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

Another option, just annotate it with your compiler's cache alignment attribute. That way you need not redo the size for each architecture.



That'd just leave you with wasted space rather than making more space available for storing things inline. For the real-world tests I would not be at all surprised if the reduced number of heap allocations was a bigger source of speedups than the more cache-friendly reads.




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

Search: