Nvidia announces RTX 2000 GPU series with ‘6x more performance’ and ray-tracing

Post by bitL » Mon, Aug 20, 2018, 9:08 PM UTC

h4b4n3r0 wrote: post #179

bitL wrote: post #12

Hmm, 24%-42% performance increase (14/16TFlops vs 11.3TFlops) for 70-90% price increase... And prices were already inflated by crypto that is now collapsing. Not sure who is the target market for this tech honestly. Still only 11GB RAM, even if 50% faster, making it a nonsense purchase for Deep Learning enthusiasts (state-of-art models are already larger). Unless somebody invented RTX-based coin of course, then this…

Whether it's substantially better for deep learning depends on whether they chose to neuter fp16 like they did in all other consumer GPUs. The main bottleneck is not actually the size of the model per se (sizes of the models have been mostly going _down_ as of late), it's the size of the batch during training. Both batch size and model size determine the size of the main memory hog: activations that you need to keep…

Post by alkonaut » Mon, Aug 20, 2018, 9:11 PM UTC

mattnewport wrote: post #180

alkonaut wrote: post #151

Earlier quoted context omitted.

Triangles and fragments per second for rasterization grew exponentially because of growth in circuit performance . Ray tracing needs to grow say 3 orders of magnitude in performance now (at least) but do so without (that) massive advances in semiconductors. That will be a challenge.

Depends what you mean by 'needs'. The combination of dedicated ray tracing acceleration hardware and APIs to drive it with some remarkable advances in denoising, in part driven by deep learning plus associated dedicated hardware, means that we are at a threshold where hybrid techniques that mix rasterization with ray tracing are viable for games and can advance the state of the art in real time rendered image quality…

Post by snuxoll » Mon, Aug 20, 2018, 9:15 PM UTC

jackpeterfletch wrote: post #181

bitL wrote: post #102

Earlier quoted context omitted.

The point was different - it is way too expensive for regular gamers, 2080Ti likely won't be able to do 4k@60Hz like 1080Ti couldn't either and 10 games featuring RTX in the nearly future is not a sufficient draw, especially when some of the effects now look subjectively worse with RTX ON (see those shadows from multiple lights above dancing people from Jenson's demo). So the question remains - who is the real target…

> it is way too expensive for regular gamers Gamers arent kids anymore. Amongst my friends that game, most are nearly 30 working excellent jobs in software.

Post by PeCaN » Mon, Aug 20, 2018, 9:18 PM UTC

etiam wrote: post #38

Since the post with the product page got merged here: https://www.nvidia.com/en-us/geforce/graphics-cards/rtx-2080... Most of it is dramatically lit renderings of fans and vacuous marketing-speak of course, but there's a tidbit near the bottom of the page about NVLink I find interesting. "GeForce RTX™ NVLINK™ Bridge The GeForce RTX™ NVLink™ bridge connects two NVLink SLI-ready graphics cards with 50X the transfer ban…

Post by eanzenberg » Mon, Aug 20, 2018, 9:20 PM UTC

old-gregg wrote: post #24

Putting AI/ML aside, I have a question for graphics experts or/and gamers: what is the practical [1] ceiling of the current champion, the 1080ti? I was under impression that that card already was much more than most people needed. In other words, is the new generation only useful for 4K gaming? [1] By "practical" I mean on 1440p@144Hz monitors.