• 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.

Substance Engine benchmark implies PS4 CPU is faster than Xbox One's

N

Nightengale

Member
B-b-but Sony didn't say anything when MS did! I thought these companies were carbon copies who all only copied each other and will do all the same stuff!! /sarcasm

MS does what Sonytendon't.
Sony does what Microtendon't.
Nintendo does what Sonysoftdon't.

What a surprise that 3 different companies do 3 different things.

NBtoaster said:
Sony could have said something..
Click to expand...

Why should Sony say anything? ( for both the RAM and CPU non-story ) They've historically never revealed these details for their prior consoles themselves, why should they just because Microsoft did?
 
A

Amir0x

Banned
Pistolero said:
Matt's reply makes it look like the culprit in the affair is the greater overhead the X-One CPU has to deal with. It might be that the PS4 only reserves one core for the OS, which would offset the superior frequency adjustement made by MS.
Click to expand...

I got the impressions it was a combination of elements including that fact, but whatever the case, the result is the same. There was mass misreporting of this subject, thus leading to thousands of now ill-informed people.
 
Truespeed

Truespeed

Member
onQ123 said:
Because the benchmark is showing the PS4 CPU to be ~ 16% faster than the Xbox One CPU.


if they are both using the same CPU with 6 cores for games that would place PS4 CPU at 2.0GHz vs 1.75GHz.


or this could mean that PS4 is able to use all 8 cores for games & they are clocked at 1.6GHz with less than a core reserved for the OS.


or it could just be that PS4 APU is designed to get more out of it's CPU than what the Xbox One can.
Click to expand...

Or 10% is allocated to the Kinect and the remaining 4+% is possibly due to API overhead or whatever.
 
S

serversurfer

Member
Pistolero said:
Matt's reply makes it look like the culprit in the affair is the greater overhead the X-One CPU has to deal with. It might be that the PS4 only reserves one core for the OS, which would offset the superior frequency adjustement made by MS.
Click to expand...
Matt's under NDA, so he can't really say, "XBone OS has a bigger CPU reservation," or "PS4 CPU is clocked higher," or anything of the sort. Technically, he probably can't even discuss the relative power of the machines at all, but the cat's sorta out of the bag now.

Regardless, when it's all said and done, the PS4's CPU is giving more to game devs than XBone's. It doesn't really matter why. No, MS aren't going to start reserving one core instead of two, because they're not gonna stop running Win8 on the thing; their OS demands will always be significantly higher than Sony's.
 
O

onQ123

Member
Truespeed said:
Or 10% is allocated to the Kinect and the remaining 4+% is possibly due to API overhead or whatever.
Click to expand...

That would be included in the 2 Cores & the API overhead would be included in what I said about the PS4 being designed to get more out of the CPU than the Xbox One.
 
S

serversurfer

Member
Truespeed said:
Or 10% is allocated to the Kinect and the remaining 4+% is possibly due to API overhead or whatever.
Click to expand...
No, it's 10% of the GPU. The OS reservation on XBone's CPU is two of the eight cores, so 25%.

The debate is whether PS4's 17% advantage comes from making seven cores available to devs instead of six at the same clock — which would be the case if they're benchmarking the entire CPU — or if it comes from the PS4 simply being clocked higher than the XBone — which would be the case if the benchmark only tests a single core. The iOS results for the benchmark would seem to indicate the latter though, so it's sounding like the PS4 is both clocked higher and reserves a smaller fraction of its larger pool of resources; seven 2 GHz cores versus six 1.75 GHz cores.
 
M

Mastperf

Member
onQ123 said:
PS4 is like "You ain't got no wins in mi casa"


Just snatching every little gleam of hope out of the Xbox One soul.


Kinect & the audio chip is the only hardware advantage that the Xbox One have left & MS better do something to show them off.
Click to expand...
SHAPE is mostly for Kinect with developers being unable to touch the majority of it. With the recent news about the PS4's audio hardware, I would say It's unlikely the XB1 has an advantage in audio.
 
A

Amir0x

Banned
Mastperf said:
SHAPE is mostly for Kinect with developers being unable to touch the majority of it. With the recent news about the PS4's audio hardware, I would say It's unlikely the XB1 has an advantage in audio.
Click to expand...

I'm pretty sure we'll be able to rule out almost any advantage that was being bandied about for XBO as 'technically superior' soon, if it's not already :p
 
B

Biker19

Banned
onQ123 said:
PS4 is like "You ain't got no wins in mi casa"

Just snatching every little gleam of hope out of the Xbox One soul.

Kinect & the audio chip is the only hardware advantage that the Xbox One have left & MS better do something to show them off.
Click to expand...

Actually, the audio chip inside the PS4 trumps the audio chip inside Xbox One, I think:

Link 1.
Link 2.
 
I

infiniteheteroskdasticity

Member
This is a complete guess but I think it is possible that the PS4 CPU turbos to 2.0 GHz when running on fewer cores. Outright turbo on a console makes no sense because it would destroy the fixed spec aspect of it but dynamic overclocking based on the number of cores used should be manageable. This would also explain why Sony hasn't been able to provide a single clock speed for its CPU.

Anyway, this makes very little real world difference. As a owner of both consoles I think the graphical gulf between the two is pretty enormous compared to past generations. Even the best looking Xbox One game, Ryse, only manages it by dropping resolution and using small tightly designed levels (compared to Killzone SF that does it at 1080p and with enormous open levels). There are many good reasons to own a Xbox One. Graphical capability just isn't one of them and I think most owners will be ok with that. As long as Halo 5 is good I'm happy with it.
 
R

RaijinFY

Member
Net_Wrecker said:
Back in my day, companies lost money on the console so they could be on the bleeding edge, and I wouldn't need 8 jobs to afford it. Then they made up the difference with lots of good software.

I want everyone to be successful this gen so that the PS5 and Xbox TWO will be true beasts again because Sony and MS will have enough bank to be safe.
Click to expand...

You can forget that, thermal limits and economics will dictate otherwise...
 
Truespeed

Truespeed

Member
onQ123 said:
That would be included in the 2 Cores & the API overhead would be included in what I said about the PS4 being designed to get more out of the CPU than the Xbox One.
Click to expand...

serversurfer said:
No, it's 10% of the GPU. The OS reservation on XBone's CPU is two of the eight cores, so 25%.

The debate is whether PS4's 17% advantage comes from making seven cores available to devs instead of six at the same clock — which would be the case if they're benchmarking the entire CPU — or if it comes from the PS4 simply being clocked higher than the XBone — which would be the case if the benchmark only tests a single core. The iOS results for the benchmark would seem to indicate the latter though, so it's sounding like the PS4 is both clocked higher and reserves a smaller fraction of its larger pool of resources; seven 2 GHz cores versus six 1.75 GHz cores.
Click to expand...

Ah, I was under the impression the CPU was handling the Kinect processing. I think I got it from a SA article.

XBox One’s Kinect sensor overcomes problems with intelligence

One thing you will notice is completely absent is any mention of how people, parts of people, and various objects are identified and analyzed. How does the system figure out that this blob of depth data a person and that blob of depth data is a chair? The answer is easy enough, the Kinect sensor doesn’t nor does the Kinect device, the XBox One does. The sensor data is fed directly to the main SoC with the lowest latency possible where the magic happens.

Remember all those offload engines on the SoC, a good number of which didn’t appear on the block diagram? This is where the Kinect does the heavy lifting but since it is done on the XBox One’s CPU/SoC I guess that is a bit of a misnomer. All the processing is done with accelerators where possible and by one of the 8 AMD Jaguar cores where they are a better fit. How is this accomplished? That is a good question that Microsoft didn’t answer.
Click to expand...
 
J

Jabba

Banned
Skeff said:
not really, if a company can charge more for a less powerful console and be successful, how powerful do you think their next console would be?
Click to expand...

Which brings the question. How powerful would the competitors be next time also? Slippery slope material.
 
Y

Yoday

Member
Excellent. The larger the power gap in the systems is, the more clean the PS4 versions of games are going to look and perform.
 
O

onQ123

Member
Mastperf said:
SHAPE is mostly for Kinect with developers being unable to touch the majority of it. With the recent news about the PS4's audio hardware, I would say It's unlikely the XB1 has an advantage in audio.
Click to expand...

Biker19 said:
Actually, the audio chip inside the PS4 trumps the audio chip inside Xbox One, I think:

Link 1.
Link 2.
Click to expand...

Amir0x said:
I'm pretty sure we'll be able to rule out almost any advantage that was being bandied about for XBO as 'technically superior' soon, if it's not already :p
Click to expand...


I know it's mostly for Kinect & it's supposed to make it a lot better at voice commands.





on another note: if PS4 CPU is out performing the Xbox One CPU by ~16% while using the same number of cores & clocked lower you have to wonder how much the GPU is out performing the Xbox One GPU by with more CU's.



PS4 might be lot more powerful than the Xbox One than people think.
 
I

ionicbluebird

Member
GrizzleBoy said:
Been wondering since forever why the XB1 has a chip that supports two different versions of wireless screen sharing protocol, yet has no screen sharing capabilities to speak of present or announced for the future.

So much potential literally being ignored.
Click to expand...

satam55 said:
Info on the PS4 & Xbox1's Wireless Chips:

PS4: Marvell Avastar 88W8797 (http://www.marvell.com/wireless/avastar/88W8797/, http://www.marvell.com/wireless/assets/marvell_avastar_88w8797.pdf)

Xbox1: Marvell Avastar 88W8897 (http://www.marvell.com/wireless/avastar/88W8897/, http://www.marvell.com/wireless/avastar/88W8897/assets/Marvell-Avastar-88W8897-SoC-PB.pdf)

I'm pretty sure only devices that have Dual-band WiFi, can do WiFi Direct. The Direct connect between the PS4 & PS Vita is probably "Wireless Ad-Hoc Mode".
Click to expand...

Would this be good for something like remote-play.... or dare I say it, Forteleza?

Sony could be caught off guard by going cheap with their wireless. I mean it's not like they are going to fracture the userbase by upgrading to compete... should have had the fancy-shmancy wifi's in the first place.

I mean, surely Sony sees Forteleza coming, don't they? I wonder what their response will be.
 
I

imt558

Banned
coldfoot said:
The devkit that demo'ed Shadow Fall in february had 4GB RAM and was clocked at 1.6GHz, this is a fact, not a rumor.
We know they've upped the memory to 8GB, we do not know if the cpu clock was upgraded, that's still a rumor.
Click to expand...

Dev kit in february was not FINAL.
 
C

Chumpion

Member
infiniteheteroskdasticity said:
This is a complete guess but I think it is possible that the PS4 CPU turbos to 2.0 GHz when running on fewer cores. Outright turbo on a console makes no sense because it would destroy the fixed spec aspect of it but dynamic overclocking based on the number of cores used should be manageable. This would also explain why Sony hasn't been able to provide a single clock speed for its CPU.
Click to expand...

It's possible but why would Sony do that? Seems like it would be extra hassle with little payoff. Game engines are expected to parallelize these days.

If it's really 7 cores @ 2 GHz vs. 6 cores @ 1.75 GHz, the performance gap becomes 33%.
 
P

Perkel

Banned
Chumpion said:
It's possible but why would Sony do that? Seems like it would be extra hassle with little payoff. Game engines are expected to parallelize these days.

If it's really 7 cores @ 2 GHz vs. 6 cores @ 1.75 GHz, the performance gap becomes 33%.
Click to expand...

Why would they do that ? They already have stronger hardware by a lot and even if CPU is actually a bit weaker they invested a lot in compute power so essentially CPU won't need to calculate some heavy stuff leaving power to do other stuff.
 
I

imt558

Banned
onQ123 said:
I know it's mostly for Kinect & it's supposed to make it a lot better at voice commands.
Click to expand...

If Xbone owner can control Xbone with voice and camera ( mandatory for voice commands ), PS4 owner can control PS4 with voice only using DS4 and headphones. What an advantage for Xbone.
 
S

strata8

Member
Turbo also doesn't make sense because they're not thermally constrained. Not by the CPU, anyway - 8 Jaguar cores at 2 GHz isn't going to draw more than 30W even under load. That's compared to 20-25W at 1.6 GHz so it's not a huge difference.
 
D

DieH@rd

Banned
strata8 said:
Turbo also doesn't make sense because they're not thermally constrained. Not by the CPU, anyway - 8 Jaguar cores at 2 GHz isn't going to draw more than 30W even under load. That's compared to 20-25W at 1.6 GHz so it's not a huge difference.
Click to expand...

Official AMD figures are 15W for one quadcore Jaguar module @ 1.6GHz [that's without on-chip GPU], and overclock is inducing almost exponential rise in power consumption. Those chips were not designed to work much above 1.6GHz.
 
S

strata8

Member
DieH@rd said:
Official AMD figures are 15W for one quadcore Jaguar module @ 1.6GHz, and overclock is inducing almost exponential rise in power consumption. Those chips were not designed to work much above 1.6GHz.
Click to expand...

That's CPU+GPU TDP. AMDs Opteron X1150 - which is a CPU-only 4 core Jaguar chip - has a TDP of 17W at 2 GHz. And that includes the consumption of the rest of the SoC which accounts for 2-3W.
 
F

flying dutchman

Neo Member
Having seen top of the line PC games on a pc rig more powerful than my PS4, we compared Killzone to BF4 and Crysis 3 and even Bioshock Infinity and Killzone more than stood up to those PC games. And in my eyes, as a now non xbox one owner, Ryse looks more impressive than Killzone and would also stand up to PC. Sure PC will have more FPS and go to a higher res and that gap will widen as time goes on, so I dont get the hate for Jaguar. Do the people here shitting on it think they have a greater understanding of cpus, gpus and the like than the engineers at AMD, Sony and MS? Seriously? Do you think think they threw on that piss weak, bottleneck inducing CPU because they lacked the knowedge that you have of CPUs and game development?
 
F

Fox_Mulder

Rockefellers. Skull and Bones. Microsoft. Al Qaeda. A Cabal of Bankers. The melting point of steel. What do these things have in common? Wake up sheeple, the landfill wasn't even REAL!
Now PS4 is definitely more powerful then xbox one.

I bet Ryse would have been at 1080p and 60 fps on ps4.
 
P

PerZona

Member
I'm actually not surprised. I thought all the while that the PS4 has a faster processor than the Xbone. And no I'm talking about the RAMs. In any case, need more games for these next-gen consoles...Feb/March really needs to come quick.

Meanwhile, I'm still thinking whether or not to purchase a Wii U....
 
C

Cheech

Member
There is nothing wrong with the CPUs in either of these machines, Jesus. You do not need some banging i7 in a game console. These do not need to be high end PC workstations to fully utilize the GPUs.

I use a 4 year old i5-760 in my gaming PC, and I still don't need to upgrade to max out the vast majority of PC games.
 
RoadHazard

RoadHazard

Gold Member
Cheech said:
There is nothing wrong with the CPUs in either of these machines, Jesus. You do not need some banging i7 in a game console. These do not need to be high end PC workstations to fully utilize the GPUs.

I use a 4 year old i5-760 in my gaming PC, and I still don't need to upgrade to max out the vast majority of PC games.
Click to expand...

Yeah, certain people's obsession with what "shitty mobile CPUs" these consoles have, and their need to keep pointing it out, is weird. The GPU is so, so, so much more important for these consoles (and any gaming PC going forward), the CPU is really just there to be the "work leader" and perform some other tasks. Most of the heavy lifting will be done by the GPU. I doubt we'll see many CPU-limited games on these consoles.
 
You must log in or register to reply here.

Similar threads

Qualcomm Unveils Snapdragon X Elite CPU PC Benchmarks: Oryon Core Faster & Efficient Than Intel 13th Gen & Apple M2 Max, GPU Faster Than AMD RDNA 3
2 3 4
172
17K
twilo99 replied
IGN/NXGamer: Assassin's Creed: Mirage PS5 vs Xbox Series X|S vs PS4 vs Xbox One Performance Review
2
70
8K
Gambit2483 replied
Intel Core i9-13900 ‘Raptor Lake’ Early CPU Sample Tested, Up To 50% Faster Than Core i9-12900 ‘Alder Lake’ at Just 3.7 GHz Clock Speeds
7
2K
kikkis replied
  • Poll
Were the Xbox One X and PS4 Pro pointless or necessary? Did you upgrade or become a first time buyer?
2 3
118
6K
Eddie-Griffin replied
  • Poll
Why Xbox Abandoning The Traditional Console Business Model, Makes Business Sense
Business Analysis Platform 2
72
5K
WitchHunter replied
Top Bottom