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

Plus lower base and boost clocks



That is somewhat offset by twice as much memory bandwidth. Every L3 miss on a 3990X is twice as expensive as it's on the 7702P


And the EPYC uses higher latency RDIMMs and LRDIMM RAM. Traditionally, server RAM (RDIMM or LRDIMMs) is 50ns+ slower than consumer UDIMMs.

Video games and pointer-chasing care more about that latency figure than bandwidth. I'm sure there are bandwidth-bound tasks, but any latency-bound task would prefer highly-clocked, over-volted (1.35V) DDR4 UDIMMs at 3200 MT/s CAS16 or faster.

Server RDIMMs are naturally slower, due to the register (and LRDIMMs are probably even slower). RDIMMs and LRDIMMs are designed for capacity more so than latency: you can have 1TB of LRDIMMs RAM on one machine but all the RAM runs slightly slower (3200MT/s maybe CAS22 or slower) as a result.


> 50ns+ slower than consumer UDIMMs.

is that like twice as slow?




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

Search: