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

Post by bitL » Mon, Aug 20, 2018, 11:19 PM UTC

kmkemp wrote: post #217

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…

Well, one audience is obvious from your own sentence: people who are willing to pay to have the best performance currently possible.

Post by digi_owl » Mon, Aug 20, 2018, 11:21 PM UTC

gameswithgo wrote: post #239

digi_owl wrote: post #231

Earlier quoted context omitted.

Seems like gaming has long since hit an "eternal September" as producers are spewing out ever more impressive tech demos. I have long since taken to killing every graphical effect game devs can think of throwing into a game (if they supplied a toggle for it) simply so i can tell where the enemy is without wearing sunglasses indoors in a dark room.

sure, for games like battlegrounds. but some games don't even have enemies!

Post by antpol » Mon, Aug 20, 2018, 11:24 PM UTC

bitL wrote: post #236

jefft255 wrote: post #225

Earlier quoted context omitted.

You know, there is more to deep learning research than meta-learning/architecture exploration. Sure you can explore the hyper-parameter space faster with 500 GPUs and get yet again a 0.05% better test score on ImageNet (or more I don't actually know), but there are other ways to do something meaningful in DL without using such compute power.

That's a fair point and I agree. It's just sometimes difficult to beat automated exploration; as a standard company you probably don't have access to top-end researchers/practitioners, just average ones, and those might get a significant boost by trading smartness for brute force and run many models in parallel in evolutionary fashion. When you e.g. look at how Google's internal system constructs loss functions and h…

Post by xboxnolifes » Mon, Aug 20, 2018, 11:28 PM UTC

digi_owl wrote: post #243

gameswithgo wrote: post #239

Earlier quoted context omitted.

sure, for games like battlegrounds. but some games don't even have enemies!

Ah yes, visual stories 2.0...

Post by antpol » Mon, Aug 20, 2018, 11:30 PM UTC

wlesieutre wrote: post #57

agumonkey wrote: post #49

Earlier quoted context omitted.

introducing fiatlux

It's not as clever, but RayCoin would market better. Fiat Lux could be its tagline? I hope I'm joking.