We're exactly three weeks away from when NVIDIA's highly anticipated Turing RTX 20 series graphics cards are set to hit shelves worldwide and gamers have been very eager to find out how the green team's latest and greatest gaming graphics cards will perform in games compared to existing GeForce 10 series Pascal graphics cards.
Specifically in games where RTX ray tracing and/or 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 a 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 going from Pascal to the same tier Turing graphics card.
HotHardware :
"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."
Transcript by wccftech.com
Expect a Larger Performance Gap Between RTX 2080 Ti & GTX 1080 Ti vs. RTX 2080 & GTX 1080
Earlier this week we broke a story stating that NVIDIA's Turing delivers ~50% better performance versus Pascal. That's what several sources have told us over the past week. Tom's ~40% isn't far off the mark, depending on the games being tested and the cards being compared.
With that being said, we're told to expect that the RTX 2080 Ti will show a bigger performance advantage versus the GTX 1080 Ti in comparison to what the RTX 2080 can deliver 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.
With that being said, it appears that a solid jump up in performance maybe soured by a disproportionately larger jump up in pricing across NVIDIA's Turing lineup, which are priced at very nearly double what their current Pascal predecessors cost. The GeForce RTX 2080 Ti will set you back almost double what a GTX 1080 Ti goes for right now. The situation with the RTX 2080 and the RTX 2070 isn't much better either, both of which are priced at almost twice what the GTX 1080 and the GTX 1070 are going for right now.
Is It Worth It?
If indeed Turing delivers a 35-45% performance improvement over Pascal, this will be the first graphics generation in memory to deliver inferior performance per dollar compared to its predecessor. This is primarily the result of how NVIDIA chose to price the RTX 20 series, which can arguably be seen as excessive from this point of view.
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.
Is it worth it? This is the Turing dilemma.
NVIDIA GeForce RTX/GTX "Turing" Family:
Graphics Card Name | NVIDIA GeForce GTX 1650 | NVIDIA GeForce GTX 1650 D6 | NVIDIA GeForce GTX 1650 | NVIDIA GeForce GTX 1660 | NVIDIA GeForce GTX 1660 SUPER | NVIDIA GeForce GTX 1660 Ti | NVIDIA GeForce RTX 2060 | NVIDIA GeForce RTX 2070 | NVIDIA GeForce RTX 2080 | NVIDIA GeForce RTX 2080 Ti |
---|---|---|---|---|---|---|---|---|---|---|
GPU Architecture | Turing GPU (TU117) | Turing GPU (TU117) | Turing GPU (TU116) | Turing GPU (TU116) | Turing GPU (TU116) | Turing GPU (TU116) | Turing GPU (TU106) | Turing GPU (TU106) | Turing GPU (TU104) | Turing GPU (TU102) |
Process | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN |
Die Size | 200mm2 | 200mm2 | 284mm2 | 284mm2 | 284mm2 | 284mm2 | 445mm2 | 445mm2 | 545mm2 | 754mm2 |
Transistors | 4.7 Billion | 4.7 Billion | 6.6 Billion | 6.6 Billion | 6.6 Billion | 6.6 Billion | 10.6 Billion | 10.6 Billion | 13.6 Billion | 18.6 Billion |
CUDA Cores | 896 Cores | 896 Cores | 1280 Cores | 1408 Cores | 1408 Cores | 1536 Cores | 1920 Cores | 2304 Cores | 2944 Cores | 4352 Cores |
TMUs/ROPs | 56/32 | 56/32 | 80/32 | 88/48 | 88/48 | 96/48 | 120/48 | 144/64 | 192/64 | 288/96 |
GigaRays | N/A | N/A | N/A | N/A | N/A | N/A | 5 Giga Rays/s | 6 Giga Rays/s | 8 Giga Rays/s | 10 Giga Rays/s |
Cache | 1.5 MB L2 Cache | 1.5 MB L2 Cache | 1.5 MB L2 Cache | 1.5 MB L2 Cache | 1.5 MB L2 Cache | 1.5 MB L2 Cache | 4 MB L2 Cache | 4 MB L2 Cache | 4 MB L2 Cache | 6 MB L2 Cache |
Base Clock | 1485 MHz | 1410 MHz | 1530 MHz | 1530 MHz | 1530 MHz | 1500 MHz | 1365 MHz | 1410 MHz | 1515 MHz | 1350 MHz |
Boost Clock | 1665 MHz | 1590 MHz | 1725 MHz | 1785 MHz | 1785 MHz | 1770 MHz | 1680 MHz | 1620 MHz 1710 MHz OC | 1710 MHz 1800 MHz OC | 1545 MHz 1635 MHz OC |
Compute | 3.0 TFLOPs | 3.0 TFLOPs | 4.4 TFLOPs | 5.0 TFLOPs | 5.0 TFLOPs | 5.5 TFLOPs | 6.5 TFLOPs | 7.5 TFLOPs | 10.1 TFLOPs | 13.4 TFLOPs |
Memory | Up To 4 GB GDDR5 | Up To 4 GB GDDR6 | Up To 4 GB GDDR6 | Up To 6 GB GDDR5 | Up To 6 GB GDDR6 | Up To 6 GB GDDR6 | Up To 6 GB GDDR6 | Up To 8 GB GDDR6 | Up To 8 GB GDDR6 | Up To 11 GB GDDR6 |
Memory Speed | 8.00 Gbps | 12.00 Gbps | 12.00 Gbps | 8.00 Gbps | 14.00 Gbps | 12.00 Gbps | 14.00 Gbps | 14.00 Gbps | 14.00 Gbps | 14.00 Gbps |
Memory Interface | 128-bit | 128-bit | 128-bit | 192-bit | 192-bit | 192-bit | 192-bit | 256-bit | 256-bit | 352-bit |
Memory Bandwidth | 128 GB/s | 192 GB/s | 192 GB/s | 192 GB/s | 336 GB/s | 288 GB/s | 336 GB/s | 448 GB/s | 448 GB/s | 616 GB/s |
Power Connectors | N/A | N/A | 6 Pin | 8 Pin | 8 Pin | 8 Pin | 8 Pin | 8 Pin | 8+8 Pin | 8+8 Pin |
TDP | 75W | 75W | 100W | 120W | 125W | 120W | 160W | 185W (Founders) 175W (Reference) | 225W (Founders) 215W (Reference) | 260W (Founders) 250W (Reference) |
Starting Price | $149 US | $149 US | $159 US | $219 US | $229 US | $279 US | $349 US | $499 US | $699 US | $999 US |
Price (Founders Edition) | $149 US | $149 US | $159 US | $219 US | $229 US | $279 US | $349 US | $599 US | $799 US | $1,199 US |
Launch | April 2019 | April 2020 | November 2019 | March 2019 | October 2019 | February 2019 | January 2019 | October 2018 | September 2018 | September 2018 |