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

Multithreaded applications tend to share a lot of data between threads, and we already know Intel's mesh fabric core interconnect[1] seems to be inferior to AMD's chiplet+io die in terms of performance and access latency uniformity.

[1] used in all 10core+ Intel CPUs.



AMD's 4000 APUs are monolithic and don't use separate chiplets and IO die. The chiplet + infinity fabric has higher latency than Intel, but that's not a problem for the APUs.


The 10900 uses a ring and IMO the mesh is superior to Infinity Fabric.




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

Search: