This site may earn affiliate commissions from the links on this page. Terms of use.

After weeks of leaks, Nvidia is finally formally launching its next-generation GPU family. As expected, the new cards are strongly focused on ray tracing, which the company claims the new GPUs are stunningly positioned to deliver.

Much of the company's demonstrations and product capability give-and-take revolve around the use of real-time ray tracing in consumer graphics for the very first time. The GTX 1080 Ti, for example, is capable of calculating 1.21 gigarays per 2nd, while Turing is capable of 10 gigarays at the same time. At one indicate, Nvidia claimed that a unmarried Turing-class GPU will deliver higher ray tracing performance than 4 DGX Voltas. When tasked with the same workload, Pascal GPUs take 308ms to run, a quad of Volta finishes in 55ms, and one Turing-course GPU can finish in only 45ms. That's still not a playable frame rate, just it's being used to render a photo-realistic Star Wars scene as opposed to a shipping championship.

The full-fat version of Turing (it's non clear which GPU this specifically refers to) is capable of 14 TFLOPS of FP32, 110 FP16 tensor FLOPS (that's the half-precision mode) and 78T RTX-OPS. That last metric isn't actually a metric at all since we don't actually know what an RTX-OP is, exactly, simply presumably, that kind of information will be fleshed out at a later engagement. The current Titan X, in contrast, is capable of 12 RTX-OPS.

Nvidia has worked on developing Turing and its ray tracing capabilities for a decade, which would put the engagement on this projection as kicking off not long before Intel started publicly talking about Larrabee, its own aborted button to move to a real-time ray tracing rendering system. And that brings united states to the GPUs themselves:

The RTX 2080 TiSEEAMAZON_ET_135 See Amazon ET commerce volition debut at $1,200 for the Founders Edition and ship at the end of September, on or "most" 9/xx. The RTX 2080 Atomic number 26, the replacement for the GTX 2080, will ship at $800 on (or virtually) the same date. The RTX 2070 FE will launch at $600 and has no shipping appointment at all. Cadre counts are lower than expected — the RTX 2080 is a 2944-core carte du jour, with an 1800MHz boost clock and a 1515MHz base of operations clock, which is actually slightly lower than the original 1080. Memory speeds are 14 Gbps with 448GB/southward of retentiveness bandwidth on 8GB of GDDR6, upwardly significantly from the 352GB/s bachelor on the terminal revision of the 1080. Standard versions of these cards may be somewhat cheaper, though we don't know that for certain yet.

The gap between the 2080 and the 2080 Ti is enormous. The 2080 Ti is 4352 cores, up 1.47x from the 2080 (the gap between the 1080 and 1080 Ti was 1.4x). Clock speeds are again slightly lower, (1350 base clock on 2080 Ti, down from 1480 on the 1080 Ti) with 11GB of RAM and 616GB/s of memory bandwidth.

Now Read: Nvidia Claims Real-Time Ray Tracing Now Possible, Nvidia GPUs Take Heavy Hit With HDR Enabled, and GPU Prices Could Exist Near to Drop