Hacker News new | past | comments | ask | show | jobs | submit login

Because it requires nVidias cooperation in implementing OpenCL. And of course they are not about to do so in a useful manner when they are leading with CUDA.

Also, the premise of OpenCL is somewhat faulty. You end up optimizing for particular architectures regardless.

Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | Legal | Apply to YC | Contact