Puget Systems print logo

https://www.pugetsystems.com

Read this article at https://www.pugetsystems.com/guides/1224
William George (Puget Labs Technician)

What Does the Launch of the GeForce RTX 20 Series Mean for the Future?

Written on August 20, 2018 by William George
Share:

Introduction

Like many of you, I was glued to my computer screen this morning during NVIDIA's live-stream of the GeForce RTX 20 series launch. This family of video cards has been rumored and hinted about online for months now, with details slowly becoming more and more clear - especially in the last week or so. The launch of a new GPU generation - "Turing" - along with its focus on real-time ray tracing was revealed last week with the launch of the Quadro RTX line, so it was apparent that the next GeForce series would have a similar focus. But what exactly was shown today, and what does it mean for the future of gaming, virtual reality, and other GPU applications?

NVIDIA GeForce RTX 2080 Ti 11GB Founders Edition

RTX Cores & Real-time Ray Tracing

The big new feature of the Turing generation of GPUs is the RTX Core: a new bit of circuitry that is specifically focused on ray tracing in real-time. Ray tracing has been used for ages to create photo-realistic images and effects in movies, but has pretty much always required pre-processing... often taking minutes or even hours per frame. To perform similar calculations fast enough to maintain the 30, 60, or even more frames per second that games and interactive computer experiences demand was unheard-of. That is why games and VR have been using rasterisation for decades, which can be done much faster but at the sacrifice of visual accuracy and fidelity.

So, what does it mean to have hardware in the GPU dedicated to ray tracing? This signals the potential beginning of a move from rasterisation to ray tracing for real-time 3D computer graphics. I say "potential" because right now this is NVIDIA-only, and on just a handful of their newest video cards. We don't yet know how well these RTX cores can keep up: whether they can handle a fully ray-traced game at both high resolution and high frame rate. It may be that fully ray-traced games will need another generation or two of GPU advancement to provide a good experience. And I say "beginning" because it will be a long time before the market is sufficiently saturated with these (and future) cards to the point that a major game could rely on ray-tracing as the only method of rendering graphics. It might also require AMD to get onboard with similar technology, since they control a substantial portion of the video card market as well.

In the shorter term, it means that game and VR designers will have the option to adopt small elements of ray-tracing into their upcoming projects. NVIDIA showed off several examples of soon-to-be-released games which will use RTX technology for one feature or another: improved shadows in Shadow of the Tomb Raider, accurate indoor lighting in Metro Exodus, and realistic reflections in Battlefield V. This is the low-hanging fruit, so to speak: things that can be implemented without completely rebuilding a game engine, and can be enabled or disabled based on the video card used so that folks without a new GeForce RTX 20 series cards can still play.

Improved Point Light Shadows in Shadow of the Tomb Raider Using NVIDIA RTX Technology

Improved Reflections in Battlefield V Using NVIDIA RTX Technology

It should also be noted that this technology is not a replacement for full, in-depth ray tracing that is found in rendering engines like OctaneRender, V-Ray, and Redshift. While based on the same ideas, those renderers are designed to make the most photo-realistic images and animations possible - with speed being important, but taking a back seat to accuracy and realism. Many such engines already utilize the general-purpose calculation capabilities found in NVIDIA's CUDA cores to run part or all of their ray tracing algorithms, but from what I can tell their calculations are much more complex in functionality than what is being added in the new RTX Cores. Anything is possible in the future, of course, but for now I would not expect the RTX Cores to impact professional rendering performance.

Tensor Cores & Deep Learning

Tensor Cores debuted on the Volta generation of GPUs from NVIDIA, including cards like the Titan V and Quadro GV100, and they are specifically tailored to perform floating point calculations (mostly FP32 & FP16) quickly for use in machine & deep learning frameworks. This technology is all about fast processing of data based on pre-built networks and AI models, not creating those networks.

Volta never came to the mainstream GeForce lineup. Because of that, I had wondered if NVIDIA might keep Tensor Cores as an exclusive feature of more professional-oriented cards - the Titan, Quadro, and Tesla - but it looks like I was wrong. Including them on the GeForce RTX 20 family of graphics cards means that NVIDIA must see a benefit to having such calculation capabilities at the consumer level, and they gave some examples of how it could be used for enhancing the resolution of still images (like frames in a video game). I'm sure there are other applications as well, but if you want more insight into machine learning check out Dr. Don Kinghorn's HPC Blog.

Hybrid Rendering Pipelines & Future Performance Potential

Throughout the presentation, NVIDIA's CEO made claims about the performance of the GeForce RTX 2080 Ti being in the ballpark of ten times faster than the current GTX 1080 Ti... but that must be taken with a grain of salt. The numbers shown seem to be based on a new metric, which attempts to combine the old-fashioned processing capabilities of video cards with the new RTX and Tensor Cores - creating a value they call "RTX-OPS". Since the 1080 Ti (and other previous-gen cards) did not have either RTX Cores or Tensor Cores, of course they score much lower in this metric. So why are they making such extreme claims?

Hybrid Rendering Pipeline on NVIDIA Turing GPU - Example from SEED / PICA

The idea, from NVIDIA's point of view, is that all of these different processing capabilities can be combined into a hybrid rendering pipeline - using different parts of the GPU for each step, allowing a dramatic improvement in performance if fully implemented. CUDA Cores that before had to handle all the steps of rendering a frame can now just work on the rasterisation, while lighting, shadows, and reflections are handled by ray tracing (RTX Cores) and post-processing is handled by deep learning algorithms (via Tensor Cores). In the long run, a new GeForce RTX 20 series video card may well end up being several times more powerful than previous models - but we won't see the full benefits until games and other 3D applications begin to make use of these technologies.

Impact on Applications & Games Today

Until then, how much faster will these cards be compared to the GTX 10 series? That we don't know for sure yet, but looking at the CUDA core count, clock speed, and memory bandwidth numbers for the GeForce GTX 1080 Ti versus the new RTX 2080 Ti... I would hazard a guess at around a 20% increase in base performance. Specs for the 1080 vs 2080 and 1070 vs 2070 look to be in the same ballpark. Anything gained through RTX technology will be on top of that, but only when applications and games add support for it.

  RTX 2080 Ti GTX 1080 Ti RTX 2080 GTX 1080 RTX 2070 GTX 1070
CUDA Cores 4352 3584 2944 2560 2304 1920
Base Clock 1350 MHz 1480 MHz 1515 MHz 1607 MHz 1410 MHz 1506 MHz
Boost Clock 1545 MHz 1582 MHz 1710 MHz 1733 MHz 1620 MHz 1683 MHz
Memory Bandwidth 616 GB/s 484 GB/s 448 GB/s 320 GB/s 448 GB/s 256 GB/s

It is also worth noting that the onboard graphics memory each card is equipped with is not increasing at all in this generation. The GTX 1080 Ti and RTX 2080 Ti both have 11GB, while the 1080, 2080, 1070, and 2070 all have 8GB. If your application is memory-limited, as can be the case with complex 3D design and rendering, then the GeForce RTX 20 series does nothing to help with that.

Closing Thoughts

Until we get our hands on some of these cards up here in the Labs department, I can't really be sure of more than what is written above. I am eager to run the new GeForce 20 series cards through their paces, and to see how software developers take advantage of the RTX and Tensor Cores in the future. We'll be posting articles with performance data as soon as we can, most likely toward the end of September and beginning of October (given the estimate that NVIDIA has given of 9/20/18 for availability).

As for my own personal systems, I currently have GeForce GTX 1080, 980, and 1060 cards in my home gaming rigs. I have been very pleased with them, so I am not chomping at the bit to upgrade, but if games I enjoy playing start adding features which utilize ray tracing I could certainly see myself upgrading my flagship rig and passing the 1080 down to my son's system (replacing the 980 he has now). I would encourage anyone else with a nice video card to wait a bit as well, since it looks like the pre-orders are going crazy and online resellers like Newegg are suffering from greatly inflated prices. The GTX 1080 debuted over two years ago, so I'm sure the 20 series will be around for a while too... there is no need to rush!

Tags: NVIDIA, GPU, GeForce, RTX, Turing, CUDA, RTX Core, Tensor Core, Video, Card, Graphics, Rendering, Ray, Tracing, Performance, Technology, Game, Design, Virtual, Reality, Lighting, Shadows, Reflections
Martin Emmerset

" a new GeForce RTX 20 series video card may well end up being several times more powerful than previous models - " by the time popular game engines are redesigned and games actually hit market we would have the RTX 30 or RTX 40 series. Rasterisation is probably here for the next 5-6 years at least. Even more so if AMD doesn't follow Nvidia here. Wondering about the future is exciting, but let's not forget we are still waiting for the 100+% increase in performance that DX12 was supposed to bring. Looking forward to Puget's benchmarks for these!

Posted on 2018-08-27 11:41:28
BennyBlinny

Thanks for the post. As part of later articles it would be good to see tests with latest version of V-Ray and Octane 4 (at that time) to see how much benefit the new core types provide, including Tensor cores not just RT cores. Right now Tensor cores are not available in standard form factors other than Titan V. I doubt anyone in the creative space has optimized their app for a single GPU but should become more common with RTX series since they have all three core types.

Posted on 2018-08-29 22:08:57

V-Ray and Octane will absolutely be among the software I test when the new cards are released! Honestly, though, I don't expect any of the new cores to have an impact on performance in those applications. I do think we'll see about a 20% increase from the previous generation, just due to normal CUDA core increases, but the RTX and tensor cores are specialized enough that they won't immediately contribute. Rendering engines could be adjusted to utilize them, potentially, but whether that is worthwhile and how quickly it happens we'll have to wait and see.

Posted on 2018-08-29 22:13:25
Niko Nikolov

For me, the first wave of ray tracing is going to be weak.Years will be needed.

My bigguer problems are two.
1.Nvidia shoud have given the twin cooler to the quadros !!!!! These things give awesome themps.Stupid move to keep it classic.

2.The boxy design and color scheme of new quadros is horrible.Silver , green and black? Honestly, those are visually, the most ugly quadros i have seen.Even the first wave of 5000 and 6000 looked better :(

I hope im not the onlyone thinking like that.

Posted on 2018-08-30 00:43:33

I can't speak to the aesthetics, since that is different for everyone, but I think I know why they didn't go with twin fans on the Quadro. Yes, twin fans do a good job of keeping a single video card cool - but they don't exhaust heat out of the chassis in the same way that a single blower fan does. You might be able to get away with two cards with that sort of cooling, if you leave space between them and have really good chassis airflow... but its not ideal. The Quadro cards are built to be used in systems where 4 or even more of them may be stacked right next to each other, and as such they require cooling that will work properly in such situations.

Posted on 2018-08-30 17:59:29
Niko Nikolov

To tell the truth,these days custom nvidias gpus are not that hot.In my rendering machine i have a twin cooler palit 1080ti and at max load it stays at 55C.(room temp is close to 30>Spain).Still it loud have been nice if they offered separate twin cooled quadros.Maybe call it ¨¨Quadro Air¨¨ it even sounds cool ;) Most people will have one or 2 max in their machines.It looks like a missed opportunity to me.

Posted on 2018-08-30 18:52:34
K_STL

My question, for both you is could ray tracing actually become dev. pushed. In other words, if developing a game, animation, etc...from my understanding if I go the route of ray tracing, I can spend less time working on light and baking i.e. meaning less dev money spent on that because I am off loading that to the RTX.

Posted on 2018-09-19 20:36:11

I honestly don't know enough about how this technology is implemented during game development to say whether it is easier on devs or not. It certainly seems like it would make some lighting and especially reflection stuff easier, since it should be done at run time instead of being baked in, but I am not a game dev myself. Hopefully we'll start to see some commentary from devs as they get their hands on this hardware :)

Posted on 2018-09-19 22:31:15
Turing

https://www.nvidia.com/down...

Nvidia GeForce 411.63 WHQL driver, first driver to support Turing GeForce GPUs.

Posted on 2018-09-19 18:41:17

Yup, looks like the driver has rolled out publicly the day before anyone (outside of the press) was supposed to get hold of them. I keep hearing rumors that widespread availability is going to lag behind NVIDIA's original plans, though... and we haven't gotten any samples here yet, which is odd. Normally we have them a week or so beforehand, giving us time to test and have articles ready when they lift the press embargo. No such luck this time around :(

Posted on 2018-09-19 22:27:06
K_STL

What does it mean for purchasing graphics cards with black friday coming up...stick with 1080 or hold on to the money for a spring RTX card?

Posted on 2018-09-19 20:38:11

I don't think there is any way to say for sure yet, since we are too far from Black Friday to know if there will be wide spread availability on the new RTX cards. If they are in shortage, I wouldn't expect any to go on sale. It will depend on your goals: if you just care about pure rasterization performance (traditional gaming) then the 1000-series is still offering great performance for the price. If you want to future-proof with new technology like the RTX cores for ray tracing in upcoming games, though, I would save up for a new 2000-series card :)

Posted on 2018-09-19 22:29:09