and change the size of test to make unit test faster
refine comment and log of mkldnnlayer

and add activation in unit tests

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