Change the CpuMatrix::copyFrom and CpuVector::copyFrom with the stream parameter to the synchronous interface.

reference or raw matrix (Matrix & or Matrix *)
contextProjectionForward
contextProjectionBackward
contextProjectionBackwardData
contextProjectionBackwardWeight
classificationError
The mul functions would be updated later.

out = w * input
where w is a parameter of size 1

Change-Id: Ife682d62323ceb1a20cbbf6269421b20a862d888

* Add matrix inverse

* Add benchmark for PaddlePaddle, tensorflow and caffe

* ConvProjection to reduce memory for goolenet

* Add unit test for ConvProjection.
1. unit test in test_LayerGrad.
2. compare the ConvPorjection and CudnnConvLayer, also compare the concat_layer+img_conv_layer and concat_layer_conv_projection.

* Reduce cudnn_conv memory and add benchmark document.
1. Use TmpMatrix as the workspace in cudnn_conv to reduce gpu memory. It reduce lots of memory.
2. Add benchmark document.
3. fix smallnet_mnist_cifar.py in paddle.

* Add job=time and refine cudnn_conv to reduce gpu memroy and speed up

* Refine cudnn_conv and shared biases operation in concat_layer and mixed_layer.

* follow comments

* follow comments

* Use unique_ptr to prevent memory leaks in CudnnConvLayer.