* 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

Heartbeat for distributed async training.

* refector geo sgd & communicator

* 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

Polish fleet API to support cuda collective mode and nccl2 mode

* fix prepare context redundant code problem, optimize executor by caching create_varaiables
test=develop

* supports collective training in executor

* make fetch_list runable with variables, add more unittest for use_program_cache
test=develop

* fix comment
test=develop

* use unique name for nccl_id

* supports output to stream in program_to_code

* insert sync_comm_stream before regularization; add skip_op_callstack capability in program_to_code

* set op role in collective training

* add collective op role

* remove orig file

* add build optimizer by strategy

* add collective strategy

* refine collective strategy

* add multi-process role maker

* refine strategy building factory so that we can easily plugin more strategy

* scale loss grad in collective sgd transpiler

* add support for distributed fc

* code format

* revert some features for dist fc

* add support for distributed fc training

* fix prepare context redundant code problem, optimize executor by caching create_varaiables
test=develop

* supports collective training in executor

* make fetch_list runable with variables, add more unittest for use_program_cache
test=develop

* use unique name for nccl_id

* supports output to stream in program_to_code

* insert sync_comm_stream before regularization; add skip_op_callstack capability in program_to_code

* set op role in collective training

* add collective op role

* fix comment
test=develop

* remove orig file

* add build optimizer by strategy

* add collective strategy

* refine collective strategy

* add multi-process role maker

* refine strategy building factory so that we can easily plugin more strategy

* scale loss grad in collective sgd transpiler

* add support for distributed fc

* code format

* revert some features for dist fc

* add support for distributed fc training

* test=develop
add collective op unittest standard

* test=develop
remove the test_collective directory

* test=develop
remove the test_collective directory

* remove slicegather test

* code format for reducescatter

* update attr of shard_index_op

* Modify macro nccl_helper

* remove test without distribute

* macro collective_helper

* marcro update

* test=develop
update support python3.5

* test=develop change gpu memory use to 0.1 when test

* test=develop
update ut equal func

* test=develop
set flags to 1.5

* test=develop fix pickle dumple  py35

* test=develop
fix divide in slice and add sync_comm_stream
update atol and rtol to 1e-05
rm shard_index op and test
modify read input from file to read from memory
remove origin_program in framework and add i/o in c_sync_calc_stream

* test=develop update unittest sync operator I/O

* add example to get_startup_program()
* fix example to get_startup_program()

* fix distribute doc

Async exe support communicator

* implement distributed transpiler with fleet

* fix params with only 1 dim
* test=develop

* move var strusted to vars_distributed.py, add optimizer's block name, test=develop

* rename optimzier's seems complex, revert it, test=develop

* replace * with details, test=develop

checkpoint for distributed training.

test=develop

test=develop