Nvidia Turing: All you need to know about the GTX 2080
Nvidia has announced its first Turing GPUs at the Siggraph 2018 conference, the Quadro RTX range, which will offer professional users a massive step up in performance. Unfortunately, we’ve got a little longer to wait until we can get our hands on the gaming graphics cards based on this tech, as the Quadro range is targeted exclusively at professional users.
If that’s you, then the new cards are offering some exciting improvements. Boasting processor cores dedicated to handling a number of discrete processes like ray tracing and AI processes, Nvidia says that the Turing GPUs can simulate physical worlds at six times the speed of previous Pascal-based GPUs.
In simple terms, this means that bigger and more complicated environments can be rendered far more quickly.
“Turing is Nvidia’s most important innovation in computer graphics in more than a decade,” said Jensen Huang, founder and CEO of Nvidia.
“Hybrid rendering will change the industry, opening up amazing possibilities that enhance our lives with more beautiful designs, richer entertainment and more interactive experiences. The arrival of real-time ray tracing is the Holy Grail of our industry.”
The big takeaway is ‘real time ray tracing,’ a feature of the Nvidia Quadro RTX 8000, which represents the high end of the range.
Ray tracing is a term for when a program attempts to recreate real world lighting effects by having pixels trace the path of light. It’s an impressive visual trick, and one that’s very taxing on a system’s memory, but with Turing, Nvidia reckons they’ve cracked it, thanks to the ray tracing and AI cores of the Quadro RTX 8000 working in tandem – this is likely what Huang means when he says ‘hybrid rendering’.
Compared to Pascal GPUs, Nvidia says, Turing graphics cards can simulate convincing physical environments at six times the speed.
Related: Best graphics cards
Nvidia Turing GPUs: Prices and release dates
The Turing-based Quadro range — the Quadro RTX 5000, 6000, and 8000 — are expected to go on sale during Q4 of this year, but a solid date’s not been given. Here’s a brief run down of what you can expect to pay for cards, based on US prices. Note that conversions are based on exchange rates that were correct at the time of writing, but don’t necessarily reflect the actual UK RRP.
- Quadro RTX 5000: $2300 (£1800)
- Quadro RTX 6000: $6,300 (£4390)
- Quadro RTX 8000: $10,000 (£7828)
However, as we mentioned above, even if you can afford to stump up two to eight grand, you shouldn’t bother getting one for your gaming PC.
Why? For gaming, these will be overkill. While real-time ray tracing sounds incredible, conjuring visions of us being able to step into photorealistic worlds, these are GPUs intended for workstations that’ll be handling things like post production video effects and CAD (Computer Assisted Design). The kind of people interested in picking up these will be the kind of people who want a high-end Intel 9th Gen and Threadripper 2s, which, in the words of AMD’s own James Prior, you don’t need for playing games.
So where are the graphics cards for gamers?
Nvidia’s 2080 Gamescom reveals
While players might be dismayed that there’s no reveal of game-centric GPUs from Nvidia right now, the company posted this teaser on YouTube, which as Videocardz points out, is crammed with cryptic (and some not so cryptic) hints about what’s in store for us at Gamescom next week.
The video shows friends with Discord handles like ‘RoyTeX’, ‘Zenith 20’ and ‘Eight Tee’ chatting away. Someone going by the handle of ‘Not_11’ also says ‘Gimme 20’.
Added up, all of this might be a reference to Nvidia jettisoning the expected GTX 1180 name in favour of GTX 2080.
There’s also a handle in there named ‘Ray’. This may or may not be a coded reference to some of that enhanced ray tracing goodness coming to gamer-level cards, or it might not.
In one of the chats, a grid reference for somewhere in Cologne, Germany are posted, but if you enter these into Google Maps, you’ll see that it’s actually somewhere a little north of the Koelnmesse, Gamescom’s main venue…
We’ll know for sure next week, as we’ll be reporting from the showroom floor at Gamescom 2018.
Nvidia Turing specs
This is where things get both technical and woolly, because while we know what the professional cards are packing, we don’t yet have a decent idea of what exactly will be making its way into the gaming cards. Instead, we have to rely on the rumour mill, which has been dutifully spinning away over the past few months.
Several reports, including a report from Tom’s Hardware, have suggested that Nvidia’s Turing cards will be packing the same RTX technology that Nvidia’s packed into its professional cards. Given what Nvidia teased in the trailer above, this now seems pretty likely.
There are also rumours that the new generation of Nvidia Turing GPUs should also have significantly higher clock-speeds in excess of 2GHz. A fourth generation of GPU Boost is rumoured to allow clocks to be pushed ever higher under the right cooling conditions.
Finally, the recent report also suggested Nvidia Turing will be making use of the upgraded HDMI 2.1 standard. There are a number of new improvements expected with the standard, chief amongst them being that it will finally support 4K content at over 60Hz (up to a maximum of 120Hz).
However, perhaps more interesting is HDMI 2.1’s introduction of Variable Refresh Rate. Nvidia’s GPUs already support their own version of the technology called G-Sync, but at the moment this is a proprietary technology that only works over the DisplayPort connector. HDMI 2.1 support would in theory mean that variable refresh rates would also work over more common HDMI connections, and wouldn’t require users to pay a premium for an expensive G-Sync monitor.
Recently leaked photographs of what appears to be an Nvidia Turing engineering sample suggest that the cards will join their Quadro siblings in using the next-generation GDDR6 VRAM, which should allow for higher clock-speeds and more memory bandwidth.
Another engineering sample contained signs that the 1180 could be powered by an 8+6pin power connector.
There’s a lot of potential tech under the hood, but if you want exact specifications we have to turn to the TechPowerUp GPU database which recently saw some additions that claim to show what the successor to the GTX 1080, the Nvidia Turing GTX 2080, will be capable of.
According to these specs, the 2080 will have 3584 CUDA cores (a 40% increase over the GTX 1080), 224 TMUs (another 40% increase) and 16GB of GDDR6 RAM (a 100% increase).
Overall, this means the new card will have 13 teraflops (tflops) of computing power, which not only faster than the 1080’s 8.7 tflops, but is even faster than the Titan Xp’s 12.
The specs also suggest that the new card will be based on a 12nm fabrication process, rather than the smaller 10nm fabrication process that was originally rumoured.
The smaller the process size, the more transistors (the yes/no gates that do all the work) you can fit on a piece of silicon, which means you effectively get more powerful components without using more energy. We warned you this would be technical.
By way of comparison, 10nm is the same process size Intel’s rumoured to be using for its Cannon Lake processors.
Check out how all the specs compare in the table below:
|GTX 1080||GTX 2080||Increase|
|RAM||8GB (GDDR5)||16GB (GDDR6)||100%|
|FP32||8.7 TFLOPs||13 TFLOPs||49%|
We’re going to keep this article updated as new rumours arrive, so bookmark this page and stay tuned to Trusted Reviews.