#GTC19: Professor Jensen Huang explains capability vs. capacity #HPCpic.twitter.com/axJbwgdqSU
Show this thread
-
Now I have more questions :-). That makes sense for consumer companies, but not for B2B companies although I think I get what he’s trying to say.
His point was scale up (in FLOPS) and scale out (in users) requires different architecture designs. Data science is in between these two extremes
-
-
OK that makes more sense.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
presumably this relates to the tightness of the problem coupling too, no? i.e., more embarrassingly parallel stuff and map-reduce/collective operations on hyperscale, whereas
#HPC requires at least neighbor to neighbor if not global comms with great frequency.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.