Recent content by Fiendish

Didn't open source already win back when Nvidia started Streamline? I'm guessing Nvidia's whole plan for awhile now is to make it trivial to add the various AA/Upscaling solutions so that it always comes down to a comparison of quality and performance. If developers have a simple framework for...

Arm doesn't need a Nvidia ownership to accomplish the goal of moving PC gaming away from x86. I think Qualcomm's suggestion of having a consortium of invested companies would likely achieve the same goal and would be a far better outcome for consumers and it's not like Nvidia would pass on...

What don't you agree with?

Those effects map relatively well to even GPUs from yesteryear but even then it doesn't take much for things to get bogged down. Modern GPUs handle those kinds effects far better. You can see the difference in relative performance cost between Nvidia's older architectures and Turing for...

The important time for it to have been used would have been back "then", in 2008-2009 and the beginning of the 2010s were broader usage would have steered the direction of GPU designs to be more flexible and suited to the task, something we are only starting to see now after a decade of...

So first, it was Nvidia crippled/hobbled "their" software to make their GPU's look better, then it was Nvidia didn't "fix" the software they inherited from Ageia, then it's Nvidia didn't fix it fast enough... seriously? Ageia got multiple developers to do exactly what you're saying they...

Sigh... they did fix it with PhysX 3, it was a significant overhaul and was completed as quickly as could be expected for something like that. Maybe you need to take another look that the timelines here. You just described Ageia's pre-Nvidia business model verbatim... You lied...

Your claim, "It's software version was meant to make the GPU version look like 10 times faster" is bullshit. You're saying the codebase from before Nvidia's acquisition was designed to make GPU's faster, despite not even being ported to GPU's yet. So AMD is fine with proprietary and locked...

That was a bullshit myth. http://www.codercorner.com/blog/?p=1129 You're ascribing information from 2010 to AMD's decision making process in 2008. In 2008 AMD had a lot more reason to distrust Intel than Nvidia and yet they had no problem supporting Intel's proprietary and locked standard...

Support for PPUs wasn't dropped until years after the acquisition and PPU sales were abysmal to begin with. You do know that Ageia sold themselves to Nvidia because they had no future right? Nvidia actively blocking AMD happened after AMD (Godfrey Cheng specifically) publicly crapped on PhysX...

Ageia's hardware accelerated PhysX was already exclusive to their proprietary hardware (Ageia's PPUs) before Nvidia's acquisition, after the acquisition they merely ported the framework to run on Nvidia's GPUs as well. Nvidia both continued and expanded the development of PhysX and if you read...

If you're upset PhysX never took off more, you might look AMD's way. https://gizmodo.com/nvidia-helping-modders-port-physx-engine-to-ati-radeon-5023150

According to the Volta whitepaper and other documentation, the full GV100 GPU had 84 SMs and no product was ever released with more than 80 SMs enabled, which means they were NEVER able to achieve a fully enabled implementation.

Based on the Gamers Nexus testing, their GTX hardware gave worse performance AND quality compared to RTX hardware. Seems like it DOES only run well with tensor core aid.

One of those games is using RT for full Global Illumination, the other is using RT for limited shadow effects, the fact that the performance hit is similar should give you a very good idea how much better dedicated hardware is. The Crytek demo ended up showing the same thing when they noted how...