The PS4 | Xbox One Benchmarks Thread

[Nate4Drake]

walsufnir said:
All these benchmarks... So the slides actually "confirm" that the CPU in Xbox One is actually a little bit faster than the one in PS4 but another benchmark shows otherwise (the compression benchmark, that is).
Even more the PS3 CPU is more capable than PS4s?
Furthermore they say there approach is bandwidth limited which automatically favors PS4 because of its way better ram - but by this they also only mention what they did to optimize for PS4 and not what they did to optimize it (if at all) on Xbox One and not mentioning usage of ESRAM for one time.

Benchmarks say the truth.  When they showed X1 CPU slighty better, they clearly said X1 CPU was using ESRAM, which was just theory and in real Game application is the GPU which makes the most use of ESRAM. 

Also, don't make the most common mistake that some do : don't compare CPU vs CPU, or GPU vs GPU alone. You have to look at the whole Achitecture of each Console.   Let's take an example : PS3 vs 360. In that Benchmark, PS3 CPU shows much better performance  than the 360 CPU(roughly 3 times), but it's not the whole story.  The Cell in the PS3 has to do so many heavy stuff to support the RSX in graphical computing that in the end the left power for Generic task is not superior at all VS 360 CPU.  On the other hand, the 360 CPU is almost free to do all the Generic task cause the 360 GPU is more powerful and sofisticated and does not need help from the CPU.

And you say ''Even more the PS3 CPU is more capable than PS4s'';  completely wrong.

As I explained above, most of PS3 CPU resources are 'wasted' for graphical stuff, while the PS4 CPU can be supported by CUs GPU to massively improve CPU performance in Physics, collision system, AI, animations, generic task, etc.

Compare APU vs APU, compare Architecture vs Architecture, don't ever compare 1single element VS 1single element.

-----------------------------------------------------------------------------------------------------------------------------------------------------------------

This explains in few words how the Asynchronous Compute Engine works.  Devs need some more time to take full advantage of it.

The Asynchronous Compute Engine basically tells data were to go, queuing up the commands and then processing them when the GPU has the spare “Cycles” to process it.

Imagine yourself driving on a highway, with hundreds of lines – but ahead of you is a toll booth. Consider that you can’t see which booths are free from your perspective (you’re stuck behind large trucks and so on after all). So you’re effectively only able to use signs tell you which lane to take. The more ACE’s there are (in this case, electronic signs) to tell you which lane to go to, the faster you’ll be sent to a lane that’s tollbooth is as empty (or at least as free) as possible.

So in other words, the ACE will accept work, and then dispatch it to a CU (compute unit) for processing when its resources are freed up. The task of the ACE is to figure out the priority of the task – in other words, to ensure that if it processes a bit of compute data, it won’t negatively affect the frame rate of the title.

Just to put this into some perspective, the PlayStation 4 has 1152 of these lanes (Streaming Processors), with 64 ‘signs’ telling the cars where to go. As a comparison, the Xbox One has 768 ‘lanes’ (Streaming Processors), with 16 ‘signs’ to tell the traffic which way to flow.

 

http://www.redgamingtech.com/playstation-4-gpu-next-gen-amd-radeon-volcanic-island-gpu-compute-similarities/