Re:Japan to Unveil Pascal GPU-Based AI Supercomputer
by deepnotderp on Monday March 13, 2017 @10:19AM
(#13857972)
Copy pasting my comment from below:
I'm aware (excruciatingly aware...) of that. Our numbers are ~10X better despite a process disadvantage.
And as always, Nvidia is twiddling the numbers, they exclude the cost of memory access when calculating 1 top/w, whereas we include it.
I'm aware (excruciatingly aware...) of that. Our numbers are ~10X better despite a process disadvantage. And as always, Nvidia is twiddling the numbers, they exclude the cost of memory access when calculating 1 top/w, whereas we include it.