|
|
|
|
|
|
by log_base_login
3110 days ago
|
|
|
> Indeed, the P100 is twice as fast and the K80, but due to the huge cost premium, it’s not cost effective for this simple task. Am I reading the graph wrong, or is this statement not true? Looks like the P100 is running the code in around half the time as the K80 and the cost is only 150% that of the K80. .5::1.5 == 1::3 > 1::1 |
|
|