DX 12 Performance discussion

[MattyMatt]

[Various] Ashes of the Singularity DX12 Benchmarks - Page 41

 

[Sagath]

Don't hold much stock in these early alpha dx12 benchmarks. Just because AMD is 'winning' doesn't mean much. I'm actually amazed that their drivers are this far along, considering how bad their release drivers have been for, oh, a decade...

 

[Bond007]

Don't hold much stock in these early alpha dx12 benchmarks. Just because AMD is 'winning' doesn't mean much. I'm actually amazed that their drivers are this far along, considering how bad their release drivers have been for, oh, a decade...

i think (someone correct me if I am wrong) that drivers play a smaller role in performance with dx12, and its more hardware. To what extent that is true I don't know, but that's the way I take many of the write-ups I have read.

 

['47 Knucklehead]

Finally, the "nVidia doesn't support Async" junk is over

NVIDIA Will Fully Implement Async Compute Via Driver Support

Basically, by the time that Ashes of Singularity is released (right now it's only a pre-beta beta), both AMD and nVidia will be using Async Compute.

And they've got Oxide from Ashes of Singularity to confirm that. Oxide’s developer “Kollock” wrote that NVIDIA has not fully implemented yet Async Compute in its driver, Oxide is working closely with them in order to achieve that.

“We actually just chatted with Nvidia about Async Compute, indeed the driver hasn’t fully implemented it yet, but it appeared like it was. We are working closely with them as they fully implement Async Compute. We’ll keep everyone posted as we learn more.”
​

From the looks of it, NVIDIA will – at least for now – rely on a software/hardware solution for Async Compute instead of a fully hardware one.

As Overclock’s Mahigan explained:

“The Asynchronous Warp Schedulers are in the hardware. Each SMM (which is a shader engine in GCN terms) holds four AWSs. Unlike GCN, the scheduling aspect is handled in software for Maxwell 2. In the driver there’s a Grid Management Queue which holds pending tasks and assigns the pending tasks to another piece of software which is the work distributor. The work distributor then assigns the tasks to available Asynchronous Warp Schedulers. It’s quite a few different “parts” working together. A software and a hardware component if you will.


With GCN the developer sends work to a particular queue (Graphic/Compute/Copy) and the driver just sends it to the Asynchronous Compute Engine (for Async compute) or Graphic Command Processor (Graphic tasks but can also handle compute), DMA Engines (Copy). The queues, for pending Async work, are held within the ACEs (8 deep each)… and ACEs handle assigning Async tasks to available compute units.


Simplified…

Maxwell 2: Queues in Software, work distributor in software (context switching), Asynchronous Warps in hardware, DMA Engines in hardware, CUDA cores in hardware.

GCN: Queues/Work distributor/Asynchronous Compute engines (ACEs/Graphic Command Processor) in hardware, Copy (DMA Engines) in hardware, CUs in hardware.”

​

 

[Sagath]

I figured that would happen.

AMD Fanboi's were plenty happy to compare their' old' $300 card as outperforming a $700 nV card. What they loved to omit was the fact that the Fury X performed the same. But hey, that wouldnt fit the narrative now would it? Lets just glaze over that.

 

[SKYMTL]

This thread was finished before it started methinks. There's nothing to discuss. Come back in a year when there will be a FEW more DX12 games. Come back in two years when DX12 becomes a "thing".