high performance computing on graphics processing units: hgpu.org

We present the design and performance analysis of a GPU-optimized implementation of a disk encryption application employing the XTS mode of operation applied together with the Twofish algorithm within the well-known TrueCrypt suite. We show how to correctly tune the design parameters, including data allocation, thread packing, and parallelization strategy. Overall, our implementation of TrueCrypt running on a NVidia GTX260 GPU outperforms by 67% the baseline implementation running on a four core CPU.