Rumor: PS4 GPU based on AMD's GCN 2.0 architecture?

James Prior (Tech Writer for Rage3D) said:
I'm hearing that PS4 GCN has 8 ACE's, each capable of running 8 CL's each. I believe Tahiti is 2 per ACE, 2 ACE's.

edit: 7970/7870 have two ACEs. That is quite a leap.

What are Asynchronous Compute Engines?

Rage3D said:
For use in compute applications, the Southern Islands GCN Tahiti design includes dual Asynchronous Compute Engines (ACE) for the independent scheduling and dispatch of work items, necessary for efficient multi-tasking. This allows compute workloads to operate in parallel with graphics workloads, and facilitates fast context switching so that demands by workloads that exceed concurrency abilities can be given needed resources. Despite featuring PCI-Express 3.0 which doubles interface bandwidth from 8GB/s to 16GB/s, plus support for numerous data and protocol commands, the internal dual DMA engines can push data through the bus to saturate that bandwidth.

Anandtech said:
Meanwhile on the compute side, AMD’s new Asynchronous Compute Engines serve as the command processors for compute operations on GCN. The principal purpose of ACEs will be to accept work and to dispatch it off to the CUs for processing. As GCN is designed to concurrently work on several tasks, there can be multiple ACEs on a GPU, with the ACEs deciding on resource allocation, context switching, and task priority. AMD has not established an immediate relationship between ACEs and the number of tasks that can be worked on concurrently, so we’re not sure whether there’s a fixed 1:X relationship or whether it’s simply more efficient for the purposes of working on many tasks in parallel to have more ACEs.

One effect of having the ACEs is that GCN has a limited ability to execute tasks out of order. As we mentioned previously GCN is an in-order architecture, and the instruction stream on a wavefront cannot be reodered. However the ACEs can prioritize and reprioritize tasks, allowing tasks to be completed in a different order than they’re received. This allows GCN to free up the resources those tasks were using as early as possible rather than having the task consuming resources for an extended period of time in a nearly-finished state. This is not significantly different from how modern in-order CPUs (Atom, ARM A8, etc) handle multi-tasking.
Feel free to look up who the some one is, I already put his background info in the quote itself.

Not really, we just dont know the level of customization they've gone for. (We dont really know all the meaty stuff inside the GPU)
I C it now. Sorry bro :)

Everything that benefits us gamers is good :D
Fun and games aside, in layman terms what potential benefits does GCN 2.0 (if true at all) bring to the table over its predecessor?

EDIT: It says upcoming device which could mean 8XXX series and may have nothing to do with PS4.
So there you go. Even if it's not 8ACEs and 8CLs each, it is indeed based on AMDs next architecture. I find it odd that this went unnoticed. I even talked about that in some thread but nobody answered me :p
He's a tech writer at Rage3D, does reviews like this for example;

The top of the OP has his direct quote.
LoL, yea, I saw that as a simple rumour from some poster. Now that I have read the name and thanks to the context you've provided it makes more sense.

Same processing power, but work can be divided into more parallel threads. That will increase efficiency, especially if you mix rendering and compute jobs.
Isn't GPU processing all about parallelism? And this makes it even more so? Is it developer input driven or hardware driven?
So there you go. Even if it's not 8ACEs and 8CLs each, it is indeed based on AMDs next architecture. I find it odd that this went unnoticed. I even talked about that in some thread but nobody answered me :p
things are subject to change which is why they didn't even have hte ps4 ready to show. still working on it as they go. hopefully by E3 they have everything finalized which sounds like they will unless tretton is a big lair