NVIDIA has come out to play with three new graphics cards, the GeForce RTX 30 Series.
The series forms the second generation of RTX, which introduced real-time ray tracing and includes the RTX 3070, RTX 3080, and RTX 3090. The GeForce RTX 30 series completely overtakes the previous GeForce lineup.
“This is our greatest generational leap ever,” proclaimed NVIDIA CEO Jensen Huang. Huang tends to make strong statements with every release—he first introduced RTX as “the holy grail of computer graphics”—but that doesn’t mean he’s hyperbolizing. Here’s what he means by “greatest generational leap”:
The new GeForce RTX 3070 and 3080 are both more performant than the previous top gun, the GeForce RTX 2080 Ti, and you’ll notice that both are also significantly less expensive. You’ll also observe that the RTX 3090 is missing from the chart. That’s because it’s off it on both axes (more on that in a sec).
The GeForce RTX cards are the first consumer cards to use NVIDIA’s new Ampere architecture, which the company unveiled back in May with the A100 GPU for datacenters. Ampere added an array of improvements, including second-gen RT Cores (for ray tracing), third-gen Tensor Cores (for machine learning), faster GDDR6X graphics memory, and more. The new GeForce GPUs are also manufactured with a custom Samsung 8nm process, rather than the previous generation’s 12nm TSMC process.
Because of all that, NVIDIA is promising that the RTX 30 Series will provide up to 2x the performance and 1.9x the power efficiency of the previous Turing-based cards. Here are the new specs:
Let’s home in on that RTX 3090, a beastly card that Huang referred to as the BFGPU—the Big Ferocious GPU. NVIDIA claims it’s up to 50 percent faster than the Titan RTX, the current king of NVIDIA’s consumer lineup, which it will also replace (the Titan series is no more).
Read more at ENGINEERING.com