• 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.

Performance Test(GigaPixels/s): PS5 outperforms RTX 2080 by a wide margin under heavy load

Agnostic2020

Agnostic2020

Member
Bernd Lauert said:
Enjoy your frame tearing I guess.
Click to expand...
I dont think he has xsx ? 😅


fwE5a40.jpg
 
Last edited:
FIREKNIGHT2029

FIREKNIGHT2029

Member
Personally I'm really happy the PS5 offers good bang for buck. I still remember when some people were expecting the PS5 to be a souped up PS4 Pro.

Obviously i don't expect it to perform anywhere near as good as the top level PC cards but it's offering really good mid-range performance for $400 and that's better than all of use were expecting months ago.
 
Bernd Lauert

Bernd Lauert

Banned
Agnostic2020 said:
Keep lying to yourself .all the analysis suggests otherwise. If u bought a 2000$ TV to fix it that's on you 😅. Give up the denial stage of grief and move to the next one. Soon bud you will get to acceptance haha. Cheers
Click to expand...

My TV was €995. If you're playing on a shitty $400 TV, all those gigapixels per second look like shit anyway.

And the analysis suggests that there is zero tearing on XSX and XSS. Just get a half decent TV, bud.
 
VFXVeteran

VFXVeteran

Banned
Stilton Disco said:
The fact the PS5 is able to do any kind of graphical rendering at 4K better than a bloody 2080 is damned impressive.

It does however give an idea, when comparing console apples to PC oranges as to where the PS5's strengths lie, with the most likely real world benefit being with texture streaming and fillrate, two things we're already seeing evidence of with the unexpected results in comparisons between PS5 and XSX.

Dismissing these kind of benchmark tests out of hand is dumb and shortsighted. This relative speed and ability is being used in PS5 game development, even if it's not for this purpose, and seeing what a really good PC component is capable of in comparison adds real world context to that, even if we don't know what it's actually being used for.
Click to expand...

Fillrate is horrible on these consoles. You can't take this isolated benchmark and apply it across the board to all scenarios. That's very misleading.

When these consoles can render native 4k/60FPS games, we can boast about fillrate. Until then, they are stuck with dynamic resolution because of the lack of fillrate.
 
N

Nhranaghacon

Banned
I still see many citing they don't understand what this means, it boils down to polygon fill rate/amount of object's on screen but in particular demonstrates the massive polygon budget specific to next gen consoles.


We will see games that exceed anything a 2080 offer's as standard due 1st part dev's focusing on one gaming ecosystem specifically for next gen Titles.

Unfortunately by the time these games release it is likely the 5080 will be at least a conversation piece to gamers.
 
A Most Virtuous Cat

A Most Virtuous Cat

Banned
regawdless said:
PS 5 really is a well optimized console, I'm continually impressed by it's performance for that price. 399 with a controller? That's a steal for this kind of performance.
Click to expand...
Steal? My friend with the 1st party Sony is offering + the crazy amazing controller + the ssd which on its own would be worth $300 + ps plus collection, $400 for the whole thing is not a steal. It is a ROBBERY!
 
DJTaurus

DJTaurus

Member
Coulomb_Barrier said:
Yep, the PS5 is running Ass Creed Valhalla equivalent to a 3070 (2080 Ti) at minimum. So much for Ampere graphics cards blowing the consoles out of the water, like some claimed.
Click to expand...
They say that consoles achieve same pc resolutions/frames at low/mid graphics (for example less effects) when for example 2080/2080ti runs at high. Do we have any source for example on Valhalla on what settings consoles are running it ?
 
Black_Stride

Black_Stride

do not tempt fate do not contrain Wonder Woman's thighs do not do not
alucard0712_rus said:
I can't stand this much fanboyism in a topic no one understands lol.
Click to expand...

Ohh we understand.
The PS5 can render text/glyphs using this specific middleware faster than the RTX 2080 when you want to fill your whole screen with text....an absolute beast of a machine....at Font Rendering.
So obviously if it can render text that fast it must also be able to beat the RTX 2080 at everything else.
 
Valued Gamer

Valued Gamer

Banned
Nhranaghacon said:
I still see many citing they don't understand what this means, it boils down to polygon fill rate/amount of object's on screen but in particular demonstrates the massive polygon budget specific to next gen consoles.


We will see games that exceed anything a 2080 offer's as standard due 1st part dev's focusing on one gaming ecosystem specifically for next gen Titles.

Unfortunately by the time these games release it is likely the 5080 will be at least a conversation piece to gamers.
Click to expand...
Pixels ain't polygons.
 
PaintTinJr

PaintTinJr

Member
VFXVeteran said:
Fillrate is horrible on these consoles. You can't take this isolated benchmark and apply it across the board to all scenarios. That's very misleading.

When these consoles can render native 4k/60FPS games, we can boast about fillrate. Until then, they are stuck with dynamic resolution because of the lack of fillrate.
Click to expand...
This test is actually a very good comparison of GPU latency for a base task IMO, because this is the API overhead as well as hardware limit. You will likely hit against API/latency inefficiency before you should run out of actual theoretical hardware performance for a task like this, so getting closer to theoretical does mean something.

These might be fonts, but it could just as easily be pre-computed(deferred buffer) particle fx being overlaid or something akin to UE5 nanite technology rendering 4 fragments(as polys) per pixel, and so tells a useful part of an incomplete story IMHO.
 
Black_Stride

Black_Stride

do not tempt fate do not contrain Wonder Woman's thighs do not do not
TheKratos said:
I have no clue whats being compared. My simple brain just wants game comparisons.
Click to expand...

See all this text:
The PS5 rendered it faster than an RTX 2080.
EoVgJx7UUAAKDBT


Why does that matter?
Because as we all know games of this generation render this much text using SLUG all the time so being able to render it out a couple μs faster than an RTX 2080 specifically when you are going to fill the whole frikken screen with it is an absolute boon.
Note that when rendering out text like a normal person the RTX 2080 walks the PS5.
 
A

alucard0712_rus

Gold Member
Black_Stride said:
Ohh we understand.
The PS5 can render text/glyphs using this specific middleware faster than the RTX 2080 when you want to fill your whole screen with text....an absolute beast of a machine....at Font Rendering.
So obviously if it can render text that fast it must also be able to beat the RTX 2080 at everything else.
Click to expand...
That's okay, but wouldn't be more interesting to see some shader, triangle, ray-tracing etc. performance than this? I mean it clocked higher than Turing, so faster fill-rate is understandable. But real-life performance?
However I was talking about fanboyism primarly.
Also 2080 is waaay faster than PS5 at ray-tracing for example.
 
Last edited:
Coulomb_Barrier

Coulomb_Barrier

Member
DJTaurus said:
They say that consoles achieve same pc resolutions/frames at low/mid graphics (for example less effects) when for example 2080/2080ti runs at high. Do we have any source for example on Valhalla on what settings consoles are running it ?
Click to expand...

They're definitely not running Valhalla at equivalent low or mid settings. It's high or ultra but I haven't seen an in-depth scene by scene analysis of PS5/X vs PC Ultra specifically.

In any case, you need an 800% zoom to notice the difference between High and Ultra. Probably, I haven't tested this game on my PC as it's pretty shit.
 
N

Nhranaghacon

Banned
Valued Gamer said:
Never heard of polygon fill rate.
You can have bigger polygons which require more pixels to fill it vs smaller ones which require less pixels.
They don't scale with each other.
Click to expand...
Fill Rate is commonly used to define peak theoretical polygon performance.

What you moved on to suggest, in fact has nothing to do with anything I cited specifically and is being used to confound in fact my own reply.

These benchmarks measure Pixel Density against Fill Rate (Polygonal Fill Rate) as is suggested where it cites the use of Bezier curves for font prospects - in plain terms - this software copies font data and turns it into Bezier curves or in other words - nuanced vertices.

Here is what is not said, the very fact that Bezier's are mentioned insinuates the software applies the font to an overlay of 3d Vertices, then convert's that data into a flat 3d font 'glyph' as Bezier data is typically only needed when rendering 2d assets as a flat 3d object when rendering.
 
Last edited:
Black_Stride

Black_Stride

do not tempt fate do not contrain Wonder Woman's thighs do not do not
alucard0712_rus said:
That's okay, but wouldn't be more interesting to see some shader, triangle, ray-tracing etc. performance than this? I mean it clocked higher than Turing, so faster fill-rate is understandable. But real-life performance?
However I was talking about fanboyism primarly.
Also 2080 is waaay faster than PS5 at ray-tracing for example.
Click to expand...

New to GAF?

Anything and everything that shows any discrepancy between the PS5/XSX/PC will lead to fanboyism.
So yes even the PS5 being able to rendering an obscene.....sorry absurd amount of text on screen faster than a PC GPU will lead to some sort of fanboyish comments.

The test is literally called "absurd"....the normal test has the RTX 2080 ahead of the PS5....but again thats at Font Rendering using this specific middleware.
I dont even know how this thread has gone as long as it has.

But in Cerny we trust and all that jazz.
 
Black_Stride

Black_Stride

do not tempt fate do not contrain Wonder Woman's thighs do not do not
oldergamer said:
WTF is this? Why does this test even matter? How about a rest that a game would actually use?
Click to expand...

It matters to the developer of SLUG (This middleware) effectively because he is proving that his middleware can render an absurd amount of text on PS5 in μs so everyone who wants to use this middleware can rest easy knowing that on PS5 all that text rendering that used to take μs will now take less μs per frame.
 
Rentahamster

Rentahamster

Rodent Whores
How can anyone even act like they understand what the useful implications of this benchmark are aside from 60 fps on Adobe Font Rendering Simulator?
 
Md Ray

Md Ray

Member
VFXVeteran said:
Fillrate is horrible on these consoles. You can't take this isolated benchmark and apply it across the board to all scenarios. That's very misleading.
Click to expand...
PS5's 143 Gpix/s peak is horrible? I agree XSX's 116 Gpix/s is horrible, which is even lower than RDNA 1 5700 XT's 122 Gpix/s fillrate.
VFXVeteran said:
When these consoles can render native 4k/60FPS games, we can boast about fillrate. Until then, they are stuck with dynamic resolution because of the lack of fillrate.
Click to expand...
For $399 the PS5's pretty good.
 
Last edited:
You must log in or register to reply here.

Similar threads

Xbox Dev Demonstrates NVIDIA GeForce RTX 2080 Ti & Xbox Series X Mesh Shaders Performance With DirectX 12 Ultimate API
3 4 5 6 7
310
36K
Three Jackdaws replied
Unreal Engine 5 revealed! Real-Time Prototype Gameplay Demo Running On PS5
30 31 32 33 34
2K
134K
Mr Wonderstuff replied
PS5 – Every Official News, Leak & Rumor on Sony’s Next-Gen Console
5
2K
SoloKingRobert replied
Xbox Series X CPU Performance May Be on Par With Ryzen 5 1600/1600 AF, Analysis Suggests
2
56
8K
JareBear: Remastered replied
C4 Engine 4.0 now has new subscription model
11
4K
blu replied
Top Bottom