Coulomb_Barrier
Member
Well we'll have to wait and see. Might be few months until any other hardware info as detailed as GDC (even if not much was reveled then).
-
Hey, guest user. Hope you're enjoying NeoGAF! Have you considered registering for an account? Come join us and add your take to the daily discourse.
The PlayStation 5 GPU Will Be Supported By Better Hardware Solutions, In Depth Analysis Suggests
- Thread starter sonomamashine
- Start date
Well we'll have to wait and see. Might be few months until any other hardware info as detailed as GDC (even if not much was reveled then).
Yoshi
Headmaster of Console Warrior Jugendstrafanstalt
Sorry, but do you have any idea how a computer system works? You have data in a persistent location (in the PS5's case: SSD), which is loaded into RAM when required and further into CPU / GPU registers for computations. The connection between CPU/GPU and RAM is very fast, whereas the connection to the SSD is slower, butmuch faster than what we are used to right now. This means that loading times will be shorter and streaming assets from disc is more viable than in past systems. However, this is not what a bottleneck usually refers to (and if you want to apply the term just to data transfer rates, then the SSD bus is of course still the bottleneck, because it is only 1% as fast as the RAM); a bottleneck refers to one of the system components that is limiting the applicability of some technique, or is weaker in relation to the other components.
For the current gen systems, the CPU is the bottleneck, whereas previous gen was bottlenecked by RAM. Whether one component in the design of PS5 or XSX ends up underpowered in comparison to the rest of the hardware is something that we will only know in a couple of months, or maybe even years. Every single time the console vendors all try to avoid bottlenecks, because a bootleneck in one area means that they overspent in the other areas. XSX and PS5 are certainly both designed with the intent of avoiding bottlenecks.
This queueing you are talking about is magical thinking, the process of obtaining data is still very much the same on PS5 as it is on other systems and even if transfer rates were good enough to use the SSD as an extension of RAM (it is not), just take a look at the design of Nintendo 64:
Peak bandwidth of RAM 562 MB/s with a RAM size of 4 MB
Cartridge bandwidth of 264 MB/s at a maximum cartridge size of 64 MB
By comparison of the capacities and speeds, you will instantly see that relatively speaking, the Nintendo 64 was much, much better in terms of data transfer rates. Would you want to claim that N64 was a system without bottlenecks?
Okami Haundo
Member
I think Microsoft's approach makes sense when you consider that they're releasing all their first party content on PC as well. In a year or two that'll be a different story, and we're more likely to see SSD's as the baseline for PC and console games.
When that time does come, I'll be curious to see what performance range developers settle on for the "minimum" PC spec. Especially in relation to SSD speeds.
Ascend
Member
There's no such thing as removing all bottlenecks. There is always one. It's kind of ironic of the PS5 supposedly removing all bottlenecks while the GPU and CPU can't run at max speeds without bottlenecking each other.
DynamiteCop!
Banned
Uh...yeah...no...
He said it was because of power management, a literal non-concern from a very low power device so obviously false justification.
Shin
Banned
I've been eyeballing the manual for a while now, I reckon that will give a lot of answers and once the official specifications page goes up.
We've yet to see the FCC SDK registration as well, either way both sides did great work with their respective hardware that much is a fact.
2013 we had 8GB GDDR5 and that was about it IIRC and the other side had ESRAM fiasco plus Kintect, new gen points and laughs at 2013 in a big way.
hyperbertha
Member
lol what propoganda? Its common knowledge at this point the PS5 will use dynamic resolution but will have a higher quality of assets. The SSDs aren't in the same league.
DynamiteCop!
Banned
LordKasual
Banned
And most importantly, the switching/shifting/voltage changes are CONSTANTLY happening at the speed of rendering individual frames. It's not as though this needs to be "switched" on and off -- the CPU/GPU is ALWAYS adjusting. So, not only is both CPU/GPU being maxed out constantly very unlikely, but the condition resolves itself immediately.
This is different in situations where i assume one component is likely to always be taxed, at which point that's where the 2% downclocking occurs to allow it to operate at maximum voltage for extended periods of time optimally.
But the point is that it wont be. There will always be breathing points, and as soon as there's a breathing point, the pressure will donate to the most needed component. It's honestly pretty clever.
Sony is targeting a lower overall price point. They chose a design that offers competitive power with what they have without overspending on the parts. No matter what they chose to do, the tradeoff was ALWAYS going to be between power and cost. Sony seems to have decided to focus on sacrificing power and storage space. With that sacrifice, they put that budget into vastly improving its streaming and bandwidth capabilities. They then mitigated the lower-power hardware they had with an architecture that offers efficiency that cuts above what it would generally be capable of, with the variable voltage system.
People can say what they want, but they very clearly put alot of time/R&D into this. The system's prize is clearly its SSD tech, but the rest of the system seems optimized to take advantage of the niche that the PS5 offers. In that sense it is a very well-designed system.
But the proof of this will be what we see from its cooling solution, which is fully dependent on its form factor, which is almost certainly why we haven't seen the console yet.
But if all things come together with a console that can actually be competitive in pricing against the XSX, then PS5 is going to be beastmode.
Last edited:
SonGoku
Member
Yes... capped as i said
Cooling solution. They want to offer a cool and quiet console which is incompatible with their design philosophy of being as cost effective as possible (bare minimum), this can be seen on the PS4 Slim and how tightly packed it is. MS on the other hand goes overboard/overkill with their cooling designs to make sure it runs cool. MS high balls the cooling requirement, Sony low balls. With the fixed power/variable frequency they don't have to guess anymore.
I discussed this before so i'll just quote myself
Last edited:
mckmas8808
Mckmaster uses MasterCard to buy Slave drives
SO you are calling him a liar? And what do you mean a "very low power device"?
sircaw
Banned
Joking aside i really do think Sony's approach is better. I am not a technical person but i can only present what i have read or seen.
Taking Ps5's new audio chip, A direct quote from the digital foundry video by Richard, he says " I am kinda blown away by it" another quote from Richard "This is potentially game changing"
From my understanding what Sony are doing,is making it possible to take advantage of this audio through any type of audio system you have. With processes like mapping to your unique ear and hearing individual droplets of rain around you, this sounds truly breathtaking. Dolby surround is excellent but sony believe they have something better.
So in terms of innovation and Audio, i will take digital foundry expertise on it.
That's point no 1.
No 2
Optimisation and efficiency.
I watched Coretecks video and his analysis about why Nvida were so successful with their memory management accelerator systems. Going by the Nvidia slide that he presented, where memory is expensive and communication is prohibitively expensive it seems Cerny is following the same nvidia road map on that. I will tell you right now, i am not a fan of Nvidia in the way they operate but they do make damn good stuff and more importantly they know what they are doing.
Sony believe that they already have enough power and want to concentrate on making the entire system more optimised in memory efficiency
So in the end i have a choice, believe in what Cerny is saying or call him a liar. I have seen nothing to tell me he is being untruthful
I will be the first to admit that most of this technical talk is well above my pay grade and there are alot of smarter people on this forum, but trying to discuss something or making a point normally ends with someone just shooting me down with some snide one sentence comment or remark.
Point no 3 the ssd.
Xbox ssd is fantastic but Sony's one is better./faster. No matter how people try to spin it, its better. Sony wants to accomplish these things with their ssd. Because they decided not to go as far in power as Xbox, the saving they made they probably poured those cost resources into the ssd.
Sony wants to achieve these things with their ssd.
Boots in a second
No load screens
Ultra high speed streaming
De-duplicate game data
No long patch installs
Is Microsoft trying to accomplish all these things, probably, i just believe Sony is concentrating on them as primary reasons to have an improved ssd.
Point No 4.
The controller. Haptic feedback as Standard. Again Sony is pushing for innovation. We use the controllers so damn much, i like the idea of what they are trying. Its another great innovative feature,
No 5. custom Gpu.
The xbox gpu has 52 cu's at 1.825 Ghz vs the 36 cu's at 2.23 ghz.
If you look at both machines you can clearly see the xbox is superior in a just numbers/power factor. The silver lining for Sony here is not to beat Xbox on power but rather beat them on cost.
Cerny said that they understood the cooling system on the ps4 was not desirable and have made great strides to remedy this.
So if Sony can get the cooling system right, they have an extremely fast chip which is vastly cheaper than the Xbox to produce. The wafer is as far as i know, one off the most expensive parts of a console.
The true reality is Sony want to fight the console war vs Microsoft on Cost. If you can create a cheaper quality product vs a more expensive quality product for the mass market, who do you think are going to win.
So let me try and sum it up as i see it.
Microsoft have built the most powerful machine, it is hard to argue with that.
There Ray tracing capabilities will be better than the Ps5.
Multi-plats should run better on Xbox but its not 720 vs 1080 anymore, diminishing things is a real thing now and i truly believe it will be extremely hard to spot the difference next generation, Yes, God bless digital foundry telling me there is an extra snowflake 500 yards to the right, oh yer, you need to zoom in to see it as well.
Microsoft has also made compromises, if you want to get to around that $500+ price range you need to make sacrifices. You can't have it all.
The console war will be won in some very clear areas, Games/Price .
To end, lets take the new Cyberpunk gaming coming out this year. I would imagine both consoles will run the game at 60 fps 4k. Set up two tvs side by side outside a shopping centre, one for each system and ask the general public to spot the difference. They won't, they can't.
Price, Games-------------everything else.
If you like Microsoft, congrats your getting a system that is top quality, with great parts.
I just feel Sony has thought about the end game a little bit more on optimisation and design.
hyperbertha
Member
Sure buddy memes will make xbox stream 2x faster. If you just don't understand how this works, why waste pointless time debating? Tell me why wouldn't the ps5 have better assets, if you even remotely understand how it works...Oh dear lord....
LordKasual
Banned
Yeah, microsoft abandoning aesthetic form factor entirely for the sake of just making optimal cooling as straightforward as possible is something i'm surprised consoles havent done already.
But i assume it's safe for them to pursue this because they've assured that they have the horsepower advantage this time around. XSX LOOKS like the stronger console.
Ascend
Member
Yeah... I already addressed that;
The PlayStation 5 GPU Will Be Supported By Better Hardware Solutions, In Depth Analysis Suggests
The thing is though even if the 10gb can be accessed @560gb and 224gb/s for the remaining 3.5gb it will still perform better then sonys 13 - 14gb @ 448gb/s. The ram is split, and its the video ram which requires and benifits from higher speeds. Faster XSX's 10gb isn't better than PS5's...
DynamiteCop!
Banned
Yes, I am outwardly calling Mark Cerny a liar, because the how and why is fundamentally obvious as to how one would arrive at a scenario like this. It's the result of pushing the hardware beyond the stated design and as a result concessions must be made. As stated these are relatively low power devices, we're talking sub 300 watts, power conservations is a non-factor.
The only reason this scenario could present itself is due to bottlenecking at the bus, or a voltage limitation related to thermal output and system instability. A bottleneck at the bus would require them to offset compute from the CPU and GPU i.e. require them to be varied and shift function as necessary because data flow saturation would bottleneck it otherwise.
The other reason is seeing as this is an APU they share a die, the amount of heat generated relative to voltage especially to maintain that 2.23Ghz would simply be too high, so either the voltage is limited from the CPU and frequency is lowered, or its limited on the GPU and its frequency is lowered.
No one would design a system of this nature intentionally unless otherwise forced to. If they could maintain both figures indefinitely they would, but the design of the system does not allow it because it was never intended to operate at this voltage and frequency; introduce the shift.
The PlayStation 5 was without any shadow of a doubt a 3.5Ghz and 9.X teraflop fixed frequency system. Its voltage was mated properly and thermals were regulated to handle those figures. At some point far in the development of the system Sony clearly got wind of Microsoft's system capability and being too far along in their design to rework it, they had to manipulate it. They had to implement broader cooling, higher voltages, implement a set of functions which allowed the GPU to push harder at the cost of CPU cycles, allowed the CPU to push harder at the cost of GPU cycles. Both cannot be true at the same time, one has to give for the other to excel.
Again, no one would intentionally design a system in this capacity because there's no advantage to it. It's nonsensical design, there's no leg up over fixed operation. If the system was locked at 2.23Ghz and 3.5Ghz it would be better. However given the above they cannot do that, because the system was never designed to operate at those heights. This is a through and through reworking to try and close a very large divide with their competitor, not intelligent or originally planned system operation.
Last edited:
Bumblebeetuna
Member
Oh it’s you again. Hi friend. I’m still waiting for you to produce that quote where I said TF are all that matters. Please address that before you get emotional about any other post of mine, thanks.
LordKasual
Banned
The differences between PS5 and XSX are honestly fascinating because Sony's focus on "gameplay enhancing features" seems to mimic what nintendo CLAIMED they were trying to do for so many years, but it's obvious now that they never cared about.
In PS5's case, the power sacrifices here actually seem to come with tangible benefits, while (most importantly) staying competitive as far as the power gap goes. You'd expect these sacrifices to result in a PS4 vs. Xbone level of discrepancy but it's nowhere close, and that's honestly kind of amazing if they can lock down a lower pricepoint.
Yeah... I already addressed that;
The PlayStation 5 GPU Will Be Supported By Better Hardware Solutions, In Depth Analysis Suggests
The thing is though even if the 10gb can be accessed @560gb and 224gb/s for the remaining 3.5gb it will still perform better then sonys 13 - 14gb @ 448gb/s. The ram is split, and its the video ram which requires and benifits from higher speeds. Faster XSX's 10gb isn't better than PS5's...www.neogaf.com
Yes, we already knew this, its 10gbs are faster only when memory isn't at capacity, and the architecture is at a disadvantage when all of it is being used.
PS5 doesn't suffer this issue -- they linearly attacked memory bandwidth on the PS5 the same way XSX linearly attacked horsepower. Probably because the design was always intended to leverage the low latency caching, so it's always consistent. And again, if the system really can refresh ALL 16 GB of its ram in a single second, it has the ability to always use all of its RAM.
i've already said, i fully expect the XSX to use the higher bandwidth 10Gb for games, but that doesn't change the fact that the interlacing is going to be less efficient with the asymmetry that microsoft opted to aim for.
It was a compromise.
It really doesn't matter how many clear and quantifiable benefits we explain to you, does it?
You're just gonna keep spouting this ignorant shit? Why are you even here?
Last edited:
DynamiteCop!
Banned
This is armchair hypothesis, not any kind of factual reality.
DynamiteCop!
Banned
I'm not going to give you any kind of real response if you can't be bothered to yourself. Don't cherry pick and expect anything in return.
LordKasual
Banned
Uh, how so? And what part?
"Cherry pick" WHAT? You're literally dismissing what you're asking us to give you, then saying we aren't giving it to you.
The fuck is wrong with you?
We're trying to have a genuine hardware conversation and have to constantly step around idiots who dont wan't to research anything, but are determined to assert they know what the fuck they're talking about.
none of us are experts and nobody has all the facts, but this conspiracy theory shit is completely useless.
Last edited:
DynamiteCop!
Banned
The entire scenario is hypothesized, there's no intrinsic knowledge that all of the RAMDAC's cannot operate at full bandwidth simultaneously. No one actually knows enough about the system design to make that kind of assertion.
While it makes for interesting discussion there's very little logical basis with so little information.
The Pleasure
Gold Member
The PlayStation 5 will feature a weaker GPU, compared to the Xbox Series X, but developers continue to praise the console. The raw specs are definitely not painting the whole picture about the new consoles, and a recent in-depth analysis suggests that the Sony next-gen console's GPU will have a better system supporting it, resulting in better overall performance.
On his blog, James Prendergast has been providing a very interesting on-going analysis of the next-generation consoles, based on what has been revealed so far. In his latest post, he took a look at how RAM, I/O and SSD speed and function will make a difference, considering the CPU difference between the two consoles is minimal.
Taking a look at the RAM configuration of both consoles, the analysis highlights how the Xbox Series X configuration is sub-optimal, as the asymmetric configuration used for the console can lead to reduced bandwidth once the symmetrical portion is full. The PlayStation 5 configuration, on the other hand, allows a static bandwidth for the entire 16 GB of GDDR6.
Taking a look at the I/0 and SSD access, the analysis highlights how the Xbox Series X simply has a slower interface over the PlayStation 5's. The solution used by the Sony console allows for better data management within the RAM as well, allowing for less frequent reloading of data into the RAM, improving system efficiency.
Putting everything together, including how the PlayStation 5 audio hardware will take less CPU power compared to the Xbox Series X, the analysis reveals that the PlayStation 5 has the "bandwidth and I/O silicon in place to optimise the data transfer between all the various computing and storage elements". The Xbox Series X, on the other hand, has some sub-optimal implementations that are going to perform below the specs of the PlayStation 5, despite the inclusion of smart prediction engines.
On a related note, a video released recently by Coreteks, who claims to have insider knowledge on both consoles, reaches the same conclusions. It is a very long video, but it's a very interesting watch nonetheless.
The PlayStation 5 GPU Will Be Supported By Better Hardware Solutions, In Depth Analysis Suggests
According to a recent in-depth analisys, the PlayStation 5 may have the weaker GPU of the next-gen consoles, but it will receive better support from the rest of the systemwccftech.com
-------------------------------------------------------------------------
We've been hearing for months that there's not much between the two devices from Microsoft and SONY, with "sources" on both sides of the argument claiming that each console has an advantage in specific scenarios. Incontrovertibly, Microsoft has the more performant graphics capabilites with 1.4x the physical makeup of the Playstation 5's GPU core. That's only part of the story though, with the PS5 running a minimum 1.2x faster than the Series X across the majority of workload scenarios. That narrows the advantage of the SX (in terms of pure, averaged, GPU compute power) to around 1.18x-1.2x that of the PS5.
But what about the CPU? Performing the same, simple ratio calculation, you can work out that the SX is 1.02x - 1.10x more powerful than the PS5's, depending on the scenario. Not that big a difference, really... and the CPU/GPU should sport pretty much the same feature set on both consoles.
However, everyone and their dog are talking about the GPUs and have been for a long time: It's not all that interesting to me at this point in time until more of their underlying architectures are revealed. Those three to four* things that are more interesting to me are:
- RAM
- I/O
- SSD speed and function
- Audio hardware
Unfortunately, we don't have the full information on the SX's audio hardware implementation, meaning we can't yet do a proper comparison between the two consoles for that. So let's begin with the RAM configuration.
RAM
Let me put this bluntly - the memory configuration on the Series X is sub-optimal.
I understand there are rumours that the SX had 24 GB or 20 GB at some point early in its design process but the credible leaks have always pointed to 16 GB which means that, if this was the case, it was very early on in the development of the console. So what are we (and developers) stuck with? 16 GB of GDDR6 @ 14 GHz connected to a 320-bit bus (that's 5 x 64-bit memory controllers).
Microsoft is touting the 10 GB @ 560 GB/s and 6 GB @ 336 GB/s asymmetric configuration as a bonus but it's sort-of not. We've had this specific situation at least once before in the form of the NVidia GTX 650 Ti and a similar situation in the form of the 660 Ti. Both of those cards suffered from an asymmetrical configuration, affecting memory once the "symmetrical" portion of the interface was "full".
Interleaved memory configurations for the SX's asymmetric memory configuration, an averaged value and the PS5's symmetric memory configuration... You can see that, overall, the PS5 has the edge in pure, consistent throughput...
Now, you may be asking what I mean by "full". Well, it comes down to two things: first is that, unlike some commentators might believe, the maximum bandwidth of the interface is limited to the 320-bit controllers and the matching 10 chips x 32 bit/pin x 14 GHz/Gbps interface of the GDDR6 memory.
That means that the maximum theoretical bandwidth is 560 GB/s, not 896 GB/s (560 + 336). Secondly, memory has to be interleaved in order to function on a given clock timing to improve the parallelism of the configuration. Interleaving is why you don't get a single 16 GB RAM chip, instead we get multiple 1 GB or 2 GB chips because it's vastly more efficient. HBM is a different story because the dies are parallel with multiple channels per pin and multiple frequencies are possible to be run across each chip in a stack, unlike DDR/GDDR which has to have all chips run at the same frequency.
However, what this means is that you need to have address space symmetry in order have interleaving of the RAM, i.e. you need to have all your chips presenting the same "capacity" of memory in order for it to work. Looking at the diagram above, you can see the SX's configuration, the first 1 GB of each RAM chip is interleaved across the entire 320-bit memory interface, giving rise to 10 GB operating with a bandwidth of 560 GB/s but what about the other 6 GB of RAM?
Those two banks of three chips either side of the processor house 2 GB per chip. How does that extra 1 GB get accessed? It can't be accessed at the same time as the first 1 GB because the memory interface is saturated. What happens, instead, is that the memory controller must instead "switch" to the interleaved addressable space covered by those 6x 1 GB portions. This means that, for the 6 GB "slower" memory (in reality, it's not slower but less wide) the memory interface must address that on a separate clock cycle if it wants to be accessed at the full width of the available bus.
The fallout of this can be quite complicated depending on how Microsoft have worked out their memory bus architecture. It could be a complete "switch" whereby on one clock cycle the memory interface uses the interleaved 10 GB portion and on the following clock cycle it accesses the 6 GB portion. This implementation would have the effect of averaging the effective bandwidth for all the memory. If you average this access, you get 392 GB/s for the 10 GB portion and 168 GB/s for the 6 GB portion for a given time frame but individual cycles would be counted at their full bandwidth.
However, there is another scenario with memory being assigned to each portion based on availability. In this configuration, the memory bandwidth (and access) is dependent on how much RAM is in use. Below 10 GB, the RAM will always operate at 560 GB/s. Above 10 GB utilisation, the memory interface must start switching or splitting the access to the memory portions. I don't know if it's technically possible to actually access two different interleaved portions of memory simultaneously by using the two 16-bit channels of the GDDR6 chip but if it were (and the standard appears to allow for it), you'd end up with the same memory bandwidths as the "averaged" scenario mentioned above.
If Microsoft were able to simultaneously access and decouple individual chips from the interleaved portions of memory through their memory controller then you could theoretically push the access to an asymmetric balance, being able to switch between a pure 560 GB/s for 10 GB RAM and a mixed 224 GB/s from 4 GB of that same portion and the full 336 GB/s of the 6 GB portion (also pictured above). This seems unlikely to my understanding of how things work and undesirable from a technical standpoint in terms of game memory access and also architecture design.
In comparison, the PS5 has a static 448 GB/s bandwidth for the entire 16 GB of GDDR6 (also operating at 14 GHz, across a 256-bit interface). Yes, the SX has 2.5 GB reserved for system functions and we don't know how much the PS5 reserves for that similar functionality but it doesn't matter - the Xbox SX either has only 7.5 GB of interleaved memory operating at 560 GB/s for game utilisation before it has to start "lowering" the effective bandwidth of the memory below that of the PS5... or the SX has an averaged mixed memory bandwidth that is always below that of the baseline PS4. Either option puts the SX at a disadvantage to the PS5 for more memory intensive games and the latter puts it at a disadvantage all of the time.
The Xbox's custom SSD hasn't been entirely clarified yet but the majority of devices on the market for PCIe 4.0 operate on an 8 channel interface...
I/O and Storage
Moving onto the I/O and SSD access, we're faced with a similar scenario - though Microsoft have done nothing sub-optimal here, they just have a slower interface.
14 GHz GDDR6 RAM operates at around 1.75 GB/s per pin, per chip (14 Gbps [32 data pins per chip x 10 chips gives total potential bandwidth of 560 GB/s - matching the 320-bit interface]). Originally, I was concerned that would be too close to the total bandwidth of the SSD but Microsoft have upgraded to a 2.4/4.8 GB/s read interface with their SSD which is, in theory, enough to utilise the equivalent of 1.7% of 5 GDDR6 chips uploading the decompressed data in parallel each second, leaving a lot of overhead for further operations on those chips and the remaining 6 chips free for completely separate operations. (4.8 GB/5 (1 GB) chips /1.75x32 GB/s)
In comparison, SONY can utilise the equivalent of 3.2% of the bandwidth of 6 GDDR6 chips, in parallel, per second (9 GB/5 (2 GB) chips /(1.75x32 GB/s)) due to the combination of a unified interleaved address space and unified larger RAM capacity (i.e. all the chips are 2 GB in capacity so, unlike the SX, the interface does not need to use more chips [or portion of their total bandwidth] to store the same amount of data).
Turning this around to the unified pool of memory, the SX can utilise 0.86% of the total pin bandwidth whereas the PS5 can use 2.01% of the total pin bandwidth, all of this puts the SX at just under half the theoretical performance (ratio of 0.42) of the PS5 for moving things from the system storage.
Unfortunately, we don't know the random read IOPS for either console as this number will more accurately reflect the real world performance of the drives but going on the above figures this means is that the SX can fill the RAM with raw data (2.4 GB/s) in 6.67 seconds whereas the PS5 can fill the RAM (5.5 GB/s) in 2.9 seconds, again, 2.3x the rate of the SX (this is just literally the inverse ratio of the above comparison with the decompressed data).
However, that's not the entire story. We also have to look at the custom I/O solutions and other technology that both console makers have placed on-die in order to overcome many potential bottlenecks and limitations:
The decompression capabilities and I/O management of both consoles are very impressive, but again, SONY edges out Microsoft with the equivalent of 10-11 Zen 2 CPU cores to 5 cores in pure decompression power. This optimisation on SONY's part really lifts all of the pressure off of the CPU, allowing it to be almost entirely focussed on the game programme and OS functions. That means that the PS5 can move up to 5.5 GB/s compressed data from the SSD and the decompression chip can decompress up to 22 GB/s from that 5.5 GB compressed data, depending on the compressibility of that underlying raw data (with 9 GB as a lower bound figure).
Data fill rates for the entire memory configuration of each console; the PS5 unsurprisingly outperforms the SX... *I used the "bonus" 20% figure for the SX's BCPack compression algorithm.
Meanwhile, the SX can move up to 4.8 GB/s of compressed data from the SSD and the decompression chip can decompress up to 6 GB/s of compressed data. However, Microsoft also have a specific decompression algorithm for texture data* called BCPack (an evolution of BCn formats) which can potentially add another 20% compression on top of that achieved by the PS5's Kraken algorithm (which this engineer estimates at a 20-30% compression factor). However, that's not an apples-to-apples comparison because this in on uncompressed data, whereas the PS5 should be using a form of RDO which the same specialist reckons will bridge the gap in compression of texture data when combined with Kraken. So, in the name of fairness and lack of information, I'm going to leave only the confirmed stats from the hardware manufacturers and not speculate about further potential compression advantages.
While the SFS won't help with data loading from the SSD, it will help with data management within the RAM, potentially allowing for less frequent re-loading of data into RAM - which will improve the efficiency of the system, overall - something which is impossible to even measure at this point in time - especially because the PS5 will also have systems in place to manage data more intelligently.
This capability, combined with the consistent access to the entirety of the system memory, enables the PS5 to have more detailed level design in the form of geometry, models and meshes. It's been said by Alexander Battaglia that this increased speed won't lead to more detailed open worlds because most open worlds are based on variation achieved through procedural methods. However, in my opinion, this isn't entirely true or accurate.
The majority of open world games utilise procedural content on top of static geometry and meshes. Think of Assassin's Creed Odyssey/Origins, Batman Arkham City/Origins/Knight, Red Dead Redemption 2, GTA 5 or Subnautica. All of them open worlds, all of their "variations" are small aspects drawn from a standard pre-made piece of art - whether that's just a palette swap or model compositing. The only open world game that is heavily procedurally generated that I can think of is No Man's Sky. Even games such as Factorio or Satisfactory do not go the route of No Man's Sky...
In the majority of games, procedural generation is still a vast minority of the content generation. Texture and geometry draws are the vast majority of data required from the disk. Even in games such as No Man's Sky, there are meshes that are composited or even just entirely draw from disk.
The Series X's SSD actually looks like it can be replaced... although you'd have to disassemble the entire console to be able to do so...
Looking at the performance of the two consoles on last-gen games, you'll see that it takes 830 milliseconds on PS5 compared to 8,100 milliseconds on PS4 Pro for Spiderman to load whereas it takes State of Decay 2 an average of 9775 milliseconds to load on the SX compared to 45,250 milliseconds on One X. (Videos here) That's an improvement of 9.76x on the PS5 and 4.62x on the SX... and that's for last gen games which don't even fill up as much RAM as I would expect for next generation titles.
Here I attempted to estimate the RAM usage of each game based on the time it took to swap out RAM contents and thus game session. We can see that State of Decay 2 has some overhead issues - perhaps it's not entirely optimised for this scenario... this is a simple model and not accurate to actual system RAM contents since I'm just dividing by 2 but it gives us a look at potential bottlenecks in the I/O system of the SX.
Now, this really isn't a fair test and isn't necessarily a "true" indication of either console's performance but these are the examples that both companies are putting out there for us to consume and understand. Why is it perhaps not a true indication of their performance? Well, combining the numbers above for the SSD performance you would get either (2.4 GB/s) x 9.78 secs = 23.4 GB of raw data or (4.8 GB/s) x 9.78 secs = 46.9 GB of compressed data... which are both impossible. State of Decay 2 does not (and cannot) ship that much data into memory for the game to load. Not to mention that swapping games on the SX takes approximately the same amount of time... Therefore, it's only logical to assume there are some inherent load buffers in the game that delay or prolong the loading times which do not port over well to the next generation.
In comparison, the Spiderman demo is either (5.5 GB/s) x 0.83 secs = 4.6 GB or (9 GB/s) x 0.83 secs = 7.47 GB, both of which are plausible. However, since I don't know the real memory footprint of Spiderman I don't know which number is accurate.
This is a really interesting implementation of using a power envelope to determine the activity across the die...
Audio Hardware
In my opinion, the "pixel" is well and truly dead. The majority of PC players in the world play at the 1080p resolution. The majority of TVs in peoples' houses are 720-1080p. 4K is a vast minority - yes, of course it's gaining ground as people replace their screens but the point is that most people are happy with their current setup and don't see the added bonus of upgrading the resolution or size of the screen setup unnecessarily.
Unfortunately, Microsoft have pushed their audio features much less than SONY have - I presume because it was not a huge focus of the console, instead they decided to focus on raytracing, graphics throughput, variable refresh rate, auto low latency mode and HDR. If you're not going to use the added rasterisation power through targetting a higher resolution, instead opting for optimisations that allow you to render at lower resolutions and scale up, why bother modelling the console around that processing power in the first place?
In comparison, SONY hasn't even name-checked HDR output like Microsoft have with 3D audio.
What we do know about the SX's audio solution is that it is a custom audio hardware block which will output compatible signals in Dolby Atmos, DTS:X and Windows Sonic codecs. This hardware will handle wave propagation and diffraction but has not officially (as far as I can find) linked this with the ray tracing engine on the GPU.
SONY, on the other hand, have gone all-in on their audio implementation. I had speculated previously that the audio solution might be based on AMD's TrueAudioNext and their GPU CU cores. Thinking that, I had presumed that the console designers would provide a subset of of their total CU count on the GPU for this function. Instead, SONY have actually modified the CU units from AMD's design to make them more like the SPUs in the PS3's Cell architecture (no SRAM cache, direct data access from the DMA controller through the CPU/GPU and back out again to the system memory). We don't know how many altered CUs are present in this Tempest engine but SONY have said that the SIMD computational power is equivalent to the entire 8 core Jaguar CPU that was in the PS4.
Essentially, SONY decided to reduce the amount of fully fledged CUs available to the GPU in order to provide this audio solution. This also means that the PS5's sound processing will take less CPU power from the system compared to the SX - which, again, counts against the SX in terms of resources available to run games.
I guess that I'll have more on this as the features are fully revealed.
SONY's implementation of RT is able to be spread across many different systems...
Conclusion
The numbers are clear - the PS5 has the bandwidth and I/O silicon in place to optimise the data transfer between all the various computing and storage elements whereas the SX has some sub-optimal implementations combined with really smart prediction engines but these, according to what has been announced by Microsoft, perform below the specs of the PS5. Sure, the GPU might be much larger in the SX but the system itself can't supply as much data for that computation to take place.
Yes, the PS5 has a narrower GPU but the system supporting that GPU is much stronger and more in-line with what the GPU is expecting to be handed to it.
Added to this, the audio solution in the PS5 also alleviates processing overhead from the CPU, allowing it to focus on the game executable. I'm sure the SX has ways of offloading audio processing to its own custom hardware but I seriously doubt that it has a) the same latency as this solution, b) equal capabilities or c) the ability to be altered through code updates afterwards.
In contrast, the SX has the bigger and wider GPU but, given all the technical solutions that are being implemented to render games at lower than the final output resolution and have them look as good, does pushing more pixels really matter?
Analyse This: The Next Gen Consoles (Part 9) [UPDATED]
So, the Xbox Series X is mostly unveiled at this point, with only some questions regarding audio implementation and underlying graphics...hole-in-my-head.blogspot.com
Jeff Rigby is that you?
DynamiteCop!
Banned
It's really simple, and I'll make it simple for you.
What system is more computationally performative with voltage/thermal/instability, and bus limitations removed from the equation?
System #1: 3.5Ghz CPU with SMT (fixed), 2.23 GHZ GPU (fixed)
System #2: 3.5Ghz CPU with SMT (variable), 2.23 GHZ GPU (variable)
Ascend
Member
Actually no. That is not what I stated nor what the truth is.
First of all, we know nothing of how much RAM the PS5 OS will be using. That will definitely be cutting into the bandwidth for games on the PS5 as well. Or does the OS somehow magically exist somewhere outside of the RAM bandwidth? The XSX has the luxury of running it on slower bandwidth. The PS5 doesn't. I will simply quote what I stated earlier. Anyone is free to refute it.
[MS] could spread that 2.5GB [of OS usage] across all six of the 2GB RAM chips. How much would that really reduce the bandwidth for games? That is around 417MB per RAM chip. If you assume the OS is constantly consuming its max RAM bandwidth capacity (which is highly unlikely), that would mean that each RAM chip would use 11.7 GB/s of the total 56GB/s bandwidth, for a total reduction of 70 GB/s. That means you would end up with 490 GB/s for the games in this case for the 10GB.
In such a case, the XSX is still faster. There are too many variables. But the bottom line is that there are multiple ways developers can still leverage the XSX to hold the advantage with its RAM. The only real way it will perform slower is if they completely botch the coding.
NeoGiffer
Member
bitbydeath
Gold Member
You didn’t say anything new above that I already stated previously.
What you’re not understanding is that these bottlenecks have impacts on other hardware components. Just because the CPU is a bottleneck it doesn’t mean only CPU functions are limited. Eg. A CPU bottleneck can impact the resolution output.
I believe ‘the magic’ is all about the custom hardware and the ability to push the max theoretical data which in turn makes things instantly read.
No, as Mark Cerny said the SSD (speed) was only one factor to resolving all bottlenecks.
S0ULZB0URNE
Member
The 10% is the power draw which = a couple % drop in performance.
2230 -2%=2185.4GHZ
Definition of A COUPLE
two or a few (of something) —In informal U.S. English, a couple can be used like a couple of; two or a few… See the full definition
www.merriam-webster.com
S0ULZB0URNE
Member
He said a couple.
Rolling_Start
Banned
The weird thing is that MS have already described how it works.
It does leave something to be discovered - actual performance in real game circumstances - but they already described how it works. They've even shown the fucking board and how different sized chips map to the bus. And it's perfectly reasonable and logical.
Yet you get the miserable nonsense quoted in the OP as being "in depth analysis" using entirely fanfiction description of how memory buses access memory chips.
You can't "resolve" all bottlenecks. There are many factors in a bottleneck, and it shifts depending upon workload. Different workloads create different bottlenecks in different hardware in different conditions.
Dammit, the world isn't one dimensional.
JLB
Banned
I can cherry pick quotes and opinions to make Xbox Series X look the way I prefer. I mean, Digital Foundry itself said that the Series X design is revolutionary, just two days ago.
Every single generation is kind of the same story, anyways. But the cold facts are clear and straitforward, as they were on 2013. And data is clear to point which console is more powerful.
Thats not the end of the world, anyways. PS2 was much less powerful that OG Xbox, like orders of magnitude, and it was the most succesful console in history. Wii case is similar. Let alone Switch.
Will just pick one of your quotes:
"To end, lets take the new Cyberpunk gaming coming out this year. I would imagine both consoles will run the game at 60 fps 4k. Set up two tvs side by side outside a shopping centre, one for each system and ask the general public to spot the difference. They won't, they can't."
That was not the case when comparing a 900p Xbox One version vs ps4 1080p.
In any case, we will need to wait and see. IMO, the most distinctive visual feature of next gen will be ray tracing, and by a wide margin. And its a given that Series X RT will be much better than PS5 since it has more CUs. And I believe it will be noticeable for the general public, but I guess we need to wait and see.
Shin
Banned
I know what the definition of a couple means, can't say the same about others though.
Case in point, if it was a couple as some of you assume, two would have been used and not a couple.
Except it wasn't therefor a couple can be anything, don't know how else to explain it to you (I shouldn't have to to begin with).
Last edited:
mckmas8808
Mckmaster uses MasterCard to buy Slave drives
You made it clear that you believe the XSX is better than the PS5 in all types of ways with the post you made. Don't run from it now.
Rolling_Start
Banned
No, he did not. He gave an example of a couple saving 10%.
He at no point said that frequency variation would be limited to 2%.
For variation to be that small he would have to have been lying about building around stable power consumption and not fixed frequency.
And he was not lying. Cerny has never lied about this shit to the best of my knowledge. He is a good guy.
So stop. He never said frequnecy variation would be limited to 2%. This was never said. Ever. By Cerny.
Nero_PR
Banned
I'll be honest, I didn't read 20% of the thread. I'm here just to see the desperate Xbox suckers and Sony defenders arguing. I actually find it interesting how Sony is trying to make up for the lack of more powerful hardware brute force wise with innovative thinking of how to get rid of the bottlenecks of communication between SSD, GPU, CPU, data flow, and many other aspects. I will give it a read after, but I'm actually cautiously optimistic how much impact their aim on optimization will have in real world performance, and how all of this will change game development time for the studios that embrace the technology.
Rolling_Start
Banned
I watched the GDC conference (twice) and Sony's SSD is fantastic.
As for the rest of the innovative bottleneck reduction relative to other systems, could you explain it to us? Given that you're so interested in it and all??
DynamiteCop!
Banned
That comparison with the Nintendo 64 is actually an excellent example of this SSD nonsense evaporating into thin air. It didn't matter how fast the Nintendo 64 could stream in data, the games still by and large ran at 20 FPS because the CPU and GPU were not up to snuff.
Great post.
Last edited:
Shin
Banned
Their idea isn't bad, 2 days ago I did a quick search to check what a really high GPU OC is (3084MHz) and that was on 16nm.
2.23GHz for the GPU on 7nm is rather realistic all things considered and not necessarily a "burn the house down scenario".
I don't think anyone have much time left to unfold all the little details about their consoles, that window is practically closing.
bitbydeath
Gold Member
Yet Mark Cerny claims to have and he addresses a few of the different types in the road to PS5 video.
JareBear: Remastered
Banned
Holy fuck that seems like a crazy bough GPU clock. 3ghz? What card pulls that off?
Bumblebeetuna
Member
Another swing and a miss, friend. How is this related to me thinking only TF matters? Are you implying the only thing impressive about the XSX is the TF number? You realize it’s an impressive piece of hardware, yes? You can squirm and grasp at straws all you want, bottom line is you caught feelings over a video game forum post and pulled some stuff out of your ass.
Rolling_Start
Banned
Yes, he looked for current and anticipated bottlenecks in various parts of the machines subsystems. But he didn't say he had "resolved all bottlenecks".
Making the claim that he did, and that the PS5 is "bottleneck free" is asinine.
DynamiteCop!
Banned
If anyone is reaching 3Ghz on a GPU they are doing it with liquid nitrogen or liquid helium and extensive voltage modifications.
2.23Ghz on air is insanely high.
Shin
Banned
GTX 1080Ti, nitrogen and all obviously but it goes to show how fast things move (PS5's GPU speed is a testament to that).
Last edited:
bitbydeath
Gold Member
Rolling_Start
Banned
And you don't think MS's years of profiling console games, and AMD's DECADES of TRYING TO BUILD CPUs AND GRAPHICS CARDS doesn't involve trying to prevent common and avoidable bottlenecks?
You don't think this is part of trying to build any system?
Are you special??
And who amongst them has ever claimed to have "resolved" *all* bottlenecks??
You don't think everyone throws engineering resources at this?
Last edited:
S0ULZB0URNE
Member
We can tell who actually listened to what he said and who didn't.
Similar threads
- Locked
- Poll