Google Announces TPUv4, 2.7x faster on average than TPUv3

Re:Google Announces TPUv4, 2.7x faster on average than TPUv3 by codefined on Tuesday May 18, 2021 @05:23PM (#27201357)

Your maths is incorrect, dividing by the number of devices doesn't make sense in this case, you should be multiplying them. E.g.

- 466 minutes of fourth-generation TPU time.

- 1,600 minutes of third-generation TPU time.

Using this logic, fourth generation TPUs are 3.4x better. But, comparing different cluster sizes is pointless. These things don't scale linearly.

[ Parent | on HN ]

Re:Google Announces TPUv4, 2.7x faster on average than TPUv3 by skyde on Sunday May 23, 2021 @07:51PM (#27259716)

you are most likely correct! I read ´Training took 1.82 minutes with 256 fourth-gen TPUs’ to mean Using all 256 TPU it took 1.82 wall clock time to do the training not 466 minutes.

This mean each TPU contributed to (1/256) assuming it scale linearly.

Even if it doesn’t the 256 TPU ran in parallel not sequentially right ?

[ Parent | on HN ]