Two Nvidia GeForce RTX 2080 graphics cards on a wooden surface

Since launching in 2019, the Nvidia GeForce RTX series of graphics cards are the most powerful consumer GPUs ever made. They add new technologies that generate lighting techniques such as Ray Tracing and DLSS that continue to be refined and enabled the upgrade of Nvidia’s now-classic reference cooler design. But of course: all this has a price.

New generation GPUs are in a higher price order than their predecessors, even considering the typical pricing issues facing buyers around the world for whatever reason. Here is the breakdown of what these cards are and what their scope is.


Two Nvidia GeForce RTX 2080 graphics cards on a wooden surface

The line of desktop graphics cards that Nvidia launched since last year already included the RTX 2060, 2070, 2080, 2080 Ti and Titan RTX models. There are versions available such as Founders Edition with higher clock speeds and a reference cooler design for $ 600, $ 800, $ 1,200, and $ 2,500. Super versions are currently available.

Third-party versions are available – except for the Titan RTX – with all the typical aftermarket features like alternative coolers (including water cooling), overclocks, cosmetic changes, and feature support. Pricing starts at $ 500 and goes beyond Nvidia’s direct purchase options.

Though it’s exclusively high-end graphics cards, Nvidia has attracted the mid-niche market since its announcement at CES 2019. The RTX 2060 went on sale on January 15 for $ 350 and offered the same set of features as its expensive sisters. , with reduced performance capabilities. Still, it wasn’t affordable, but the power it offers at that price made it the most attractive card within the RTX generation.

Nvidia RTX Launch at CES 2019

Nvidia also confirmed partnerships with various companies to use these new mobile GPUs to speed up more than just gaming. We are told that certain 3D modeling, animation, and video editing software will be able to speed up your processes using an Nvidia Turing graphics card or chip.

Performance is high, but not excessively

After Nvidia held onto performance comparisons to Ray Tracing at Gamescom, our own testing of the RTX GPUs showed that the cards were the most powerful ever released, but not nearly as much. They are much better at Ray tracing than their next-gen counterparts, though overall games simply increased the performance spectrum a notch.

There is no denying that the 2080 is more powerful than the 1080, and the 2080 Ti more powerful than the 1080 Ti, but that is far from the whole story. The 2080 lags behind the 1080 Ti in some tests, perhaps most notably in our ultra 4K gaming test.

READ Also  Top 50 Movies on Amazon Prime Video (June 2020)
Turing architecture on Nvidia GeForceRTX

The price of the new cards was initially problematic after launch, as their relative performance counterparts in the previous generation were often available at lower prices.

Ultimately, the 2080 and 2080 Ti are 20 to 30 percent faster than their newer, next-generation counterparts in the harshest scenarios, but in many tests that gap may be as small as percentage points of a single digit, so performance improvements depend on the software running.

The same goes for the Titan RTX, a slightly more capable RTX 2080 Ti, it has proven to be more powerful than even the monstrous Titan V in many environments, although it will probably be reserved almost exclusively for rendering and business tasks.

The RTX 2060 is a bit more impressive in that it is similar to a GTX 1070 than a replacement for GTX 1060, but its performance is still not astonishing. Especially when you start playing with advanced features like Ray Tracing.

He benchmark Nvidia’s RTX 2060, showed at its launch in 2019, that it beat a GTX 1070 Ti in some games, but those results were a bit false. They paired the RTX 2060 with a $ 1,000 Intel 7900X CPU, which is far from a likely scenario in the type of midrange gaming systems the RTX 2060 is targeting.

Titan RTX RTX 2080 Ti RTX 2080 RTX 2070 RTX 2060 GTX 1080 Ti
GTX 1080 GTX 1070
CUDA cores: 4,608 4,352 2,944 2,304 1,920 3,584 2,560 1,920
Base Clock: 1,350 MHz 1,350 MHz 1,515 MHz 1,410 MHz 1,365 MHz 1,480 MHz 1,607 MHz 1.506 MHz
Max Clock: 1,770 MHz 1,545 MHz 1,710 MHz 1,620 MHz 1,680 MHz 1,582 MHz 1,733 MHz 1,683 MHz
Vel. Memory: 14 Gbps 14 Gbps 14 Gbps 14 Gbps 14 Gbps 11 Gbps 10 Gbps 8 Gbps
Memory interface: 384 bit 352 bit 256 bit 256 bit 192 bit 352 bit 256 bit 256 bit
Memory bandwidth: 672 GBs 616 GBs 448 GBs 448 GBs 336 GBs 484 GBs 352 GBs 256 GBs
TDP: 280 W 250 W 215 W 185 W 160 W 250 W 180 W 150 W

There are some interesting intergenerational changes at play with the RTX Turing generation. CUDA cores have increased in similar types of numbers, though not percentages, between the 900 series and 1000 series graphics cards, so we see a noticeable, if not significant, increase in overall performance.

The clock speed has dropped, which is not entirely surprising, but when displayed alongside an increase in power consumption, it is slightly more so. It could be that those RT and Tensor cores require some juice of their own.

GDDR6 memory provides a solid boost in speed and bandwidth for the 20 series, making both the 2080 and 2070 almost in line with the GTX 1080 Ti, though not entirely.

We now know that whether the 2080 can compete with the 1080 Ti really depends on what software is running and with what configuration. The 1080 Ti will be left behind when the Ray tracing it’s on, but in traditional lighting scenarios, it should be competitive, if not even more powerful than the RTX 2080.

Ray tracing and DLSS

While the number of traditional CUDA cores in new graphics cards has increased across the board, the most exciting achievement of this new generation we are told is the addition of dedicated hardware for Ray Tracing and the IA, artificial intelligence.

The Turing architecture includes RT cores that use clever tricks to speed up Ray Tracing and make it possible to produce realistic lighting and reflections within games.

These new technologies at the heart of the Series 20 architecture mean that certain games will be able to take advantage of real-time reflections and advanced smoothing techniques like never before.

It is a beautiful, but expensive technology. The first tests showed that the Ray tracingOn the most powerful cards, it could only be rendered effectively at 1080p and 1440p at playable frame rates. Even after optimization patches.

Arguably the most intriguing technology these cards make possible is Deep Learning Super Sampling, or DLSS, enabled by the Tensor RTX series cores.

They effectively use artificial intelligence on cards to simulate higher resolution rendering without the performance overhead. It is not perfect and the list of games is still small, but there is a lot to be excited about DLSS. If you see wider use, that’s why.

Ports, noise and cooling

While the hardware inside the 20 series cards changed, the exterior also received a major overhaul. After decades of a single fan, Nvidia added a second to its design. This creates a higher air volume configuration, no doubt to ensure that temperatures remain consistent with the higher power requirements of the 20 series RTX graphics.

And the result was cooler, quieter cards, but that’s not always the full story.

At the back end, where you connect your display, the 20 series offers some port options. Along with the more typical DisplayPort 1.4 and HDMI 2.0b connectors, there is also a VirtualLink; a USB-C shaped port, designed to provide power and video to virtual reality headsets, which means a reduction in the number and size of cables, even for VR.

Is performance worth it?

As exciting as all of the above features and spec enhancements are, they should be taken in the context of cost. The 20 series RTX cards are the most expensive new Nvidia GPUs that have been released in a long time and with quite a margin.

The RTX 2080 Ti had a cost of $ 1,200 dollars for the Founders Edition and no less than $ 1,000 for a third-party version. The 2080 came out at a price of $ 800 and $ 700 respectively, while the 2070 is $ 600 and $ 500, at least. The latest RTX 2060, meanwhile, cost $ 349 at launch.

That is too much money, even for high-end cards. The 2060 is much better value for money, and if you’re looking for the 1070 Ti or 2070 as possible upgrade options, it’s not far from its capabilities and more affordable. However, it’s still not a cheap card, and budget-conscious gamers are likely to be on the lookout for something that will be a replacement for the GTX 1060 in the near future.

We would expect similar or even higher price jumps in the mobile space. While Ray Tracing on a small laptop screen may look great in certain settings, we are skeptical about the visual enhancement you get in titles in general. Gaming laptops also sell for a higher price, so with RTX hardware, it would tend to increase.

Developers are unlikely to largely adopt Ray Tracing until there is a large enough quantity of RTX-compatible cards. It may catch up for years to come, but it will be some time before most players can support it.

Editor’s recommendations


Please enter your comment!
Please enter your name here