By using this site, you agree to our Privacy Policy and our Terms of Use. Close
fatslob-:O on 07 August 2017
Edit Thread
Pemalite said:

nVidia and AMD describe Asynchronous Compute differently anyway.

If it's exposed in Direct X 12, regardless of how extensive, it's part of the Direct X 12 spec.

It really isn't, multi-engine goes far beyond just async compute. Just as multi-engine exposes the concept of stateless compute (async compute) it comes with a number of things like stateless resource transfers (async copy through GPU DMA engines) and near stateless graphics (future) but it also takes into account hardware that don't have stateless GPU design ... 

Pemalite said:

Not really.

AMD, nVidia have contributed to the Direct X specification. There is license agreements and patents at play here.

Heck even companies like S3, Imagination Technologies, NEC, Matrox, SiS have contributed to Direct X over the years.
For example, where do you think S3 texture compression came from? ;)

Microsoft just can't say "Get out" to S3.

Microsoft still gets final say in the end regardless of AMD, Intel or Nvidia's contributions ... (I don't imagine NEC to have ever contributed to the DirectX specifications when they were just chip manufacturers for ImgTec much like TSMC is for Nvidia.) 

And yes Microsoft can say "get out" to S3 regardless of weather or not they adopted patented technology from them plus S3 holding S3TC hostage isn't going to be an issue any longer ... (the patent for S3TC is going to expire this October just like the patent for anisotropic filtering did a couple years ago)

Pemalite said:

AMD and the Industry are one in the same. AMD works with Microsoft and Khronos. Heck, Vulkan was born out of AMD's development of Mantle.

Not really, the industry includes several other seperate IHVs like Intel, Nvida, ARM, Qualcomm, ImgTec and serveral other ISVs like Microsoft, Apple, Google, Nintendo, Sony, Epic Games, Unity, EA, Ubisoft, Activision or other parties like Samsung ... 

Pemalite said:

 

Most certainly not. I hate walled gardens. 

To be fair, that hasn't really been AMD's M.O. for a very long time, since the early days of Tessellation a few decades ago.

But they need it in order for them to realistically compete ... (Until IHVs can agree upon a common ISA for GPUs it's just going to be the fact of life. Heck, Nvidia is using proprietary technology and it's making them boatloads of money.) 

Pemalite said:

The lowest common denominators, the Xbox One, Xbox One X and Playstation 4... Aren't really FP16 powerhouses so it's use will be limited even on PC. It's only the Playstation 4 Pro and Vega that are pushing double-rate FP16, it's not enough market saturation for it to obtain wide-spread industry use anyway. Thankfully.

I thought we left lower precision rendering back in the Geforce FX and earlier periods. Haha

But the fact that the PS4 Pro ALONE is already translating FP16 optimizations to two AAA games on the PC side immediately is amazing which means future games being built on the latest idTech 6 or Dunia 2 engine will automatically have FP16 optimizations ... (Maybe even more since the latest Frostbite 3 engine already supports FP16 on PS4 Pro and I imagine that will also soon translate to PC. AMD doesn't have to target wide-spread industry use, just AAA games in general and not necessarily AAA japanese games either since the vast majority of them are lost causes so that they can win in the most difficult benchmarks.) 

Lower precision is fine as long as the devs can control it ...