We are just three weeks away from Nvidia’s most awaited RTX 20 series graphics cards shipment. The RTX 20 series graphics card including RTX 2070, RTX 2080 and RTX 2080 Ti will hit the shelves worldwide in three weeks from now.
Older GeForce 10 series pascal graphics cards performance is 40% slower compared to RTX 20 series graphics cards with Turing architecture. Specifically in games where RTX ray tracing and NVIDIA’s brand new AI assisted anti-aliasing tech, DLSS, is not involved. Especially since traditional gaming performance is an area that NVIDIA hadn’t touched on during Turing’s announcement event at Gamescom or since, that is until yesterday.
NVIDIA : RTX 2080 Ti, 2080 & 2070 Are 35-45% Faster vs Pascal Predecessors in Current Games
The company’s venerable tech PR man Tom Petersen went on HotHardware’s Geeks webcast and talked about what everyone has been waiting for NVIDIA to talk about: Turing’s traditional gaming performance versus Pascal.
HotHardware asked Tom about what gamers should expect from an RTX 2080 compared to 1080, but Tom did us on better and talked about how the Turing lineup, in general, will perform compared to Pascal. Stating that gamers should expect roughly between 35-45% better performance is going from Pascal to the same tier Turing graphics card.
“What can gamers expect? Let’s say a gamer has a 1080 now, could they expect a 2080 to be a faster card? Is the experience with current games going to be better?”
NVIDIA Director of Technical Marketing, Tom Petersen:
“That’s a great question I think we could’ve done a little bit better on during the public announcement. Turing is a beast. It’s going to significantly improve the gaming experience on old games and it’s going to rock it when you adopt new technology…”
“We did share some data that showed a bunch of games and you’ll see the perf [performance] roughly somewhere between 35 to 45 percent better at roughly the same generation. So, 1080 Ti to 2080 Ti and of course that’s going to vary based on the game and based on the setting.”
Larger Performance Gap Between RTX 2080 Ti & GTX 1080 Ti vs. RTX 2080 & GTX 1080
RTX 2080 Ti will show a bigger performance advantage compared to the GTX 1080 Ti while the RTX 2080 can deliver better speed versus the GTX 1080. Which makes sense, considering that the CUDA core count delta between the 1080 Ti and the 2080 Ti is considerably larger than that between the 1080 and 2080.
Turing: Great Performance, Steep Pricing
Generally speaking, a ~%40 performance boost from Pascal to Turing is a solid jump up, especially at the top end of the spectrum which is more prone to stagnation due to its higher susceptibility to bottle-necking in addition to the lack of competition from the Radeon side in this area of the market.
Well as the trend is set by a few companies if the product is good enough the price of it would be much higher. Initially, it was expected that the RTX series will be cheaper but now it is in rumors that RTX series will cost double as the cost GTX series cards now.
Performance Per Dollar?
It will be the first generation of the graphics card in history to deliver such performance per dollar compared to its predecessors. If Turing architecture really performs as it is expected to be 35-40%.
Why? Because ray tracing. A feature that the company has announced will make its way to 11 games down the line, but there’s a caveat. Not even the RTX 2080 Ti is fast enough to run it at resolutions higher than 1080p with a 60 FPS average. If you play at 4K or 1440p — and many high-end GeForce owners certainly do — this is obviously a problem. It’s clear then that despite the considerable performance sacrifices and the cost premium associated with Turing, NVIDIA is still banking on ray tracing to sell it.
NVIDIA GeForce RTX 20 Series Graphics Cards Official Specifications
|Graphics Card Name||NVIDIA GeForce RTX 2070||NVIDIA GeForce RTX 2080||NVIDIA GeForce RTX 2080 Ti|
|GPU Architecture||Turing GPU (TU104)||Turing GPU (TU104)||Turing GPU (TU102)|
|Process||12nm NFF||12nm NFF||12nm NFF|
|CUDA Cores||2304 Cores||2944 Cores||4352 Cores|
|GigaRays||6 Giga Rays/s||8 Giga Rays/s||10 Giga Rays/s|
|Cache||4 MB L2 Cache?||4 MB L2 Cache?||6 MB L2 Cache|
|Base Clock||1410 MHz||1515 MHz||1350 MHz|
|Boost Clock||1620 MHz
1710 MHz OC
1800 MHz OC
1635 MHz OC
|Compute||7.5 TFLOPs||10.1 TFLOPs||13.4 TFLOPs|
|Memory||8 GB GDDR6||8 GB GDDR6||11 GB GDDR6|
|Memory Speed||14.00 Gbps||14.00 Gbps||14.00 Gbps|
|Memory Bandwidth||448 GB/s||448 GB/s||616 GB/s|
|Power Connectors||8 Pin||8+8 Pin||8+8 Pin|
|Starting Price||$499 US||$699 US||$999 US|
|Price (Founders Edition)||$599 US||$799 US||$1,199 US|
|Launch||September 2018||September 2018||September 2018|