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

64 KB is a pretty significant budget for such a small operation. I've had a variant that uses 768 bytes with some extra logic, but will deprecate that kernel soon.

https://github.com/ashvardanian/StringZilla/blob/0d47be212c5...



If you scale up the multipliers, you should be able to eliminate the variable shift, which would reduce the lookup table to 512 bytes.


This seems like something that could be in hardware to allow native execution of the instruction. Is that not the case anywhere?




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

Search: