Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

REP MOVS is still extremely fast --- and also small. It'll copy cacheline-sized chunks if the size is large enough.

LOOP is a bit of a weird case. I've seen it benchmark both slower and faster than dec/jnz depending on the surrounding instructions.



loopXX instructions do not use CPU LSD (Loop Stream Detector) while cmp/jnz construct takes advantage of it. This speeds up some small loops. Also, there are some rules in intel manuals for instructions within cmp/jnz loop like no mismatched push/pop, etc.

now, does anyone know why?


like no mismatched push/pop, etc.

My guess is virtual stack pointer update prediction latency.

To expand on that, Intel's CPUs have had for a long time a separate piece of hardware dedicated to a "virtual" stack which speeds up push/pop instructions. If pushes and pops are not mismatched, then all stack operations can stay entirely within that and there's no need to update the "real" stack pointer nor stack entries upon leaving the loop.


Thank you for your answer! Any idea why would loops not use LSD when programmed using loopXX instructions but would use when cmp/jnX is used?




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

Search: