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

If you mean branch prediction, then yes, it will end up inadvertently executing the wrong instructions and discard them, but it halts execution of the wrong branch at the first opportunity and reschedules to correct its mistake.

A GPU will execute both branches to completion.




No, he means the SSE predication instructions.

The comparison instructions let you build a mask vector, and instructions like blendv use that mask vector to only impact a subset of elements.

It's been a common feature on many RISC and VLIW cpu's over the years. It is in no way unique to GPU's.


Ah, thanks for clarifying.




Consider applying for YC's Spring batch! Applications are open till Feb 11.

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

Search: