Compute Unified Device Architecture

At present, we are somewhere in-between these points the barrier to utilizing GPU hardware for general purpose computation has been reduced by the introduction of general purpose GPU programming models such as NVIDIA s Compute Unified Device Architecture (CUDA) [15] and AMD s Stream [20]. However, algorithmic paradigm shifts are often required in existing codes to maximize such performance offered by the massively parallel GPU hardware. 

Finally, we believe that Thread-Level Parallelism (TLP) is one of the next trends in computer architecture and therefore have started implementing a Graphic Processing Units (GPU) based on Compute Unified Device Architecture (CUBA). We are plaiming on expanding software-based and hybrid techniques to protect such systems in the presence of faults. 

---