really AMD sees such profit opportunity in having 4p+8c rammed literally everywhere in 5 product families instead of classic 12 full cores ccd?
Oh there's a ton.that there's little-to-no advantage for 12p standard core CCDs.
In mobile power envelopes? How frequency-restricted are these dense cores gonna be?Oh there's a ton.
In any power envelope.In mobile power envelopes?
They're just on N3p.How frequency-restricted are these dense cores gonna be?
phat.DENSEWe can argue back and forth but AMD doesn't do big.LITTLE.
AMD users laughed at Intel ADL's big.LITTLE, yet AMD was just a gen or two late with big.LITTLE...
What AMD really needs to step up its game in mobile is to provide a top-noch SW/HW support and viable (complete) platforms to OEMs. OEMs juggling with 7 different SKU lines doesn't seem like it.
In any power envelope.
Why do you think all server Zen6 is N2?
?I have doubts that the Hi product will ever make it onto an actual machine
In any power envelope.
Why do you think all server Zen6 is N2?
They're just on N3p.
they are SoCs (with maybe bundled i/o too)Wait, ALL the 4p+8c Zen6 dice are on N3p? Even the ones that go into Halo?
anything with graphics is 3nm. you are not getting graphics on 2nmyeah I don't get it
server zen6 EPYC cores are both dense and N2
client zen6 has N3P instead???
as with zen5, the flagship-on-mobile-package will be both best deal and best performer
24 full phat N2 cores + 2LP + 3D (X2)
1 IOD, 1 CCD, 3 SoCs, 2 GMDs (which are also used for dGPUs)
Olympic Ridge: IOD + CCD
Medusa Point: SoC + (optional) CCD
Medusa Premium: SoC + AT4 GMD
Medusa Halo: SoC + AT3 GMD
10965HX3D (24 full cores) + dGPU > Medusa Halo
if there's 5 medusa CPU families before Halo, then Halo will be priced 3000+++ and won't be worth vs full 10965HX3D on mobile
only for LLMs basically
All SoCs are on N3P. All CCDs are on N2PWait, ALL the 4p+8c Zen6 dice are on N3p? Even the ones that go into Halo?
That's not part of client Zen6Isn't the Magnus SoC + AT2 config missing here, as it follows the same SoC + ATx scheme?
That seems unfortunate that they don't have an N2P version of the SoC for Halo/Halo mini. It'll only be a problem for Halo mini I guess.All SoCs are on N3P. All CCDs are on N2P
The only difference between Magnus and the rest is it'll initially be sold to a single and exclusive client, Microsoft. It it's using AT2 which is also going into dGPUs, then it's safe to assume there are no custom blocks in the silicon (not that there were any relevant ones in Scarlett and Lockhart anyway).That's not part of client Zen6
I'd say it's more to gain in having the GMDs made on N2P than the SoC.That seems unfortunate that they don't have an N2P version of the SoC for Halo/Halo mini. It'll only be a problem for Halo mini I guess.
Nope.The only difference between Magnus and the rest is it'll initially be sold to a single and exclusive client
medusa premium (mini halo) is for whom actually ?Nope.
Consoles have poverty CPUs.
Client stuff can't go with poverty CPUs anymore.
It's for no one.medusa premium (mini halo) is for whom actually ?
Wtaf is stx1 thenthere was no such product / swimlane before right ?
that is succeeded by medusa point 1 right ?Wtaf is stx1 then
