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

https://en.wikipedia.org/wiki/Apple_M1#CPU:

“The high-performance cores have an unusually large 192 KB of L1 instruction cache and 128 KB of L1 data cache and share a 12 MB L2 cache; the energy-efficient cores have a 128 KB L1 instruction cache, 64 KB L1 data cache, and a shared 4 MB L2 cache.”

⇒ chances are you don’t even have to try to fit an emulator of a 8-bit machine and it memory into the L1 cache.




I think you would very much have to try to fit a complete emulator of, say, the Game Boy into 128 + 64KB.

There's plenty of behaviour that is self-evident on real silicon but verbose and tricky to express in software.


Real question about L1 caches. For a long time, x86 (Intel & AMD) L1 caches have been pretty much pegged at 32KB. Do you know why they didn't make them larger? My guess: There is a trade-off between economics and performance.


There is a trade-off between cache size and latency.


Ok, so why do the new Mx chips from Apple have an L1 cache size greater than 32KB? Did they solve some long standing design issue?




Consider applying for YC's Summer 2025 batch! Applications are open till May 13

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

Search: