Review
Although a number of manufacturers produce their own variants of the GeForce RTX 2080 Ti, for the purposes of this review, I used one of Nvidia’s own Founders Edition cards. Unfortunately, I haven’t been able to test Nvidia’s low-end or mid-range GeForce RTX cards, the GeForce RTX 2060 and 2070 and their Super variants. However, I have included a popular synthetic benchmark, 3DMark, as part of my tests, so you should be able to get some idea of how they would have performed by comparing my results to the other 3DMark scores available online. Nvidia’s RTX 2080 Super is a very mild upgrade from the previous card, but at least it’s not more expensive. This is a bit of a disappointment, especially if you thought the 2080 Super was going to be a reborn 4K beast of a GPU or that it would be a lot closer to the RTX 2080 Ti. Of course, the RTX 2080 Ti is still way out in front, as expected given its $500 price difference.
Nvidia’s new high-end graphics cards are the GeForce RTX 2070, RTX 2080 and RTX 2080 Ti, the company announced today during a pre-Gamescom 2018 livestream from Cologne, Germany. This means that a solution based on a 384-bit interface and surrounded by 12 DRAM dies could feature up to 24 GB of VRAM while a 256-bit solution can house up to 16 GB of VRAM. While VRAM is one thing, the maximum bandwidth output on a 384-bit card can reach a blistering fast 672 GB/s while the 256-bit solution can reach a stunning 448 GB/s transfer rate on existing 14 Gbps dies which are in full production.
I’ll be testing a couple of these over the next few weeks to see how they compare, but the figures below should still give you a pretty good idea of what to expect in terms of raw performance increase. The point of saying all of this is that a strict Pascal vs. Turing core comparison needs to account for architectural differences that could change how well a “core” performs to begin with. In reviewing “Founders Editions” of the RTX 2080 ($799) and RTX 2080 Ti ($1,199), I ran the usual gamut of benchmarks, and I did the usual double-checks of various games. But all the while, I turned Nvidia’s sales pitch over and over in my mind—because that’s more or less all I could do with the sales pitch.
But that’s just the tip of the iceberg, the performance metrics don’t stop at the 1080 Ti. The GeForce RTX 2080 is just stunning amounts of performance for gamers for a really unbeatable price point considering where we were with the last generation of GPUs. New Turing shader architecture with Variable Rate Shading allows shaders to focus processing power on areas of rich detail, boosting overall performance. Test scores and system configurations are below, and we’ll update these with new gaming laptops as we test them.
The only problem is that, for Core i5 PC owners at least, the GTX 1080Ti offers a near identical experience for less money. To help answer those questions, I’ve got the Founders Edition of Nvidia’s gigabyte gtx 1060 3gb (to see what its beefy big brother’s like, have a read of my Nvidia GeForce RTX 2080Ti review instead). For those of you who like numbers out there, the next two paragraphs are for you. Like all RTX 2080 cards you’ll be able to buy soon, you’ll find 8GB of GDDR6 memory here that can deliver a massive 448GB/s of memory bandwidth, as well as 2944 CUDA cores and a base clock speed of 1515MHz. Where this card differs from the reference spec is its boost clock speed, which has been raised from 1710MHz to 1800MHz. NVIDIA announced its new Turing video cards for gaming today, including the RTX 2080 Ti, RTX 2080, and RTX 2070.
Nvidia’s Nsight Visual Studio Edition application is used to inspect the state of the GPUs. Nvidia Titan RTXAPI supportDirect3DDirect3D 12.0 OpenCLOpenCL 3.0OpenGLOpenGL 4.6VulkanVulkan 1.2HistoryPredecessorGeForce 10 seriesVariantGeForce 16 seriesSuccessorGeForce 30 seriesThe GeForce 20 series is a family of graphics processing units developed by Nvidia. Serving as the successor to the GeForce 10 series, the line started shipping on September 20, 2018, and after several editions, on July 2, 2019, the GeForce RTX Super line of cards was announced.
The RTX 2080 Ti is untouched, for now, and remains at the top of Nvidia’s product stack at $1,200 with the 2080 Super slotting in below it for $500 less. Despite matching the previous flagship in performance – a card that saw my test system draw around 403W under load, the RTX 3070 managed the same performance at just 343W. This makes it the ideal partner for small form factor systems too, where undervolting might yield far lower power draw and temperatures than the RTX 2080 Ti. Meanwhile, DLSS is artificial intelligence that actively adjusts the resolution in a game to maximize frame rates in areas where resolution isn’t as important and to maximize resolution when the scene calls for it. For example, if you’re sprinting in a first-person shooter, you don’t need high resolution for a hazy scene, but if you’re stopped in the middle of a vibrant forest, the higher resolution will be utilized.
In 2016, NVIDIA announced their Pascal GPUs which would be featured in their top to bottom GeForce lineup. After the launch of Maxwell, NVIDIA gained a lot of experience in the efficiency department which they put a focus on since their Kepler GPUs. Now, with an enhanced FinFET process available, NVIDIA is taking the efficiency lead beyond where it was previously, is completely gtx 1090 unrivaled by the competition. With Volta, NVIDIA focused on the AI and HPC market but most of the features that Volta supported aren’t necessarily needed in the gaming department. That’s where Turing comes in, a GPU designed solely for the consumer segment. If a GPU doesn’t have enough graphics memory for a computational task, it has to send data out to system RAM.
For those who like to know what difference is between GDDR5 and GDDR56, we know from the official specifications published by JEDEC both memory standards are not a whole lot different from each other but they aren’t the same thing either. The GDDR6 solution is built upon the DNA of GDDR5X and has been updated to deliver twice the data rate and denser die capacities. Hardware support for USB Type-C™ andVirtualLink™, a new open industry standard being developed to meet the power, display and bandwidth demands of next-generation VR headsets through a single USB-C™ connector. New memory system featuring ultra-fast GDDR6 with over 600GB/s of memory bandwidth for high-speed, high-resolution gaming.