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

Forums - Gaming Discussion - Ubisoft GDC Presentation of PS4 & X1 GPU & CPU Performance

ICStats on 21 October 2014
ethomaz said:

Found that thread in GAF (http://www.neogaf.com/forum/showthread.php?t=915229) with a summary:

  • X1 Marginally faster CPU (due to higher clock speed, 1.6ghz vs 1.75ghz)
  • PS4 - Has actually significantly more GPU benchmarking than thought compared to Xbox1, nearly 100% more.
  • CPU + GPGPU management is essential and seems no where near optimal this early in the generation.

Yep.  The faster CPU clock roughly accounts for the difference shown in CPU performance.

The thing to note though this says for "5ms" of time in other words if you used 5ms of CPU core time you could process that much, but the XB1 & PS4 don't necessarily have the same amount of CPU core time available per frame due to system reservation.  If the XB1 has higher system reservation for Kinect and multiple Operating Systems then it's CPU time available to the game may be lower.

The GPU benchmark is interesting.  There should not be 100% difference in compute power on the GPUs, but perhaps this benchmark is showing the memory difference, or 64bit throughput difference, or perhaps Sony's GPU API & compiler are just better than Microsoft's.



My 8th gen collection

Around the Network
ethomaz on 21 October 2014

ICStats said:

Yep.  The faster CPU clock roughly accounts for the difference shown in CPU performance.

The thing to note though this says for "5ms" of time in other words if you used 5ms of CPU core time you could process that much, but the XB1 & PS4 don't necessarily have the same amount of CPU core time available per frame due to system reservation.  If the XB1 has higher system reservation for Kinect and multiple Operating Systems then it's CPU time available to the game may be lower.

The GPU benchmark is interesting.  There should not be 100% difference in compute power on the GPUs, but perhaps this benchmark is showing the memory difference, or 64bit throughput difference, or perhaps Sony's GPU API & compiler are just better than Microsoft's.

Or 8 ACEs vs 2 ACEs... or 64 compute queues vs 8 compute queues... or 18 CUs vs 12 CUs.



HollyGamer on 21 October 2014
ethomaz said:

ICStats said:

Yep.  The faster CPU clock roughly accounts for the difference shown in CPU performance.

The thing to note though this says for "5ms" of time in other words if you used 5ms of CPU core time you could process that much, but the XB1 & PS4 don't necessarily have the same amount of CPU core time available per frame due to system reservation.  If the XB1 has higher system reservation for Kinect and multiple Operating Systems then it's CPU time available to the game may be lower.

The GPU benchmark is interesting.  There should not be 100% difference in compute power on the GPUs, but perhaps this benchmark is showing the memory difference, or 64bit throughput difference, or perhaps Sony's GPU API & compiler are just better than Microsoft's.

Or 8 ACEs vs 2 ACEs... or 64 compute queues vs 8 compute queues... or 18 CUs vs 12 CUs.

Just imagine if Sony increase the GPU clock to 900 mhz it will make PS4  performing 2.0 teraflops, i wish they increase back then even use 384 bit bandwith for the GDDR5 not the 256 bit GDDR5 like now. or even increase th cpu clock to 2 Ghz. :(



ICStats on 21 October 2014
HollyGamer said:
ethomaz said:

ICStats said:

Yep.  The faster CPU clock roughly accounts for the difference shown in CPU performance.

The thing to note though this says for "5ms" of time in other words if you used 5ms of CPU core time you could process that much, but the XB1 & PS4 don't necessarily have the same amount of CPU core time available per frame due to system reservation.  If the XB1 has higher system reservation for Kinect and multiple Operating Systems then it's CPU time available to the game may be lower.

The GPU benchmark is interesting.  There should not be 100% difference in compute power on the GPUs, but perhaps this benchmark is showing the memory difference, or 64bit throughput difference, or perhaps Sony's GPU API & compiler are just better than Microsoft's.

Or 8 ACEs vs 2 ACEs... or 64 compute queues vs 8 compute queues... or 18 CUs vs 12 CUs.

Just imagine if Sony increase the GPU clock to 900 mhz it will make PS4  performing 2.0 teraflops, i wish they increase back then even use 384 bit bandwith for the GDDR5 not the 256 bit GDDR5 like now. or even increase th cpu clock to 2 Ghz. :(

That would probably be HOT, literally.

Imagine if it was as big as an Xbox One, then you could fit nearly two PS4s in there. ;-D

XB1 7,216,720mm^3 With power brick outside.

PS4 4,445,375mm^3 With power supply built in!



My 8th gen collection

HollyGamer on 21 October 2014
ICStats said:
HollyGamer said:
ethomaz said:

ICStats said:

Yep.  The faster CPU clock roughly accounts for the difference shown in CPU performance.

The thing to note though this says for "5ms" of time in other words if you used 5ms of CPU core time you could process that much, but the XB1 & PS4 don't necessarily have the same amount of CPU core time available per frame due to system reservation.  If the XB1 has higher system reservation for Kinect and multiple Operating Systems then it's CPU time available to the game may be lower.

The GPU benchmark is interesting.  There should not be 100% difference in compute power on the GPUs, but perhaps this benchmark is showing the memory difference, or 64bit throughput difference, or perhaps Sony's GPU API & compiler are just better than Microsoft's.

Or 8 ACEs vs 2 ACEs... or 64 compute queues vs 8 compute queues... or 18 CUs vs 12 CUs.

Just imagine if Sony increase the GPU clock to 900 mhz it will make PS4  performing 2.0 teraflops, i wish they increase back then even use 384 bit bandwith for the GDDR5 not the 256 bit GDDR5 like now. or even increase th cpu clock to 2 Ghz. :(

That would probably be HOT, literally.

Imagine if it was as big as an Xbox One, then you could fit nearly two PS4s in there. ;-D

XB1 7,216,720mm^3 With power brick outside.

PS4 4,445,375mm^3 With power supply built in!

Well i dont mind if the console is more bigger then current one, if will fit biger fans. The current cooling system has 85mm diameter and it can keep the temp around 20-25 degree  celcius if the games is on ( 800mhz GPU and 1.6 Ghz CPU) . and idle around 15-20. So if they put around 110 mm fans, probably they should be able to overclock the gpu to 900mhz and the cpu to 1.9 to 2.0 Ghz.



Around the Network
Cobretti2 on 21 October 2014
ethomaz said:
Cobretti2 said:
Why are you recycling images that we already seen in the 20 threads or so about how ubisoft suck because of 900p on PS4?


Just let it go. It's done. Vote with your wallet.

Did you have another thread about this benchmark presentation?

Ohhhh there aren't... this is the first time posted in this forum from what I searched.

the topic was covered in one of the bitchfest ubisoft threads. You don't need a UNIQUE thread for something covered in there.



 

 

ethomaz on 21 October 2014

I don't think Sony will increase the clocks... it will generate too many issues with heat and the console already perform better than the competition.



walsufnir on 21 October 2014
darkknightkryta said:
Yeah, PS4's GPU is pretty beastly compared to the competition. Cell was also a beast of a processor. It's a shame there was never any incentive to progress the technology for Cell, I feel it scales very well.


Oh, there was. But not for consoles.



walsufnir on 21 October 2014

I always think these benchmarks funny. Remember the benchmark from last year that showed us PS4 CPU was faster than Xbox One? Now this shows the exact opposite.
Without any further data what was really tested (given these slides provide way more information than the graph last year) we can't infer *anything*, in my opinion.



mornelithe on 21 October 2014
walsufnir said:
I always think these benchmarks funny. Remember the benchmark from last year that showed us PS4 CPU was faster than Xbox One? Now this shows the exact opposite.
Without any further data what was really tested (given these slides provide way more information than the graph last year) we can't infer *anything*, in my opinion.

You mean last year, before Microsoft bumped the clock up 10%?  And this year...after the bump, it shows differently?  No way!