test=develop

* optimize depthwise conv by register memory
* test=develop

test=develop

test=develop

  1. Accelerate SelectedRows MergeAdd functor

  2. Add SelectedRowsSumTo functor to support MergeAdd multiple SelectedRows into one

test=develop

* "fix compile error"

* "fix ci"

* rerun ci
test=develop

* test=develop

rerun ci

test=develop

* refine reduce by cub
* optimize KernelDepthwiseConvFilterGrad
* optimize depthwise conv and reduce mean and reduce sum
* fix bug: dilation
* cuda arch and cuda 8 compatible

This reverts commit a6c8d6b9.

This reverts commit bd79e046, reversing
changes made to 6b4d290c.

* Optimize GRU with AVX instruction

* Clean code

* Add the Unitest and fix the align issue

* Remove the remanent part of the unitest part

* Code clean

* Fix the parameters length issue for fusion_gru to pass CI

* Change the default type as float32

* Add Preface

* Add demo code

* Save file

* Refine code

* seems can work

* use elementwise strategy

* Use ElementwiseComputeEx

* Add comments

* extract functions from operator

* Refine code

* Follow comment

* code refine

* add op_fuse  pass

* add backward

* code refine

* use TopologySortOperations

* follow comments

* refine IsFusible

* code enhance

* fix op_fusion_pass

* refine code

* refine fuse_elemwise_act_op

* adjust the input and output

* refine logic

* add intermediate_edge

* disable inplace

* follow comments

* refine logic

* follow comments

* Remove the removable IntermediateOut

* change strategy

* code refine

* enable fuse backward

* code refine

* code refine

* rename unit test

* follow comments