Very good result. AMD has an even bigger lead in 32B. My GTX 980@stock had to crunch for nearly 51 minutes.

Very good result. AMD has an even bigger lead in 32B. My GTX 980@stock had to crunch for nearly 51 minutes.

 

AMD was always better in OCL.

AMD was always better in OCL.

Yes, but that's not the reason for the good score. The 290s have exeptional integer performance. The implementation itself only accounts for als much as 4 percent in my first tests with the new CUDA version. I am a bit disappointed.

680 was the last great consumer-grade CUDA card