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

But it does a AOT recompile from x86 to ARM for extensions and plugins according to the second presentation today.


Even if it's precompiled and not at runtime, we don't really know what the performance looks like, especially in hand rolled assembly where something that isn't a one-to-one cycle match could have obvious effects.


Also, Rosetta 2 doesn't support AVX. So it would rely on there being an alternate code path which would be AOT transpiled.




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

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

Search: