It's been adopted by Apple, not trademarked.
Of course GPGPUs, Cells and such can tremendously improve performace and efficiency. My GF9800GT crunches 4500 Folding@Home PPDs or 5500 distributed.net WUs/day on ~100 Watts. That's nearly tenfold of a really fast system using quite a bit more power.
Of course the clients are currently using CUDA, but an open standard like OpenCL is definitely a step forward to broader support.
