* fix nccl2 lars dist support

* put lars in momentum op

* add tests lars

* fix ci

* fix cpu kernel

* soft warning

* remove lars in test_recognize_digits.py

* move to another op

* add file

* update api.spec test=develop

* update test=develop

* fix api.spec test=develop

* wip

* wip, finish grad merge ops

* wip, finish graph build

* wip test running

* work on 1 gpu

* workable version

* update

* fix tests

* fuse broadcast op

* fix compile failed

* refine

* add batch merge test mnist

* fix CI test=develop

* fix build

* use independent bn params for batch merge test=develop

* update api.spec

* follow comments and for test

* wip

* refine tests test=develop

* follow comments test=develop

* remove startup bn modify test=develop

* follow comments test=develop

* fix merge test=develop

test=develop

test=develop

test=develop

test=develop

test=develop

test=develop

test=develop

test=develop

test=develop

1. Fix CUDA kernel when height is large than 2048.
2. Support input with more than 2D.
3. Fix unit test when k is large than 1.
4. Enhence unit testing.

test=develop

* speedup split_op
test=develop

* speedup split_op
test=develop

* rename ConcatGrad to Split

* refine concat and split
test=develop

* fix compile error

test=develop

test=develop

Add rpc profiler flags

test=develop

MKLDNN conv + elementwise_add fusion: skip connection attribute renamed. Comments about patterns added.

test=develop

MKLDNN conv + elementwise_add fusion: Fix output_data to point to the right tensor, also fix transpiler integration

MKLDNN conv + elementwise_add fusion: output and elemwise param share data in conv primitive. Output is properly allocated

test=develop