GPU code addition.

[karanchahal]

This pull request seeks to add building this project for the GPU. Currently, the kernel for the dot product is added (matrix multiplication).

To build for the GPU, the cuda compiler takes in main.cu as the source file. main.cu includes buildTensorflowGpu.h instead of buildTensorflow.h (as in the main.cpp case).

The buildTensorflowGpu.h file inserts code for the CUDA kernels into the project by including the gpu/defn.h and gpu/impl.h.

These two files contain the kernel code definitions and implementations respectively.

Finally to build for the cpu, we fire the make all command and to build for the GPU we fire the make gpu command.