and add branch net comparing with cpu result

By shell command

```bash
sed -i 's#ifdef PADDLE_ONLY_CPU#ifndef PADDLE_WITH_GPU#g' `find ./paddle/ -name '*.h' -o -name '*.cc' -o -name '*.cpp' -o -name '*.c' -o -name '*.cu'`
sed -i 's#ifndef PADDLE_ONLY_CPU#ifdef PADDLE_WITH_GPU#g' `find ./paddle/ -name '*.h' -o -name '*.cc' -o -name '*.cpp' -o -name '*.c' -o -name '*.cu'`
```

Remove the pserver, trainer, evaluators and some useless gradientmachines when compile mobile inference library.

Add a space

Fix format

refine MKLDNNLayer logical: move forward and backward to MKLDNNLayer and remove copyOutputInfoToOtherDevice