Async compute is nothing new - CPUs do it all the time when context switching. But still you are going to use the same resources in rendering, as there is not much time to "context switch". All the time frames want to be rendered, where do you want to get the time for doing GPGPU with the same resources?

What they are mostly saying is that you can use the resources for rendering and GPGPU at the same time but if you do GPGPU then these resources do GPGPU and not rendering work. There is no duplicated hardware present.

As Nate4Drake already quoted:

"Cerny explained that there are many situations during game applications where functions pertaining to graphics take a backseat, and that the PS4 hardware has been designed to make the most of the under-utilized portions of the GPU during such frames.''

When will this be? In a graphical demanding game this will not likely happen. And when it does what do you want to compute then? A game has to be developed that "if close to nothing happens" to compute but what for?

You do know Async is not a magic bullet.  GPGPU and the GPU are fighting for the same resources.  Yes both can run at the same time but if resources are limited or there is a bottleneck in the process you might not see great gains or performance.   Here is a very important part of that interview that needs to be understood.

""The reason so many sources of compute work are needed is that it isn’t just game systems that will be using compute -- middleware will have a need for compute as well. And the middleware requests for work on the GPU will need to be properly blended with game requests, and then finally properly prioritized relative to the graphics on a moment-by-moment basis.""

Short statement but for the developer its a lot of work and would be very specific for each game.  Using GPGPU compute in parallel is not something that developers just code for it and it just works.  From the statement above, there is a lot of understanding of game state where you setting priorities on what get resources and when.  Scheduling those calls can be a real pain and syncing everything together probably is a nightmare unless you really need to go down that route for more gains in performance.  From this point of view, it definitely something that will need to be planned out way ahead of time and developers probably have to prototype some stuff first before wasting time in development if there are no real gains in performance. 

Of course it's not a magic bullet, nobody said it is - anybody half-literate in hardware can understand what PS4's architecture is all about and what Cerny designed.

And naturally that it requires effort and learning curve due to how it works - that's why Cerny said we'll be seeing this in 3rd or 4th year used more extensively.

That is the rason I'm suggesting to anyone who is interested more in this (and who might have certain urge to downplay this) to read that interview bit more carefully - that implies with understanding.

Again, most of the power of PS3 Cell(SPEs) must be used to help the weak and Raw GPU(RSX) of PS3...

On the other hand, the very very powerful CUs of PS4 GPU can help sooo much the PS4 CPU, so what you are saying does not make much sense.

Let people with more understanding work for the Hardware. No offence.

Yeah i'm no expert and i know about Liverpool's ACE units and yes those will show there worth in the future. But what i meant was the limited per core performance of the PS4/X1 cpu's. Atleast PS3 hade one fast PPE, giving some proper performance in single threated applications, PS4 doesn't have that. Development of games like AC Unity already shows the cpu limitations, and having even just one or two faster core's makes development so much easier. It simply gives you higher maximum performance when needed.

I'm talking about a ''big/little'' concept. So for example one or two 3.2 ghz bulldozer cores with say for jaguar 1.6 ghz cores(jaguar cores can't be clocked that high), or any similair feasible combination. Maybe even two or four jaguar cores at say 2.4 ghz and the other at 1.2 ghz would have been more usable. Especially since some of these cores are used for OS and other system applications anyway. Even if the theoratical total performance of those eight jaguar cores at 1.6ghz is higher, having one or two faster cores is much more usable.

But again i'm no expert and i don't know if it was feasible combined with the gpu on one chip.

You make it seem like Async is something big from your statement.  Designing something and getting real world results are 2 different things.  MS designed their ESRAM to be able to read and write at the same time but in real world scenerios, those situations are very limited.  The same can be true for being able to do GPU and GPGPU at the same time.  When and where are the scenerios going to be where you can do both at the same time to get real world benefit.

The interview is fine and I read it back in the day.  Just like with MS solution, I am looking more for real world examples and the same will be for Sony implementation.