NVIDIA today unveiled a series of important advances to its world-leading deep learning computing platform, which delivers a 10x performance boost on deep learning workloads compared with the previous... Nvidia DGX-2 Is First 2 Petaflop Deep Learning System
Wait a minute.... So, are they telling us that 6 of these, would net you the 10th position of the TOP500 Supercomputers? And with 15, the 3rd ? And... Imagine with just 60, then ? Jensen is even openly admitting it: "....machine translation reaching human capabilities ..." NVidia is gonna take oveee... 'How did my foil hat got up there? Apologies.
They are probably only counting the deep-learning flops, not the generic flops. The tensors cores on Volta give it a huge boost in deep learning flops.
My thought too at first but I will quote the article: "...the first single server capable of delivering two petaflops of computational power...". Unless we missed something, that clearly implies computation.
In the same boat, my Fury is doing okish (is semi unlocked) I was thinking to buy NVidia's next flagship model on release as tired of waiting.... but after GPP I am going to be waiting a while longer it seems.
Good thing we have custom resolutions at least. Lots of titles actually do play at 60fps ultra 4k on a 1080ti but for the ones that don't, running them in either 3456x1944 or 3584x2016 can usually play on ultra at 60fps and looks pretty damn decent on a 4k screen. That's what I'm doing for now and for the foreseeable future until nvidia releases new cards. Also reserving 3200x1800 for those poorly optimized games or extremely demanding games in the future.
Not tried that angle, is a good idea. I've been mostly playing through my back catalogue of older Steam games that run great at 4K on my Fury. Is a good excuse to get through some of them
