By using this site, you agree to our Privacy Policy and our Terms of Use. Close
JRPGfan said:

1) "They are patents. They aren't actual products. " - Permalite

I know that, but this appears to for the PS5, and will likely be for a real product.

Sony has a patent for cartridges. Didn't mean the Playstation 5 will be using carts.

And how do you know it will be for the Playstation 5? Gut feeling? Need more than that to assert that something is true I am afraid.

JRPGfan said:

2)  "Variable clockrates that aren't developer controlled/influenced isn't a good thing..."

Theres nothing that isnt good for something.  This is fantastic for reduceing overhead, and increaseing power effeciency.
Thats why you see it on the PC, mobil, laptop, smartphone side.  Which in turn could mean you get a small chip to run faster, and waste less power.

Is it fantastic for the developer? maybe not, but overall I'd say its a good thing (for the hardware).

It doesn't reduce overhead. (Whatever that is supposed to mean?)

PC and mobile uses it because not all components are taxed at 100%, thus there is headroom to drive up clockrates or reduce power consumption and thus heat.

Consoles are innately different in that regard where we can assume that the developer will be using every component to it's maximum potential in order to drive overall simulation quality.

JRPGfan said:

3) "We have been stacking NAND chips for years."

That form of stacking is differnt than this one right? Those are layers, to reduce the size of it
(if your layout was side by side, the SSD would be thin as a sheet of paper but gigantic):
They dont really take any advantage of the fact that they are ontop of one another (afaik).

It's still stacking, it's just a variant of it.
I also mentioned HBM which stacks memory on top of a Silicon Interposer and logic.

It's nothing new, Sony didn't go out and invent the wheel again.

And you are correct, that if an SSD had all it's NAND laid out in a planar form factor the size would be massive, hence the need for stacking, there isn't the same need for stacked processors, otherwise AMD would have done the same with it's chiplets.

JRPGfan said:

4)  "Controller is just an evolution of past designs, it's different, but it's not going to be playing games any differently,..... ."

"Wired were also given the opportunity to play a version of Gran Turismo Sport on the PS5 dev-kit, which allowed them to experience the improved haptic feedback, which they described as "Driving on the border between the track and the dirt, I could feel both surfaces."

This sensation, Wired explains, "disappeared entirely" when they replayed the same track using the DualShock 4, which emphasises exactly how much the haptic feedback has been improved in the DualSense." - Wired

Theres been other journalist and tech guys, that have tried it, and says it plays very differntly than the past controllers.

It's still a controller that is based on past controller designs, it's nothing new, novel or different.

It still uses the same button layout, it still uses two analogue sticks, still uses a D-Pad, it even copied the ergonomics from Microsoft. - It has a few extra features bolted-on in a new shell, it's NOT a new or revolutionary change in how you play games with a controller, it's an evolution of past designs... Let's not try and frame it as anything else other than that... Otherwise that is just being disingenuous.

JRPGfan said:

5)  "Please elaborate on those bottlenecks."

They have a custom memory controller, that allows for upto six levels of priority when reading from the SSD (when normally its ~2).

example:  "While textures are being loaded, an enemy might be shot and have to saying some dying words. That interrupts the texture loading."

On sony's SSD that npc that dies, and says some words, wont effect loading speeds of other things needed to be loaded.
While on Xbox it probably does.  Will this actually be something noticeable ingame? Who knows.

Watch from 12m onwards.

Check-in (copying data from one place to another) takes roughly 1 next gen CPU core. And thats just the tip of the iceberg, if all the overheads get 100 times larger, that will cripple the player as soon as that massive stream of data comes off the ssd.

It is all well and good to parrot information you heard elsewhere... But you didn't really elaborate on what those actual bottlenecks are.

Because the Xbox Series X and PC also removes those "bottlenecks" by moving to an SSD from a mechanical disk and it doesn't use that priority level system.

Is the only bottleneck the storage? What about the rest of the system?
I am not asking these questions because I don't know, I am asking these questions to see if you know and actually understand them.

JRPGfan said:

1) Custom flash controller (to handle that) and custum units inside the APU.

2) Kracken (compression)  (turns those 5,5GBS (raw) -> 8/9 GBS (typical) and can go upto 22GB/s (max theoretical))
(in terms of cpu performance (for compression), this kracken chip is like 9 cpu cores, in the PS5)

3) Dedicated DMA controller (which again is like 1 cpu core worth saved)

4) I/O Co-proccessors that direct the custom hardware parts (again offloading the cpu)
(1 of them, is for SSD IO, lets sony by-pass traditional file IO, as it bottlenecks when reading ssd)
(1 of them, is for memory mapping, mapping and remapping as part of file IO, and this too as a bottleneck)

5) Coherancy engines (to assist the co-proccessors, mainly data in the gpu caches, flushing gpu cashe when ssd is read, is a "unattractive option" and can really hurt the GPUs performance, so sony implimented a "gentle" way of doing things, were coherancy engines talk to the gpu and inform it of overhead ranges and scrubbers... bla bla bla)

honestly just go watch Mark Cerny again, he talks about these bottlenecks and how they delt with them in the video.

Points, 1, 2 and 3 all relate to the same thing.

What are those custom units you speak of?

What Kraken chip? You aren't confusing things are you? Because the Kraken decompressor isn't actually a chip, it's a fixed function unit on the APU.

DMA controller isn't anything new.

I/O Co-Processors isn't anything new.

Coherancy engines? Again, nothing new. Playstation 4 gamers talked up coherency last generation... Still waiting to see the results.

And I don't want to re-watch Cerny's video, I know exactly what he is talking about, I am trying to see what your perception of his technical explanations are.

JRPGfan said:

6) "Seems? Elegant solutions? We haven't even seen the console yet!
It's all well and good to use buzzwords to hype something up, but don't use them before we have even seen the hardware."

Fair enough, so far its just a patent that points out how the PS5 APU might be cooled, and that its useing 3D stacking.
Its not a actual product yet.

"might" being the key operative word.

JRPGfan said:

7) "Chip stacking has a ton of caveats... And like you alluded to, cooling is a big one... Implementing an additional cooling layer between stacked chips increases complexity and reduces yields and is entirely unnecessary in scenarios where you have enough space (I.E. PC and Console) when you can simply go the chiplet route and interface those chips with a larger and more efficient surface area to draw heat from. - Basic thermodynamics comes into play."

Yes you have more heat, in a smaller area, makeing cooling abit harder.
The upside is ; its more power-effecient (which means less heat overall) and has lower latency when moveing data between parts.

The idea that they just cool the 3D chip from both sides, kinda off-sets that draw back though right?
You just doubled the area were heat can disspate from.

Also this isnt a "additional cooling layer between stacked chips"
The ilusstration shows that its cooled from the front of the chip, and the back side of the chip.
Theres no cooling "inside" the layers of the chip or such as you worded it.

How is it more power efficient? And how would it effect latency? And how does any of that even matter?

--::{PC Gaming Master Race}::--