix

* test=document_fix

* test=document_fix

* fft; test=document_fix

* emb; test=document_fix

* emb; test=document_fix

* emb;test=document_fix

* fold; test=document_fix

* fold; test=document_fix

* fold; test=document_fix

* fold;test=document_fix

* GELU;test=document_fix

* update irfftn docs;test=document_fix

* Update fft.py

* Update fft.py

* Update common.py

* Update common.py

* Update fft.py

* Update input.py

* Update pooling.py

* dropout2d; test=document_fix

* Fold; test=document_fix

* update fold math;test=document_fix

* Update common.py
Co-authored-by: NLigoml <39876205+Ligoml@users.noreply.github.com>

* add python final state

* fix bug

* fix bugs

* fix bug

* fix bug

* revert impl, final state mul not support selected rows

* fix softmax use cudnn error

* add softlable false unitest

* revert loss.py

* update loss.py in nn.functional and nn.layer module

* update nn.Pad1D and 2D,3D class in common.py

* add code copy from function anchor for cn docs code alignemnt

* update pad class in common.py

* update common.py in functional and layer model

* fix format issue

* update format issue

* update pad;test=document_fix

* update NLLLoss;test=document_fix
Co-authored-by: NLigoml <39876205+Ligoml@users.noreply.github.com>

some python c api use final state

* add forward inplace final state api

* fix bug

* fix reshape

* fix coverage

* add inplace info for erfinv, lerp, put_along_axis

* fix put_along_axis infer_meta

* fix format

* update yaml

* fix

* transfer trilinear op to phi, change name from trilinear_interp_v2 to trilinear_interp

* reserve linear_interp param

* change testcase scale if-branch

* testcase test_imperative_case

* fix trilinear testcase

* import paddle in test_trilinear_interp_v2

* transfer bilinear op to phi, change bname from bilinear_interp_v2 to bilinear_interp

* reserve linear_interp param

* fix cross device import

* transfer bicubic_interp op to phi, change name from bicubic_interp_v2 to bicubic_interp

* test final_state_bicubic_interp api

* testcase match imperative case

* change name linear_interp_v2 to linear_interp

* fix deprecated_op_names

* deprecated_op_names add linear_interp_grad