Nvidia has launched a trio of new GPUs in its higher-end product families, replacing or augmenting the existing RTX 2060, 2070, and 2080 with a new family of “Super” cards: the RTX 2060 Super, RTX 2070 Super, and (upcoming) RTX 2080 Super. These new cards are still built on the same 12nm process and carry the same features and capabilities as their predecessors. What they offer is substantially improved performance at the same MSRP as the cards they replace. The RTX 2060S and RTX 2070S are what Nvidia should have launched last year. The RTX 2080S won’t actually be out for review until July 23.
This chart shows the distribution of improvements and upgrades across the cards. The RTX 2060 Super is, for all intents and purposes, an RTX 2070. The RTX 2070S is, based on reviews, offering about 96 percent of the performance of an RTX 2080. These new GPUs drop in at the same prices that their earlier selves occupied, which means Nvidia has effectively reversed some of the price increases they inflicted on the market in the first place when they launched the Turing family.
The straight-line performance increase for the RTX 2060S and 2070S over the original RTX 2060 and 2070 appears to be between 1.1x – 1.2x, with the average in both cases falling around 1.15x. These GPUs are generally about 15 percent faster than their predecessors at the same price. The market has repaid Nvidia with low adoption rates. As we’ve previously covered, the Turing adoption rate has been markedly slower than Pascal at every price point and product level we could reasonably compare, virtually across the board. This remains true today. Nine months after launch, the most-adopted RTX GPU is the RTX 2070, with 1.1 percent of the market.
In February 2017 (the equivalent comparison point), the GTX 1060 held 4.08 percent of the market, followed by the GTX 1070 (3 percent), and the 1080 (1.41 percent). The 1050 Ti had another 1.04 percent, and the 1050, 0.52 percent. The top 5 Pascal cards accounted for 10.05 percent of the market.
Comparing with Turing today, we see very different figures. The RTX 2070 is the most-adopted card, at 1.1 percent. The RTX 2060 follows, at 0.85 percent, RTX 2080 (0.75 percent), RTX 2080 Ti (0.42 percent), and GTX 1660 Ti (0.4 percent). The top 5 Turing cards collectively hold 3.43 percent of the market.
According to Chris Stobing at PCMag, the RTX 2070 Super “earns our Editors’ Choice as the $ 499 high-end card that the GeForce RTX 2080 should have been. Its stellar performance at its price makes up for the wait—and makes it without peer.”
There have been some design changes to accommodate the increased performance; the RTX 2070S now has an 8-pin + 6-pin connection rather than a single 8-pin, and TDPs have increased in some cases to deal with the increased power consumption. The RTX 2070S uses the same GPU as the RTX 2080/2080S (a reversion to the previous norm), while the RTX 2060S is based on an expanded version of the same TU106 core that it previously used.
Rise of the Tomb Raider shows the RTX 2070 and RTX 2070S more-or-less tying at 1080p, but the faster GPU sharply distinguishes itself at higher resolutions. The gains here are significant enough to represent a reset for Nvidia’s overall product stack. The RTX 2070S is effectively an RTX 2080, for $ 500 instead of $ 700. The RTX 2060S is an RTX 2070 at $ 400 instead of $ 500. When the RTX 2080S arrives, it’ll presumably improve on the RTX 2080 by 8-10 percent as well given the boost to its overall specs.
This is what Nvidia should have launched last September. It’s a significant enough price improvement to change the overall value proposition of the cards. We’ll be revisiting the question of ray tracing support and the overall value these cards offer against AMD’s upcoming GPUs in weeks to come, but one thing is clear: AMD probably needs to tweak its own launch pricing.
I know people are leery of trusting manufacturer benchmarks, but in this case, we want to see AMD’s project best-foot-forward, and we can assume the company gave it to us. Previously, ignoring 22 percent and 15 percent outliers, AMD projected that the 5700XT would be 2.6 percent faster than the RTX 2070, but cost $ 50 less at $ 449. Even if you include the outliers, the 5700XT leads the RTX 2070 by just 5.8 percent. The RTX 2070S appears to offer a consistent ~1.15x improvement over the RTX 2070.
The straight-line comparison suggests the 2070S will be a hard point for the 5700XT to match. The RX 5700 is in a slightly different position.
The RX 5700 was an average of 8.8 percent faster than RTX 2060 if we toss the 22 percent outlier and 10 percent faster if we don’t. The fact that this GPU also picks up a price increase makes it an easier comparison point for AMD. With the 5700 tagged at $ 379 and the 2060S hitting $ 400, the fact that Nvidia also gains roughly 1.15x performance for this card gives AMD a little more breathing room.
AMD may or may not respond with price adjustments before launch, but the 2070S looks like stiffer competition. And these new Turing cards are a noticeable improvement on previous models. All of this sets up a very interesting comparison coming in just a few more days.