fix compile error on windows

optimize distribute checkport

test=develop

fix build error on noavx

test=develop

* wip simplify operator framework

* wip

* wip

* done test=develop

* clean test=develop

* fix test=develop

* fix deps test=develop

* fix cpu build test=develop

* fix tensorrt build test=develop

* fix tests test=develop

* fix test=develop

* fix cpu build test=develop

jitcode act relu, exp, sigmoid, tanh

* fix space_to_depth_op unicode problem

* test=develop

change the target cost of test_label_semantic_roles to speed up test

* Fix truncated normal.

* Fix.

* Make nce support more distribution.

* Fix API.spec.

* Fix python API.

* Fix.
test=develop

* Fix API.spec
test=develop

* Fix sampler.

* Fix order of arguments in python API.
test=develop

test=develop

test=develop

Add PRelu tensorRT plugin and Conv2d transpose op converter

Fix expand op incorrect infer shape

* add cudnn ctc loss

* wip add test test=develop

* wip

* wip

* done test=develop

* move include cudnn test=develop

* test test=develop

* fix build test=develop

* fix build test=develop

* fix build on cudnn5 test=develop

* fix cudnn5 build test=develop

* fix cudnn5 build test=develop

* merge develop softmax functor change test=develop

test=develop

test=develop

fix typo test=develop

adjust the python script

* fix inference on gpu out of mem

the transfer logic in operator.cc will keep creating new scopes.

* rename and fix blas vsqr

test=develop

* update

test=develop