MKLDNN conv + elementwise_add fusion: Fix transpiler integration to predict skip connection input of eltwise_add

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: some refactoring: consts, function calls instead of constant values

MKLDNN conv + elementwise_add fusion: graph is corrected based on actual argument name, not formal argument name

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

MKLDNN conv + elementwise_add fusion: inputs in pass modified. Support for new conv parameter. UTs corrected

MKLDNN conv + elementwise_add fusion: added reachability tests, inputs and outputs in graph nodes are transformed

MKLDNN conv + elementwise_add fusion: implementation of patterns refarctored, applied to graph. UTs added

[MKLDNN] Fuse Conv + Bias using Pass

do not enable MKL-DNN twice

Add ifdef guard for MKL-DNN placement pass

test=develop

test=develop

test=develop

test=develop

fix roi pool register

This patch also refactors conv+bn (includes changes from PR
https://github.com/PaddlePaddle/Paddle/pull/13926)
updated to use the mkldnn-placement-pass.

test=develop

Fix jit exp

After the MKL-DNN placement pass there is no need to enable MKL-DNN
in operators via executor

test=develop

* add detect and end2end code

* update the scale for coodinates restore

* fix merge bug with dev.

* fix merge bug with dev.

* test=develop

* fix code style test=develop

* fix code style test=develop

* test=develop

* test=develop

* test=develop

update readme.md

* add MKL-DNN placement pass

This patch also refactors conv+bn (includes changes from PR
https://github.com/PaddlePaddle/Paddle/pull/13926)
updated to use the mkldnn-placement-pass.

test=develop

* remove redundant pass list

* add comment on the default first pass

* fix test for conv+relu mkldnn fuse

test=develop