* add ps table (#29463)

* add ps table

Change-Id: I468a04bd071d21ff52654926fcf4d5f3da19e178

* add service (#29560)

* add service, remove ut on mac

* fix heter_profiler & add heter stop method

* fix code style

* merge pscore

Change-Id: Ie7f60d1cdde6755a0c29db26863c6283e9843d57

* fix cmake

Change-Id: I6773509a7b4ca79139ecc40b7bf3eb318ceff8bb

* fix conflit

Change-Id: I35575be0c96a8520f9d756ea7f1ff0b904a165ba

* fix conflit

Change-Id: Ic926ea0b0d67803226d51241397ba3b510226bfa

* fix test_dist_fleet_heter_ctr & peformance update

* test=develop, bug fix

* test=develop, add ps auto

* add print test_dist UT elapsed time

* UT elapsed time optimize

* add save/load for parameter server

* support ps-gpu

* move paddle.fleet to paddle.distributed.fleet

* test=develop,test=document_fix, remove the out args

* fleet_util move to paddle.fleet
Co-authored-by: NWuHaobo <wuhaobo1994@gmail.com>
Co-authored-by: Ntangwei12 <tangwei12@baidu.com>

Integrated Trainer of Parameter Server (API add `fluid.contrib.layers.sparse_embedding` only) (#22957)

* Integrated Trainer of Parameter Server

This reverts commit 66fce9e8.

Fleet Parameter Server API Integrated

* add thread barrier for the compiled program

* add half_async in the communicator
* fix DistributedStrategy

* fix grad clip， clip op belongs to Backward op when running in Parameter Server mode.

* add distributed_strategy

add executor.FetchHandler for train/infer from the dataset

* refector geo sgd & communicator

* add print log for unittest of distributed training
test=develop

* fix save/load in Fleet
* add UT framework of Fleet