December 25, 2024

So after a full 4 to 5 months of pure speculations of the GeForce 20 series has been finally announced at Gamescom. Unlike previous launches, however, Nvidia is launching all their High-end parts together. The RTX family is made up of the Quadro series at the top and then the 2080Ti, 2080 and finally 2070. So what has changed, what are the pricing and what is the performance like? Good Questions let’s find out.

So first up why RTX instead of the GTX? Well because of Ray Tracing. A Graphics technique that Nvidia is touting as the biggest visual jump we have seen since the jump from 2D to 3D. What is ray tracing you might ask? It’s a much more advanced and lifelike way of rendering light and shadows in a scene. It’s what movies and TV shows use to create and blend in amazing CG work with real-life scenes. The drawback is ray tracing often requires extensive server farms to pre-render graphics. That’s been too much to ask from a real-time, interactive video game running on a compact box in your home.

Nvidia claims that a fully unlocked Turing GPU is faster at Ray Tracing than 4 Tesla V100 running together. Mighty impressive stuff. They also said that it’s faster than the Titan Xp by about 10 times in ray tracing.

All three cards will be launching over the next two months. First off will be the RTX 2080 Ti and RTX 2080, which will launch on September 20th. The RTX 2080 Ti will start at $999 for partner cards, while the RTX 2080 will start at $699. Meanwhile, the RTX 2070 will launch at some point in October, with partner cards starting at $499. On a historical basis, all of these prices are higher than the last generation by anywhere between $120 and $300. Meanwhile, NVIDIA’s own reference-quality Founders Edition cards are once again back, and those will carry a $100 to $200 premium over the baseline pricing. So taking all that into account we have twice the asking price for the Ti, 200 dollars more for the 80 and 200 more for the 70. Expensive stuff to say the least.

NVIDIA GeForce Specification Comparison
RTX 2080 Ti RTX 2080 RTX 2070 GTX 1080
CUDA Cores 4352 2944 2304 2560
Core Clock 1350MHz 1515MHz 1410MHz 1607MHz
Boost Clock 1545MHz 1710MHz 1620MHz 1733MHz
Memory Clock 14Gbps GDDR6 14Gbps GDDR6 14Gbps GDDR6 10Gbps GDDR5X
Memory Bus Width 352-bit 256-bit 256-bit 256-bit
VRAM 11GB 8GB 8GB 8GB
Single Precision Perf. 13.4 TFLOPs 10.1 TFLOPs 7.5 TFLOPs 8.9 TFLOPs
Tensor Perf. 440T OPs
(INT4)
? ? N/A
Ray Perf. 10 GRays/s 8 GRays/s 6 GRays/s N/A
“RTX-OPS” 78T 60T 45T N/A
TDP 250W 215W 175W 180W
GPU Big Turing Unnamed Turing Unnamed Turing GP104
Transistor Count 18.6B ? ? 7.2B
Architecture Turing Turing Turing Pascal
Manufacturing Process TSMC 12nm “FFN” TSMC 12nm “FFN” TSMC 12nm “FFN” TSMC 16nm
Launch Date 09/20/2018 09/20/2018 10/2018 05/27/2016
Launch Price MSRP: $999
Founders $1199
MSRP: $699
Founders $799
MSRP: $499
Founders $599
MSRP: $599
Founders $699

 

So that’s well and good, the 2080Ti is at least 10 times more powerful than the 1080Ti and is priced just twice as costly. Good price to performance, right? Wrong. Nvidia never showed actual FPS in of their demos, other than an Unreal Engine 4 game which I had never heard of and supposedly a GTX 1080Ti can run it at 40 fps while possibly the 2080Ti can run it at 60fps.

For the whole demo, Jensen only talked about Gigarays and Tensor performance. And the visual changes such as soft shadows, real-life reflections and better volumetric lighting. This is where I got concerned. Previously if you have watched either the 900 series launch or the 10 series launch, Jensen would pit the 80 part with the last gen Ti or Titan and show how powerful the new card was at a lesser price point. This time however it was straight up 2080Ti and no FPS numbers. When Nvidia Turned on RTX in the Shadow of the Tomb Raider demo, visibly you could see a difference but if you noticed that Demo carefully the FPS seemed to take a noticeable hit. This is leading me to believe that even with these new cards RTX is too demanding to enjoy a full 60 fps at the desired Resolutions right now.

What is even more surprising to me is that Nvidia released the Ti with the 80 card. Why is that? Now you as a consumer might thing well because they care about their customer base and wants to give them the best. That may be true. The Titan release has always been a bait for people foolish enough to fall for it, but since Nvidia is a profit-oriented company we have to look at it from a profit standpoint as well. What if 2080 was simply not a great deal faster than 1080Ti? That would explain 2 very important changes Nvidia made to their presentation this year, First is not showing direct FPS numbers and Second why they are releasing a Ti at the same time as the 80. Plus from the Price point, they are now not baiting people to pay 1200 Dollars for the 699 dollar performance, they are demanding it from day 1.

So what is pricing back home in India? Well, the good news is it’s in pre-order now, the bad news is its overpriced above the already hiked price. A single Zotac Reference Design 2080Ti will set you back by 1,00,000 Rs. That’s about a 35k increase over the 1080Ti. It’s a similar story for 2080 which is 20 to 25k more expensive than  1080.

So what do I make of all these info? Well, the technology is interesting, to say the least. Computer graphics has been stuck pretty much since the days of Far Cry made my Crytech, only with fine refinements along the way. Ray Tracing could surely push the nextgen graphics forward, but is it worth the price? Hmm, that is something I can’t really give a definite answer right now since we have no FPS numbers and these Gigaray stuff means nothing to me as these are not even present in previous gen cards. We don’t know how widespread the use of this RTX will be ( remember PhysX? ). Also with 7nm so close and the Ti releasing so early pretty sure Nvidia won’t make this a 2year Generation. Either way, you should not pre-order even if you want these cards Day 1.