* add visit_place to phi/core/utils

* remove reference to operator.h in phi/kernels/funcs/math_function.h

* update data type from framework.proto to phi

* fix enforce error in fluid

* rm framework::tensor_util in phi

* clean TensoCopy

* fix bugs

* fix bugs

* fix bugs

* repalce mutable_data

* revert custom_device_test.cc

* move incubate to geometric

* add paddle.geometric

* fix unittest bug

* add float16 support for segment op

* change reindex and sample neighbors flag name

* add heter graph reindex

* move sample_neighbors.py to neighbors.py

* delete khop_sampler in geometric

* delete unused code

* change sample_neighbors api input order

* fix en doc

* fix unittest

* fix unittest

* change reindex

* fix division by 0

* delete unnecessary input argument

* delete final_state

* refactor the optional tensor

* remove optiona<MetaTensor> in InferMeta

* fix bug

* fix optional<vector<Tensor>>

* fix bug

* fix rmsprop

* fix amp of eager_gen

* polish code

* fix deleted code

* fix merge conflict

* polish code

* remove is_nullopt_

* fix merge conflict

* fix merge conflict

* segment pool support for int int64 kernel.

* add support in python api

* move segment_pool to phi.

* mark summed ids as optional tensor.

* fix as reviews.

* move gather.h gather.cu.h scatter.h scatter.cu.h to phi library

* fix CI

* fix rocm ci

* rename pten dir to phi

* rename namespace to phi

* rename infrt pten dir to phi

* resolve conflict

* rename pten to phi in cmake

* revert all infrt change

* change needed files

* fix infrt failed

* fix inference failed

* move operators/math/math_function_* to pten/kernels/func
* namespace from `paddle::operators::math` to `pten::funcs`

From --ptxas-options=-v, SegmentOpsKernel uses 66 registers in a block.
There are two ways to resolve this problem:
    Reduce the threads per block launch configuration
    add __launch_bound__ to give information to nvcc compiler for reducing registers usage
this PR chooses __launch_bound__ solution because changing gpu_launch_config may affect other ops.

* refine structure for cuda and rocm

* update

* update

* update

* update

* [OPs] Bug fix, fix the segment mean for illegal syncthreads usage.

fix cpplint error for the autmic max/min

Add GPU Kernels of Segment Ops,  support, sum, max, min, mean