Add distribution supported

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

* Integrated Trainer of Parameter Server

* test=develop, fix_embedding

* add to_readable_code method, test=develop

* polish doc details, test=develop

* polish doc note, test=develop

* fix unittest error, test=develop

* fix coverage, test=develop

* add print test, test=develop

* add print param, test=develop

* hidden to_readable_code api, test=develop

* remove original tool methods, test=develop

* remove old api using code, test=develop

* Add two types of Metric Calculator: MultiTaskCalculator & CmatchRankCalculator.
* Add a config for DynamicAdjustChannelNum function to denote whether we will discard the remaining instances when they are not be distributed evenly.
* Remove CPU code in Pull/PushSparse and we will add it back when testing it fully.
* Fix some known issues: such as copying persistable vars after one epoch running.

* add sync communicator and implement

* add deprecated for distribute transpiler, will delete it after 2.0.0, test=develop

* add half_async in the communicator
* fix DistributedStrategy

* test=develop, bug fix for sparse recorder

* add special way to add distribute vars， Update Pyramid hash op

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

* add distributed_strategy

* add fake init for the trainer, fix large memory hold in the trainer
* do not merge recv vars from a remote endpoint, test=develop
* add recv and save op, merge slice var in one op, save memory
* remove hsigmoid with pull sparse, test=develop

* Add a single_process_multi_thread transpiler.
* Add some UTs.
* Fix some API description.

* add Adam beta1/beta2 support Variable. test=develop

* update pserver decay blocks

* update distributed notify handler

* fix fetch handler error with pslib
* fix distributed lookup table op with 1 pserver

* test=develop,Fix communicator slow bug

* test=develop, delete if() in stop_worker()

* test=develop

* fix UT, test=develop

* fix bug in fetch handler, test=develop

* fix bug in fetch handler, test=develop

* test=develop, fix fetch barrier bug

* test=develop, bug fix

* test=develop, bug fix

* test=develop, fix bug

* bug fix: invalid learning rate decay in pserver async mode

* doc fix, test=develop, test=document_fix

* test=develop,test=document_fix,fix transpiler doc,add API.spec

* delete debug vlog & add rpc function & fix word2vec bug & speed GEO-SGD

Heartbeat for distributed async training.

* refector geo sgd & communicator

* add deprecated memory optimize doc, test=develop, test=document_fix

* merge develop to solve conflict, test=develop, test=document_fix

* fix DistributeTranspilerConfig document, test=develop

fix wrong place with distributed_lookup_table

* fleet api add input check, test=develop

test=develop

* fix correctness of the communicator

* fix a bug in send thread when sending var context is empty, test=develop

* add lookup_table_prefetch_op and prefetch optimize, test=develop

* remove remote prefetch GPU supported

* word2vec force with CPU, test=develop

* test dist remote lookup table force with CPU, test=develop

* fix sync mode hang in transpiler
* remove sync mode in send/recv
* replace PADDLE_ENFORCE with PADDLE_ENFORCE_NE

* remove unused inference_transpiler unit-tests

test=develop

* remove InferenceTranspiler usage in quantize_transpiler.py

test=develop

Polish fleet API to support cuda collective mode and nccl2 mode

* deprecate python memory optimize, test=develop

* remove memory_optimize in unittests, test=develop

* add unittests to deprecated interfaces, test=develop

* remove legacy memory optimization codes, test=develop

* follow huihuang's comments,test=develop

* follow luotao's comments, test=develop