• Hey Guest. Check out your NeoGAF Wrapped 2025 results here!

[MLiD] XBOX Magnus RDNA 5 Finalized

Even if Magnus has more RAM, and 40% better than PS6 on paper, I think with all this overhead and OS bloat, it will most likely be 10%-15% better. But the real question is better in what? Shouldnt the major change in architecture produce exceptional visual fidelity to the point of diminishing returns or will it regress to more shitty DF videos on: Magnus having more grass and shrubs in certain areas, shadow details being better when character is walking, less pixelated grass blades and flowers. I mean like come on!
wLBB0cQxWdW5kw3Y.jpg
 
...

yea yea. Doesn't change my point. I already edited it in.
What point? You didn't address the more realistic simplified bandwidth compromises on the XsX - from the two memory pool contention - I explained and just doubled down on info that misrepresents the XsX memory balancing act when trying to use a unified 12GB with the GPU.

Let's put some depth into the simple theoretical exercise of a unified 12GB for the XsX GPU.

Off the bat we'll look at CPU bandwidth.

40GB/s is in the ballpark from the Road to PS5, so we'll use that for both systems.

on PS5 that's a simple unified deduction,

448GB/s - 40GB/s = 408GB/s for a 12GB VRAM pool for use with the GPU.

On XsX we have 10GB/s at 560GB/s and 6GBs at 336GB/s but the CPU 40GB/s is from 336GB/s where both bandwidths share unified processing time so 40/336 = ~12% instantly means the 560GBs is depleted to use just 88% of the time (~494GB/s) before we start looking at the 2GB of VRAM on the CPU memory side.

If we say a typical game sticking with 10GBs of VRAM averagely uses (494/10) 49.4GB/s per GB for argument sake - omitting all inefficiencies for this example. But as we are now moving up to 12GB that distribution no longer holds, so first of all we need to work out how much longer the GPU processing will take to complete a CPU memory bottlenecked task on the 2GB compared to a GPU memory bottlenecked task on 2GBs of the 10GBs. Which should be merely dividing 560/336, giving us a ratio of x 1.66 (5/3rds).

To then workout how much of that remaining 88% of the processing time is needed for 2GB at 336GB/s versus the 10GBs at 560GBs - to give each GB equally processing capacity we need to scale the 2GBs by the 5/3rds and treat it as (10/3) 3.3GBs vs 10GBs, effectively normalizing the bandwidths for both pools.

That way you get A) = 3.3/13.3 x 0.88 and B) = 10/13.3 x 0.88 to get

A) (10/3) /(40/3) x0.88 = (30/120) x 0.88 = (1/4) x 0.88 = 0.22
B) 10/(40/3) x 0.88 = (30/40) x 0.88 = (3/4) x 0.88 = 0.66

so then we get in total for the CPU memory (0.12 + A) x 336 = (0.12 + 0. 22) x 336 = 114.24 GB/s
+
the GPU side 0.66 x 560 = 369.6 GB/s

= 483.84 GB/s

which in these idealised circumstances is already a lot closer to the unified 448GB/s of the PS5 bandwidth and in real terms the 22%(0.22) percent of the 336GBs isn't 114.24GBs for the GPU, because it is wasteful by a factor of 5/3rds meaning in real bandwidth terms to the GPU it is actually 44.35GBs, which when added back to the 66% (0.66) 369.6 GB/s produces a GPU total effective bandwidth of ~414GB/s versus the PS5's 408GB/s.

The major missing piece here is that this is all idealised for the XsX memory use, without the big efficiency losses of copying between the pools with redundant data that are necessary, the need for a second garbage collector/memory defragger for the slower pool taking further bandwidth time, and the small percentage memory controller efficiency loss for switching modes/pools, even if assuming all of those solutions are perfect too despite the greater complexity.

Realistically the XsX using 10GBs for VRAM probably matches the PS5 for real-time GPU bandwidth, and at 12GBs in real game code is probably (90% of that 414GB number via complexity) around the 370GB/s - obviously still ignoring that all these figures will be actually lower scaled equivalents of their theoretical maximums used here.
 
Last edited:
DF videos on: Magnus having more grass and shrubs in certain areas, shadow details being better when character is walking, less pixelated grass blades and flowers. I mean like come on!
Yes DF will do PC vs PS videos, same as they already do.
I don't think they will have specific Xbox vs PS videos anymore, it's more likely that they'll do Steam Machine vs Xbox videos since that's the same product segment.
 
What point? You didn't address the more realistic simplified bandwidth compromises on the XsX - from the two memory pool contention - I explained and just doubled down on info that misrepresents the XsX memory balancing act when trying to use a unified 12GB with the GPU.
Good write up. It's quite informative/interesting.

What you're essentially saying is that because the CPU accesses the memory bus at a lower rate, the effective bandwidth use of the CPU is higher. Thus my estimate of 504 GB/s for the extreme highly unlikely scenario (12/12.5GB to GPU) isn't accurate and that it should be ~477 GB/s. Or specifically, 40 * 560 / 336 =66.667. 26.7 GB/s wasted by CPU.

imo the scenario is so rare it's borderline irrelevant (a scenario where dGPU uses than 12/12.5GB). However I will engage since you put a decent amount of effort.

First, the 40 GB/s bandwidth for the CPU is on the high end.



Not a single game over 20 GB/s. Most below 10 GB/s for CPU. A game where CPU uses 500 MBs total will not have the CPU use 40 GB/s or even 20 GB/s. But lets be safe and say 20 GB/s

In other-words, CPU uses 20 * 560 / 336 = 33.3 GB/s

Instead of a 504 GB/s effective memory BW as I said. It's 504 - (33.3-20) = 491 GB/s once you account for CPU's accesses being slower.

This is an interesting technical discussion. However, this isn't a useful one. XSX having a slightly lesser memory bw lead over PS5 under extreme conditions doesn't explain WHY PS5 is beating it. This is why I was getting irritated.

The actual story of why XSX is losing is the weaker front end. And it's being buried while we discuss precisely how much faster is XSX's memory bandwidth.

And it's the relevant conversation since magnus has a 26-31% stronger backend and 33% stronger front end at the same clock. And magnus is expected to clock higher, has more than double the L2 cache and has a wider unified memory bus.

This is what I meant by saying that PS6 Can't compete and that Magnus is basically a PS6 Pro. Sony tied last gen because MSFT fumbled. Xbox haven't repeated XSX's mistakes.
 
Last edited:
This is what I meant by saying that PS6 Can't compete and that Magnus is basically a PS6 Pro. Sony tied last gen because MSFT fumbled. Xbox haven't repeated XSX's mistakes.
It's ~3:1 for PS5... 4:1 at the end of gen.
It will be >9:1 for PS6.
They just don't need to compete, Xbox is dead.
 
Last edited:
So is Magnus basically the better Steam
machine? 1200 €/$ for RTX 5080 Performance doesn't look bad at all if done right (i.e. open system).
This could very well lead to a migration from existing PC players to Magnus…but what's in it for Microsoft? Or will it only be possible to buy games from XBox Store?
Maybe they will sell it boundled with a long term( 2 years) gamepass premium subscription.
 
Good write up. It's quite informative/interesting.

What you're essentially saying is that because the CPU accesses the memory bus at a lower rate, the effective bandwidth use of the CPU is higher. Thus my estimate of 504 GB/s for the extreme highly unlikely scenario (12/12.5GB to GPU) isn't accurate and that it should be ~477 GB/s. Or specifically, 40 * 560 / 336 =66.667. 26.7 GB/s wasted by CPU.

imo the scenario is so rare it's borderline irrelevant (a scenario where dGPU uses than 12/12.5GB). However I will engage since you put a decent amount of effort.

First, the 40 GB/s bandwidth for the CPU is on the high end.



Not a single game over 20 GB/s. Most below 10 GB/s for CPU. A game where CPU uses 500 MBs total will not have the CPU use 40 GB/s or even 20 GB/s. But lets be safe and say 20 GB/s

In other-words, CPU uses 20 * 560 / 336 = 33.3 GB/s

Instead of a 504 GB/s effective memory BW as I said. It's 504 - (33.3-20) = 491 GB/s once you account for CPU's accesses being slower.

This is an interesting technical discussion. However, this isn't a useful one. XSX having a slightly lesser memory bw lead over PS5 under extreme conditions doesn't explain WHY PS5 is beating it. This is why I was getting irritated.

The actual story of why XSX is losing is the weaker front end. And it's being buried while we discuss precisely how much faster is XSX's memory bandwidth.

And it's the relevant conversation since magnus has a 26-31% stronger backend and 33% stronger front end at the same clock. And magnus is expected to clock higher, has more than double the L2 cache and has a wider unified memory bus.

This is what I meant by saying that PS6 Can't compete and that Magnus is basically a PS6 Pro. Sony tied last gen because MSFT fumbled. Xbox haven't repeated XSX's mistakes.

You are ignoring the fact that the Xbox (outside maybe MS studios games) will run PC games and not dedicated software made specifically for it, nobody is going to bother to make "xbox" version of games, so any advantage it has over the Ps6 is going to be nullified right there and it will get even worse as times goes by, specially since many devs will use just the ps6 as baseline for development.

It all remains to be seen but if Xbox its just a "ps6pro" running pc storefront games, than I risk to say the ps6 will have the uperhand eventually and more definitely in games developed using the ps6 as baseline and then ported to pc.

The hardware gap dosent look large enough to surpass dedicated software development vs generic storefront pc game
 
You are ignoring the fact that the Xbox (outside maybe MS studios games) will run PC games and not dedicated software made specifically for it, nobody is going to bother to make "xbox" version of games, so any advantage it has over the Ps6 is going to be nullified right there and it will get even worse as times goes by, specially since many devs will use just the ps6 as baseline for development.

It all remains to be seen but if Xbox its just a "ps6pro" running pc storefront games, than I risk to say the ps6 will have the uperhand eventually and more definitely in games developed using the ps6 as baseline and then ported to pc.

The hardware gap dosent look large enough to surpass dedicated software development vs generic storefront pc game
Now prove your point that Magnus won't have dedicated Console SKUs for the Xbox ecosystem. Don't just make things up to fit your bias, bring some evidence. The other guy said there won't even be any Xbox ecosystem versions at all, even PC SKUs, and that MS will be selling Steam/Epic games, lmao.
 
Now prove your point that Magnus won't have dedicated Console SKUs for the Xbox ecosystem. Don't just make things up to fit your bias, bring some evidence. The other guy said there won't even be any Xbox ecosystem versions at all, even PC SKUs, and that MS will be selling Steam/Epic games, lmao.
🤣Prove your point shenshitsu.
Spongebob Squarepants GIF
 
Top Bottom