Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Google Announces TPUv4, 2.7x faster on average than TPUv3. Parent comment
W / (256 * speed_v4) = 1.82
W / (4096 * speed_v3) = 0.39
speed_v4 / speed_v3 = (4096 * 0.39) / (256 * 1.82) = 3.43
Note that this assumes that training speed is perfectly linear with the # of accelerators which is not true as you get to very large #s (like 4096!). So the true number should be smaller than the 3.43x above, and the reported 2.7x makes sense.
There are no comments on this comment yet.
W / (256 * speed_v4) = 1.82
W / (4096 * speed_v3) = 0.39
speed_v4 / speed_v3 = (4096 * 0.39) / (256 * 1.82) = 3.43
Note that this assumes that training speed is perfectly linear with the # of accelerators which is not true as you get to very large #s (like 4096!). So the true number should be smaller than the 3.43x above, and the reported 2.7x makes sense.