* Revert "Revert "Add Event for TensorCopy" (#16022)"

This reverts commit e2da3a5b.

* use default stream
test=develop

* Revert "Add Event for TensorCopy (#15953)"

This reverts commit 7235fd66.
test=develop

* fix CI
test=develop

Add Event for TensorCopy 

* Revert "Add Event for TensorCopy (#15953)"

This reverts commit 7235fd66.
test=develop

* fix CI
test=develop

Add Event for TensorCopy 

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

Fix the bug that profiler cannot trace the nccl allreduce operator

test=develop

Fix code to support cpplint syntax check

test=develop

Add a few more RecordEvent.
Cleanup

In cupti samples, only cuptiFlush is used.
I can't find any places calling cuptiFinalize and
this API can error out as not_implemented in some
cuda installation.

    Experiment on vgg flower, 2 trainers, 1ps.
    more trainer could have more speedup.

    After:
    Pass = 0, Iters = 327, Speed = (7.52) img/s
    Before:
    Pass = 0, Iters = 385, Speed = (6.77) img/s

smaller binary proto
avoid untrackable kernel

* Make CUPTI_LIB_PATH not passing by macro.
* Add missing header