- Mar 3, 2017
- 1,779
- 6,798
- 136
Strix to Medusa is 10Qs with a +100MHz refresh in between.It's an 8Q cadence with client SoC uncore being the lowest priority (GPGPU > server > GPU > client SoC).
KRK's the actual part it succeds so it's 8Q-ish exactly.Strix to Medusa is 10Qs with a +100MHz refresh in between.
DMR still supports higher memory speeds I'm pretty sure lolYep, Intel no longer has a high speed mem advantage as that is equalised.
Isn't this Zen 7?All that leaves them with is AMX, which is neutralised by ACE in Florence.
Nope, both MRDIMM-12800DMR still supports higher memory speeds I'm pretty sure lol
Yes Z7 EPYC is Florence. Intel still autowins in GEMM benches until then.Isn't this Zen 7?
no.DMR still supports higher memory speeds I'm pretty sure lol
yes. but Intel gotta touch Venice first.Isn't this Zen 7?
