NVIDIA RTX 3080 FOUNDERS EDITION REVIEW
Nvidia RTX 3080 specs
The key specs, most especially when it comes to gaming, are those heavily beefed up CUDA core numbers. We're seeing effectively twice the number of cores compared to what we were expecting, and far more than the equivalent GPU of the previous Turing generation. That's down to the redesigned data paths Nvidia has fitted into the GA102 silicon at the heart of the RTX 3080.
The full GA102 GPU, the same essential chip which powers both the RTX 3080 and the upcoming RTX 3090, houses 10,752 CUDA cores. The cut-down version dropped into the RTX 3080, however, sports 8,704. That is still a huge increase over the paltry 3,072 CUDA cores Nvidia released the RTX 2080 Super with just last year. Although that kinda depends on your definition of a 'core'.
These cores are arrayed across 68 streaming multiprocessors (SMs), which means that you get a few more of the dedicated 2nd gen RT Cores too. Because of the way the new architecture is designed, however, you do get fewer AI-driving Tensor Cores.
The RTX 3080 GPU is built on the Samsung 8N design, which is nominally an 8nm production node, with a die size of 628.4mm2. That's smaller than the top Turing chip, which was 754mm2, but packs in another 10 billion transistors at 28.3 billion transistors. It is though a larger slice of silicon than the TU104 which powered the equivalent level card of the last generation, the RTX 2080.
A side-by-side look at the Boost clock speed of the RTX 3080 compared with the RTX 2080 Super might have you worrying for the performance of the GPU as it rated slower, but in our testing we've clock speeds well north of 1,800MHz as standard—at a similar level to the last-gen Turing card.
You do get faster memory too, with 10GB of GDDR6X memory, running across an aggregated 320-bit memory interface. That delivers a pretty spectacular 760GB/s of bandwidth compared with the sub-500GB/s of the standard GDDR6 of the Turing card.
But you are definitely going to need some serious PSU performance for your new card, because this Founders Edition has a board power rating of 320W, and we've seen this version of the RTX 3080 running well above that on average, with peaks up to 368W in demanding games.
Nominally Nvidia is suggesting a 750W PSU as a minimum, but that's not really taking into account the higher power draws of some modern CPUs. If you're rocking a Core i9 10900K, for example, you'll likely need 850W at least.
Testing Results: Recent AAA Games
The following benchmarks are games that you can play. We typically used in each case the highest in-game preset and, if available, DirectX 12. As mentioned, we've got a host of AAA titles in here; multiplayer-focused and esports titles are in another chart further down.
Across every test we ran, the Nvidia GeForce RTX 3080 Founders Edition proves itself as the premium GPU of a new 4K gaming era. While gains in both 1080p and 1440p resolutions were substantial, the real meat of the RTX 3080's gaming-benchmark dominance becomes apparent once you take a look at 4K numbers.
In games like F1 2020, the RTX 3080 Founders Edition saw results that were up to 70 percent faster than the previous-generation card it's replacing (the RTX 2080 Founders Edition) and still manages to beat out both the GeForce RTX 2080 Ti and the GeForce RTX 2080 Super by a substantial margin.
For a possible look at the future of gaming, you'll want to pay special attention to the chart for Death Stranding. This is because, like Shadow of the Tomb Raider and Call of Duty: Modern Warfare, it's one of the few titles out there that integrates DLSS directly into the engine of the game. This means it can achieve serious performance gains over results we'd see with the feature turned off, and it represents the potential for DLSS 2.0 (and hopefully, 3.0), as the upscaling method continues to evolve.
So, how did those "third generation" Tensor cores pay off? On the GeForce RTX 2080 Ti, Death Stranding hits an impressive 121fps with DLSS turned on to Performance mode, but the RTX 3080 just has that little bit of extra juice to carry it through, posting a finish of 148fps (which is just crazy when you remember this is all happening at 4K resolution). This result makes it the first single-card solution we've seen that finally lives up to the (possibly premature) expectations set by 4K 144Hz monitors like the Editors' Choice Acer Predator XB3, succeeding where even dual GeForce RTX 2080s strung together in NVLink have previously struggled to keep up.
Going through the rest of the AAA gaming results, it's clear that the GeForce RTX 3080 is a card that makes a statement and has the horsepower to back it up: 4K gaming isn't just here, it's here and then some. With that in mind, the percentage gains in both 1080p and 1440p aren't as substantial as the ones in 4K. That makes sense when you consider that 4K performance is usually highly GPU-dependent, while lower resolutions are generally some combination of CPU- and GPU-dependent depending on the engine and how the game itself has specifically been optimized.
For example, while the difference between 4K results in Total War: Warhammer II represented a gain of more than 35 percent between the GeForce RTX 2080 Ti and the RTX 3080, it translated to just a 3 percent lift once we dialed the game resolution down to 1080p. This wasn't always the case, though. In Red Dead Redemption 2, the 1080p and 1440p results saw gains of roughly 20 percent each, while 4K results were around 30 percent faster.