* fix threaded executor bug
test=develop

* change the order of class member
test=develop

* Fix Travis CI
test=develop

* refine parallelExecutor
test=develop

* Polish op_handle
test=develop

* Remove unnecessary op_handle
test=develop

* Fix Travis CI
test=develop

* Fix fetch bug
test=develop

* Remove WaitInputVarGenerated

* Fix OpHandleBase::Run
test=develop

* debug
test=develop

* use origin fetch_op_handle
test=develop

* Revert op_handle_base.cc
test=develop

* Polish code
test=develop

* Fix OpHandleBase::Run
test=develop

* code refine

* test CI and CE
test=develop

* fix OpHandle::Run
test=develop

* refine AllReduceOpHandle
test=develop

* Polish code
test=develop

test=develop

* refine profiler && add runtime tracer

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* fix bug && test=develop

* add thread id map && test=develop

* test=develop

* testing

* bug fix

* remove cuda event && refine code && test=develop

* test=develop

* test=develop

* test=develop

* fix windows temp file && test=develop

* test=develop

* fix windows bug && test=develop

* fix start up issue && test=develop

* code polish &&  test=develop

* remove unused code && test=develop

* add some cupti cbid && test=develop

* add FLAGS_multiple_of_cupti_buffer_size && test=develop

* fix compile error && test=develop

* add keyword && test=develop

* fix && test=develop

* code polish && test=develop

test=develop

Fix code to support cpplint syntax check

test=develop

Dry run tests will skip `Op.Run` and just perform job scheduling. It helps to analysis dead lock in PE.

test=develop

test=develop

test=develop

test=develop

It seems that the blocking queue might be destroyed early than Run
method complete. It might because the Run method throw some unhandled
exception. However, it should be shared_ptr when multthread access an
resource. So change BlockingQueue as a shared_ptr.

test=develop

    Node should be created by Graph::CreateXXX so that
    they are managed by graph.

Reduce one level of inheritence.

Add a few more RecordEvent.
Cleanup

small thread-safety fix and doc improvements.

replace use_event with use_cuda, because use_event means the program running with CUDA, so use_cuda maybe more intuitive.