The RTX 4090 bets on software, and it’s a good call


Nvidia finally announced the RTX 4090 and RTX 4080 during its GeForce Beyond special stream. Maps are coming soon and they are packed with new features. So much, in fact, that Nvidia focused much less on raw performance in its presentation and much more on the software stack that will support the Ada Lovelace GPUs.

There are a lot of unanswered performance questions about the RTX 4090 and RTX 4080, especially since they are more expensive than the previous generation. Still, the cards are a sign of what’s to come in the future of PC graphics. Power matters, of course, but increasingly the fidelity of games depends on the software supported by newer GPUs. Nvidia makes that call, and it’s the right one to make.

Where the raw power stops

It’s easy to assume that throwing more power at the performance issue is all you need to do to increase frame rates, but the speed at which Nvidia moves doesn’t allow the hardware to catch up. If Jensen’s comments are anything to go by – where games become a massive simulation – you’d need a GPU several generations later.

Currently, the highest quality rendering occurs offline. Simply put, a GPU works on rendering every frame, no matter how long it takes. Games render the same, but it happens at runtime. The application (your game) executes instructions while rendering, and the render must be fast enough to have a playable frame rate.

The GPUs available to gamers are the same as those available to visual effects and animation studios in many cases, so this jump in rendering fidelity cannot be solved by releasing new GPUs. There must be a way to optimize runtime performance to have the same quality as an offline render. That’s the idea, at least.

A graphic showing how Nvidia's DLSS 3 technology works.

Nvidia achieves this through two main tools: Deep Learning Super Sampling (DLSS) 3 and Shader Execution Reordering (SER). Most Nvidia users are familiar with DLSS. This is an upsampling tool that uses a lower internal resolution before upscaling with AI to reach your monitor’s native resolution. Fewer pixels to render means faster performance. Simple enough.

DLSS 3 seeks to go further. In addition to traditional AI upscaling, DLSS 3 will generate entirely unique frames that were not rendered by your GPU. It looks at previous and future frames and can predict what your GPU would render in between. It goes without saying, but single frames that your GPU doesn’t need to render are a tempting offer to boost performance.

A graph showing how Nvidia's shader runtime revamp works.

SER specifically applies to ray tracing, which is required for a game that wants to be a great simulation. Nvidia says it reschedules shading workloads in real time, which can deliver up to 25% improvement in your frame rate. Nvidia equates SER to out-of-order execution for processors, which is quite the assertion.

Generally, ray tracing does not work well with parallel processing. Simply put, each ray needs its own attention due to the semi-random nature of how light bounces around. GPUs are really designed for parallel processing, which is why ray tracing is so demanding today. By optimizing ray tracing instructions based on available power, Nvidia hopes to further boost frame rates.

Software defined

The top of the Nvidia RTX 4080 cooler.

In the world of processors, there has been a lot of talk in recent years about the end of Moore’s Law. GPUs and CPUs are getting to a point where it’s not as simple as packing more transistors into the same space, which was the idea behind Moore’s Law in the first place. And we are already seeing how software can fill in the gaps.

Of course, DLSS isn’t the same as native rendering – there’s a slight trade-off in image quality – but it offers a much bigger performance boost than even a typical GPU generation. This is a difficult fact to face. A software feature, free to Nvidia RTX owners, delivers more performance than a brand new GPU. In fairness, the same goes for AMD‘s FidelityFX (FSR) super resolution, especially in its newest version.

We are reaching a point where GPUs will be defined by the software they support. SER and DLSS 3 are just the start. Clearly, Nvidia sees that the performance gains available through software optimizations can outweigh even generational improvements with enough creativity, and that should mean faster frame rates for gamers, even if they can’t afford a high-end GPU.

Will it work?

While Nvidia’s claims about DLSS and SER make sense, that doesn’t mean the software combo is a winning ticket. It’s the same company that launched ray tracing back in 2018 in an absolutely abysmal line of games, and frankly, even ray tracing today isn’t worth the performance shortfall in many cases. This could happen again with DLSS 3 and SER.

But I am confident. There are issues with the price of the RTX 4090 and RTX 4080, absolutely, but the technology underneath is very promising. DLSS works wonders now, and I hope Nvidia learned from the first version about how image quality can improve the experience. SER is also exciting, promising free ray tracing performance without any special rendering techniques.

My confidence is not concrete, however. It’s important to wait until the RTX 4090 and RTX 4080 are here before drawing any firm conclusions. Either way, the future of PC graphics has been and will continue to be defined by software, and Nvidia’s latest GPUs are testament to that.

Editors’ Recommendations


Comments are closed.