|
|
|
|
|
by dragonwriter
4654 days ago
|
|
It seems to me, intuitively, that the only ways to do that are: 1. Essentially equivalent to streaming, or 2. Essentially equivalent to normal CPU->GPU communication but over the network (and, thus, needing the bandwidth that local CPU->GPU communication has if you want to avoid slowing things down -- GigE wouldn't seem to be enough, much less WiFi, even if you consider only bandwidth and not latency.) |
|