[MLID] Zen 6 Magnus Leak: AMD's MASSIVE APU for next gen console (+ Medusa Point Specs)

It's the same size as RDNA3.
I scaled, then trace over each block.

RDNA3.5 is even wilder.
The WGP is constantly changing.
Like Kepler said, it'll be bigger.

I'm looking it up and they are narrower than in your illustration. Even your RBE is wider than necessary. I think you can comfortably do 5/6WGP per row instead of 4.

Navi 48 XL, RDNA 4.

gVdSKbhMhvKTNn8U.jpg


Stryx point RDNA3.5

9cmjsNVFJxZLl6yD.jpg
 
Last edited:
Moore law is dead, any console more powerful will cost more and will not get cheaper overtime

More expensive means less public willing or capable of buy which in turn means more risk to publishers to launch games only on the console

So the question remains, if they launch a console called PS6 and all or almost all the games continue to be made and launched for and on the ps5 is this truly a PS6 or is just a PS5 Pro 2?

That's less a problem of Moore's Law, more one of Dennard Scaling these days.

That's a good point you've raised, I'm curious what the narrative and discourse will be going into "next-gen", and surrounding these consoles. Sony will likely. and based on past history go down an efficient route, like they did with PS5's "fast and narrow design", relatively less CU's but a faster clocked GPU or Xbox's slower but wider approach, more CU's but clocked relatively slower.

If we assume Magnus is Xbox's next chip, then it's likely they'll be sticking with the same design philosophy, but this time ensuring there's a clear advantage in performance compared to the competing PS6. Personally I welcome it, but I'm curious how the market will react to a product will likely could be priced $1000 +

What might also complicate things is the ML technology, PS5 Pro using PSSR, and will soon incorporate into it FSR 4, I'm wondering if Microsoft will also adopt FSR 4 and how this may complicate things considering Project Amethyst. I'm wondering if Microsoft may develop their own ML based upscaling technology.

It really just comes down to the value proposition MS can offer. Exclusives 100% won't be a part of that, since they release their games everywhere now. Price won't be it, at least not with any Xbox device using this Magnus APU.

At the end of the day it has to still deliver the convenience & usability of an Xbox console environment, but some of the more obvious openness & modularity of PC & Windows, in a way where they don't conflict with each other.

Considering that PS6 is releasing in 2027+, I don't see how they can guarantee a substantial power difference when PS6 will be on n2p and the Series X2 will be on n3p. It's a 40% density gap. That's not their goal because it's not going to be a realistic goal. Their goal is to be the best gaming PC one can get in a console like hardware / form factor (i.e. APU + soldiered GDDR7 main memory) that can rival RTX 5080 / 4090 performance in 2026. By 2028/2029, they'll have a successor that will trounce the PS6 handily.

Hypothetical PS6 in 2027 will have
8-10 core Zen 6
24GB GDDR7 on 256 bit bus (896GB/s bandwidth)
64-128mb Infinity Cache
68/72 Cus at 3.5 ghz (up to ~61 teraflops)
whichever forward UDNA 2/3 features Cerny decides to incorporate due to Project Amethyst.
~300mm2 die size
$599-$699 (Most likely $699)
such a PS6 will likely perform as well if not better with optimized console SKUs of games.

Yeah those are pretty realistic PS6 specs, and the thing with MS's approach is they can justify 3-year iterations across APU packages if they want, so a high-end device in 2029 outperforming PS6 would be expected.

But that type of device is also going to cost a lot more, for obvious reasons.

Hello

Why would you assume the Xbox consoles won't have optimized SKUs?

SIE's SDK and APIs have generally been better than Microsoft's for over a decade now. This gen it got so bad with Xbox that "the toolz" became a meme.

Basically, PlayStation APIs are more tuned and focused on game development, while the DX12U APIs are more focused on providing a huge gamut of solutions for general 3D pipelines that can include (but aren't limited to) gaming. However, the degree of choice with implementations you can roll with in DX12U actually can be time-wasting for engines if they need to plug through a crap ton of things to find the one solution that works well with them.

That type of redundancy isn't really a thing with PlayStation APIs, AFAIK, so for game dev they tend to be better. Plus SIE have groups like XDEV, which grew from the ICE teams, which were specifically made to help come up with solutions for game dev on PlayStation platforms like PS3 and onward.

That's disappointing NGL. Sony and MS have always being within one year after volume production of a node since Xb1/PS4 gen.

I'm guessing the AI boom is affecting availability of advanced nodes.

Well, someone on IconERA pointed out the Rapidus fab in Japan having recently developed a 2nm chip, and from what I read that fab is being developed to help companies (including Sony, who have a big investment in its development) to be less reliant on TSMC for wafers.

It's a good call, and if the fab can get large enough scale in the next few years there's a decent chance SIE & Sony will use its 2nm for PS6. But it's nothing locked in stone ATM, and could very well not happen. Tho, it's just nice to see another promising fab come up that could become a viable alternative, after Global Foundries basically fell behind (and even Samsung, for the smaller nodes, more recently).
 
That's less a problem of Moore's Law, more one of Dennard Scaling these days.
the cost stopped failing at 28nm a has been increasing since


its literally over in the economic side

if they choose to launch a new console on the market they can call it ps6 how many times they want but as soon as every game continues to launch in the ps5 the console will be a ps5 pro 2 in everything but the name
 
I don't think 24gb RAM is enough for a proper generational leap with PS6.

Consider the OS needs resources and such, and there are plenty of ideas for games that need a ton more RAM like for physics.
 
I don't think 24gb RAM is enough for a proper generational leap with PS6.

Consider the OS needs resources and such, and there are plenty of ideas for games that need a ton more RAM like for physics.
Could be enough if developers properly use PS5 fast I/O. They'll do it more if next Xbox is irrelevant to them.

But 3rd party developers really have to stop using CPU to stream in and decompress data on PS5 like in so many games still.
 
Last edited:
I'm looking it up and they are narrower than in your illustration. Even your RBE is wider than necessary. I think you can comfortably do 5/6WGP per row instead of 4.

Navi 48 XL, RDNA 4.

gVdSKbhMhvKTNn8U.jpg


Stryx point RDNA3.5

9cmjsNVFJxZLl6yD.jpg
Tried that already.

It makes the GCD bigger than the SoC.
For it to work, the GCD has to be on 2nm, while the SoC is on 3nm.

That may be why he only listed the node for the SoC. The GCD is probably on a different node.
 
Tried that already.

It makes the GCD bigger than the SoC.
For it to work, the GCD has to be on 2nm, while the SoC is on 3nm.

That may be why he only listed the node for the SoC. The GCD is probably on a different node.
That was my thought too, but since the video came out I went through a bunch of internal AMD documents and managed to find a mention of Magnus among a bunch of other N3P CPU/GPU/APU products in development so I think N3P is more likely.
 
well, next gen will need serious horsepower as that generation will be the raytracing generation.

current gen is the beginnings of raytracing, and next gen will be when it will be matured. similar to how gen5 was the first steps into 3D, while gen6 finally was actually good at 3D.

AI upscalers only help so much when it comes to raytracing.
if you play Doom TDA with a very low internal resolution, you'll start seeing very obvious artifacts from the drastically reduced ray count.
this doesn't happen with Doom Eternal as it doesn't rely on RT GI.
so at the same internal resolution Eternal will look better/more stable than Dark Ages, which means you can use more aggressive reconstruction without introducing to many issues.

ray reconstruction can help with with a bit, but can also introduce its own artifacts.


so both manufacturers need to make sure they have enough horsepower that raytracing, and possibly pathtracing run well and look clean.
you don't want to be the system that has constant boiling artifacts or excessive ghosting compared to the other one.
Ray reconstruction. That's all it'll be about in next gen. We've already see it on the SW2. A weak ass hardware looking reasonably well. For the average Joe it'll be indistinguishable. If you watch a DF video with direct comparison sure. Here are more upscaling artefacts, etc. But in general to appeal to the higher end user with a more expensive machine is going to be suicidal. I bet most will be content with the "more affordable" PS5 Pro. What a time to be alive, to write that last sentence.
 
Last edited:
That was my thought too, but since the video came out I went through a bunch of internal AMD documents and managed to find a mention of Magnus among a bunch of other N3P CPU/GPU/APU products in development so I think N3P is more likely.

Have you shared all you know about upcoming consoles?
 
The problem MS has is that they'll need to refresh all their Azure racks to support XCloud.

One key point I think that kinda got lost in the weeds was that from the start the back-end was designed to run clusters of Series S level hardware. So a massive jump in power at the base level is going to incur an equivalently huge increase in both installation and running costs for their ever so important streaming ambitions.

Unless they are pivoting away from their Xbox Anywhere approach back-end provision/running-cost has to be a larger area of concern than the contents of their consumer units.
 
Tried that already.

It makes the GCD bigger than the SoC.
For it to work, the GCD has to be on 2nm, while the SoC is on 3nm.

That may be why he only listed the node for the SoC. The GCD is probably on a different node.

Something like the below doesn't work? I made the WGP as narrow as the ones in RDNA3.5 and 4. Also the RBE should be much narrower because it's not increasing in transistor count much if at all.

K KeplerL2

id9X2C3NQE08kRoo.png
 
Last edited:
Something like the below doesn't work? I made the WGP as narrow as the ones in RDNA3.5 and 4. Also the RBE should be much narrower because it's not increasing in transistor count much if at all.

K KeplerL2

id9X2C3NQE08kRoo.png
We can expect UDNA CUs to be bigger than RDNA4 because of improved RT. I expect 4 Shader engines in order to put more CUs. XSX was already unbalanced in that area (vs PS5 and all others AMD RDNA2 GPUs) because it was also designed for compute servers. Could be the same here.

6 Shader Engines for a console doesn't make any sense. SEs take too much precious space.
 
Last edited:
One major problem with that. Wafer prices have increased drastically.
A 300mm^2 chip in N6 costs around 70-80$
But in N3P it will cost around 150-170$
And in N2P it will cost around 260-290$

Either the console price has to increase a lot, or Sony will have to pick a smaller chip and clock it higher.
The later is what Nvidia and AMD have been doing with their GPUs.
And Sony could stay on older process node as well. These consoles aren't mobile phones so staying on N3P or even older is still valid.

And hell, Switch 2 seems to be doing ok on the older Samsung node even.
 
Something like the below doesn't work? I made the WGP as narrow as the ones in RDNA3.5 and 4. Also the RBE should be much narrower because it's not increasing in transistor count much if at all.

K KeplerL2

id9X2C3NQE08kRoo.png
If we use that shape, the GCD becomes taller than the SoC.
 
Last edited:
? All I did is make your WGPs and RBEs narrower. Is there something I am missing?
You made the WGP narrower without taking into account it's area.

Making it narrower would also make it taller than in your edit because of it's area.

Keep in mind you're removing transistors.
 
You made the WGP narrower without taking into account it's area.

Making it narrower would also make it taller than in your edit because of it's area.

Keep in mind you're removing transistors.

Do we have a number for area of each WGP in RDNA5 on n3p? What is the area you used for the WGP?

Each WGP in the Navi 48 XL on n4 should be around 3.6mm2.
 
Last edited:
Isn't PS6 performance going to be similar to nvidia 4080? this card has 16GB of ram and even the 5080 has 16GB with a 256 bit bus and 960GB/s of bandwidth. Exactly what many think the PS6 will have (bus and bandwidth).

PS6 will likely have 24GB of ram.
 
Last edited:
GPU is gonna generate neural textures next-gen in many cases. Decompression hitching will probably be severely lessened if not completely mitigated due to less bus transfer.
 
Last edited:
Isn't PS6 performance going to be similar to nvidia 4080? this card has 16GB of ram and even the 5080 has 16GB with a 256 bit bus and 960GB/s of bandwidth. Exactly what many think the PS6 will have (bus and bandwidth).

PS6 will likely have 24GB of ram.
Unlikely unless a competitor to TSMC takes over.
 
I'll say this isn't for Xbox either if we're looking at codenames.

Xbox has been pretty consistent with their codenames lately.

Xbox One & Xbox Series codenames
Cities / places
Durango
- Xbox One base console codename → City in Mexico
Edmonton - Xbox One S console codename → City in Alberta, Canada
Aruba - Xbox One X dev kit codename → Island in the Caribbean
Tigard - Xbox Series X dev kit codename → City in Oregon, USA
Edinburgh - Xbox Series S AMD SoC codename → Capital of Scotland
Brooklin - Xbox Series X mid‑gen refresh codename → Likely variant of Brooklyn, NY, USA
Ellewood - Xbox Series S mid‑gen refresh codename → Variant of Elwood, which is a city name (e.g., Elwood, Illinois, USA)
Anaconda - Xbox Series X console codename → City in Montana, USA
Lockhart - Xbox Series S console codename → City in Texas, USA
Yuma - Xbox cloud streaming client / dev environment codename → City in Arizona, USA
Keystone - Xbox cloud streaming device codename → Refers to "Keystone State," nickname of Pennsylvania, USA

People / mythology
Scarlett
- Xbox Series generation umbrella codename → Human first name
Anubis - Xbox One S AMD SoC codename → Egyptian god
Dante - Xbox developer tools / SDK codename → Famous poet (or DMC character)
Uther - Next‑gen Xbox platform codename → King Uther Pendragon from Arthurian legend
Scorpio - Xbox One X console and SoC codename → Astrological sign
Aries - Rumored early Xbox Series prototype codename → Astrological sign


Just speculation, I can see this being made by Valve as well. Something that can go into multiple devices, e.g. handheld, table, mini PC, etc. Where the SoC has a GPU (orange rectangle) for the handheld and for tables or mini PCs, the GCD is then attached.

If you just move Strix Point CUs over to the GCD without any scaling, you get about 64CUs.

It's reminds me of Strix Halo.

 
Last edited:
I'll say this isn't for Xbox either if we're looking at codenames.

Xbox has been pretty consistent with their codenames lately.

Xbox One & Xbox Series codenames
Cities / places
Durango
- Xbox One base console codename → City in Mexico
Edmonton - Xbox One S console codename → City in Alberta, Canada
Aruba - Xbox One X dev kit codename → Island in the Caribbean
Tigard - Xbox Series X dev kit codename → City in Oregon, USA
Edinburgh - Xbox Series S AMD SoC codename → Capital of Scotland
Brooklin - Xbox Series X mid‑gen refresh codename → Likely variant of Brooklyn, NY, USA
Ellewood - Xbox Series S mid‑gen refresh codename → Variant of Elwood, which is a city name (e.g., Elwood, Illinois, USA)
Anaconda - Xbox Series X console codename → City in Montana, USA
Lockhart - Xbox Series S console codename → City in Texas, USA
Yuma - Xbox cloud streaming client / dev environment codename → City in Arizona, USA
Keystone - Xbox cloud streaming device codename → Refers to "Keystone State," nickname of Pennsylvania, USA

People / mythology
Scarlett
- Xbox Series generation umbrella codename → Human first name
Anubis - Xbox One S AMD SoC codename → Egyptian god
Dante - Xbox developer tools / SDK codename → Famous poet (or DMC character)
Uther - Next‑gen Xbox platform codename → King Uther Pendragon from Arthurian legend
Scorpio - Xbox One X console and SoC codename → Astrological sign
Aries - Rumored early Xbox Series prototype codename → Astrological sign


Just speculation, I can see this being made by Valve as well. Something that can go into multiple devices, e.g. handheld, table, mini PC, etc. Where the SoC has a GPU (orange rectangle) for the handheld and for tables or mini PCs, the GCD is then attached.

If you just move Strix Point CUs over to the GCD without any scaling, you get about 64CUs.

It's reminds me of Strix Halo.


You forgot Arden (XSX SoC) and Sparkman (XSS SoC).

Also you can't do any type of D2D in handhelds, the power waste kills battery life.
 
Last edited:
There's nothing on RDNA4 and RDNA5 hasn't even been announced yet.

RDNA4 i calculated using the CG image that we have. It's not the most accurate. From n4 to n3p we expect a 60% density increase so at minimum the WGP will be 2mm2.
 
You forgot Arden (XSX SoC) and Sparkman (XSS SoC).

Also you can't do any type of D2D in handhelds, the power waste kills battery life.

Yeah, doesn't seem like there is any pattern to MS SOC codenames. The only thing you can say is that they're not Shakespeare or Matrix references.

They're all over the place.
 
Last edited:
I need to know how much of a jump it is over the PS5 pro, is the CPU good?

Its far too early in the leaks to know if this is powerful enough.
for what? What do you need all this "power" for? What games. We aren't even pushing this gen's tech and haven't gotten many games at all.
Frankly as someone who doesn't give a damn about 4k, its been very underwhelming outside of faster load times, although expensive storage, bloated games taking up too much storage, and expensive games isn't helping.

Way more excitement from Switch and the PC indie and Console AA scene.
PS6/xbox next 2030.

Make the jump mean something again!
 
for what? What do you need all this "power" for? What games. We aren't even pushing this gen's tech and haven't gotten many games at all.
Frankly as someone who doesn't give a damn about 4k, its been very underwhelming outside of faster load times, although expensive storage, bloated games taking up too much storage, and expensive games isn't helping.

Way more excitement from Switch and the PC indie and Console AA scene.
PS6/xbox next 2030.

Make the jump mean something again!

Just for more 60 / 120 FPS titles. I just want a decent CPU in consoles. Hopefully the next Gen really delivers on that front.
 
Last edited:
for what? What do you need all this "power" for? What games. We aren't even pushing this gen's tech and haven't gotten many games at all.
Frankly as someone who doesn't give a damn about 4k, its been very underwhelming outside of faster load times, although expensive storage, bloated games taking up too much storage, and expensive games isn't helping.

Way more excitement from Switch and the PC indie and Console AA scene.
PS6/xbox next 2030.

Make the jump mean something again!
I want all the power I can get for my console games and my shooters as I always play games like COD and the upcoming Battlefield on console
 
I still wouldn't rule out this being for PS6 simply because MLID says it is, and he is the one providing us with the information.
His source may have directly indicated it, and/or it may be the same source that provided him with the PS5 Pro details.

Why the big upgrade? If Sony's goal is to include the bullet points of path tracing / 8K they will need something beefy.

As for the code name, I wouldn't be surprised if they switched from Matrix to something else given the last movie was a complete disaster.
 
So perfect for the next gen Xbox! /s

Btw, I don't remember you saying this: https://www.techpowerup.com/339101/...u-could-feature-96-cus-and-384-bit-memory-bus
I think the people writing this slop just conflate the speculation going on here and on x and the anandtech forums. I know at least 3-4 posters here also are regulars on anand. On anand there was speculation about the largest rdna5 gpu likely being in the 96cu ballpark.

Honestly it's pretty silly how much is taken out of context and then reported as fact.
 
Last edited:
I think the people writing this slop just conflate the speculation going on here and on x and the anandtech forums. I know at least 3-4 posters here also are regulars on anand. On anand there was speculation about the largest rdna5 gpu likely being in the 96cu ballpark.

Honestly it's pretty silly how much is taken out of context and then reported as fact.
I hate that they do that.

It has an effect of we not getting any good leaks due to leakers being put in the spot light and losing their sources.

But these guys don't care as long as they get their clicks.
 
I still wouldn't rule out this being for PS6 simply because MLID says it is, and he is the one providing us with the information.
His source may have directly indicated it, and/or it may be the same source that provided him with the PS5 Pro details.

Why the big upgrade? If Sony's goal is to include the bullet points of path tracing / 8K they will need something beefy.

As for the code name, I wouldn't be surprised if they switched from Matrix to something else given the last movie was a complete disaster.
Playstation changes their codenames every generation.

PS4 used UK cities/Latin references and PS5 used Shakespeare characters. With the Pro models sticking with Matrix characters.

I could of sworn I saw a leak awhile back that said the PS6 had two chips in development too.
 
Consoles GPU are around 60 series GPU of closest generation PS5 GPU is between 6600XT and 6700 in terms of real world performance, so is PS5 Pro GPU around 9060 and 9060XT, so I'll argue that PS6 GPU is gonna be around RTX 6060 or even Ti (Best case scenario like PS5 reaching 3060Ti performance in very specific conditions).

That would put it at around 5070 Super to 5070Ti Super level of performance with similar RT and ML capabilities of AMD really delivers in those. And it's not gonna be cheap at all.
 
Playstation changes their codenames every generation.

PS4 used UK cities/Latin references and PS5 used Shakespeare characters. With the Pro models sticking with Matrix characters.

I could of sworn I saw a leak awhile back that said the PS6 had two chips in development too.

The second might be the rumoured handheld device.
 
That could be the case or the MLiD leak is the two chip form that earlier leak.

I measured the die size of the WGP in your hand drawn diagram and the size came out to ~2.1mm2 which matches the 60% reduction from RDNA4 on N4.

96CUs is likely configuration for Magnus til we can better die shots that says otherwise.
 
I measured the die size of the WGP in your hand drawn diagram and the size came out to ~2.1mm2 which matches the 60% reduction from RDNA4 on N4.

96CUs is likely configuration for Magnus til we can better die shots that says otherwise.
When i get some free time, I'll do a more accurate representation.
 
When i get some free time, I'll do a more accurate representation.

You would need to fold and shrink the GDDR7 phy by 60% and then layout everything between the controllers.
Hard to do accurate since we're basing it off a recreation.
 
Last edited:
the cost stopped failing at 28nm a has been increasing since


its literally over in the economic side

if they choose to launch a new console on the market they can call it ps6 how many times they want but as soon as every game continues to launch in the ps5 the console will be a ps5 pro 2 in everything but the name
Been saying the same thing. This may be the very first time I don't get new consoles day zero. I mean, the PS5 is a nice, but not so large of a jump compared to ps4.

I bought a ps5 pro launch day, and I have buyers remorse. On screen, in action, it's not some major leap, it's barely noticeable.

And since PS6 will be BC it's going to be the same shit. I feel like at least the ps4 had better 1st party output from Sony than PS5 did. Nothing about the ps5 or series X really screamed "next gen" to me, at all. In fact BC and also the series S has held gaming back from taking leaps you couldn't do on the generation before.
 
Proelite Proelite
An update from MLiD.
EjBrgocI7tdm88pB.jpg


My guesses was pretty close.
If you just move Strix Point CUs over to the GCD without any scaling, you get about 64CUs.
Now if you zoom in close to one of the GDDR7 PHY, you can see it's split into two 16bit slices. Could he have misinterpreted one of these 16bit slices as a 32bit PHY?

If we look at it that way, 6 × 32bit = 192bit-bus.

A 192bit bus isn't as bad as it seems.
Micron reveals the future of GDDR7 memory
One of the most interesting aspects of GDDR7 isn't its raw bandwidth, it's the memory's planned capacities. 16Gb (2GB), 24Gb (3GB), 32Gb (4GB), 48GB (6GB), and 64GB (8GB) modules are part of the GDDR7 standard.

Possible capacities:
6 chips × 3 GB = 18 GB
6 chips × 4 GB = 24 GB
6 chips × 6 GB = 36 GB

SK Hynix launches GDDR7 with up to 40Gbps speed
And possible bandwidth:
192bit-bus ÷ 8 × 28 = 686GB/s
192bit-bus ÷ 8 × 32 = 784GB/s
192bit-bus ÷ 8 × 36 = 882GB/s
196bit-bus ÷ 8 × 40 = 980GB/s



The benefits of a 192bit-bus is less power, complexity and cost.
 
Top Bottom