This is what I was wondering as well. I work on a BigData BI solution, and in my experience IO and not processing time is the final bottleneck. I would expect working on the GPU to be slower, not faster, than working on CPU, because of the extra time needed to copy the data/results into/out of the VRAM. Also 40M tweets is what I would consider the very bottom of the BigData scale. I would guess the use-case here is one where the calculation is very complex, much more so than the data itself.