eRe4s3r wrote on Jul 29, 2013, 10:08:
Basically, the bandwidth required is extremely small... latency is the real linchpin for moving light-sources. And if it can stay within 100ms it's fine.
Correct, latency is the issue. Part of that is the processing time but the point of this tech basically is that it eliminates that aspect. 100ms might be tolerable although in my experience with virtual audio piping, 50ms is what you really want...and honestly that is feasible.
More interestingly, it hints at grid-based geographical load balancing, something I predicted would eventually be big more than 5 years ago (it was and is being researched at Palo Alto). Even the old experts (I've seen network designers from the 80s make "informed" posts on the technology in recent times) really miss the point that bottlenecks in the network are the main issue. IPv6 will take away the barriers to an effective grid, but I'm getting ahead of myself with regard to this specific announcement by Nvidia. Needless to say that being able to rely on locality means lower latency and less redundant information transfer.
Long story short, it optimizes rendering through prediction and the use of cloud networking.