News for hackers. Stuff that matters.

A comment on Comparing Google’s TPUv2 against Nvidia’s V100 on ResNet-50.

Re:Comparing Google’s TPUv2 against Nvidia’s V100 on ResNet-50 by Tenoke on Thursday April 26, 2018 @10:53AM (#16932385)
>For the V100 experiments, we used a p3.8xlarge instance (Xeon E5–[email protected] 16 cores, 244 GB memory, Ubuntu 16.04) on AWS with four V100 GPUs (16 GB of memory each). For the TPU experiments, we used a small n1-standard-4 instance as host ([email protected] two cores, 15 GB memory, Debian 9) for which we provisioned a Cloud TPU (v2–8) consisting of four TPUv2 chips (16 GB of memory each).

A bit odd that the TPUs are provisioned on such a weaker machine compared to the V100s, especially when there were comparisons which included augmentation and other processing outside of the TPU.

[ Parent | on HN ]
Re:Comparing Google’s TPUv2 against Nvidia’s V100 on ResNet-50 by elmarhaussmann on Thursday April 26, 2018 @10:56AM (#16932420)
All of the computation, including pre-processing, is offloaded to the TPU. The weak machine is really just idling. A bigger one will only cost money and have no measurable effect on the performance.
[ Parent | on HN ]
Re:Comparing Google’s TPUv2 against Nvidia’s V100 on ResNet-50 by KaoruAoiShiho on Thursday April 26, 2018 @12:01PM (#16933079)
What is the cost difference between the CPUs on the google cloud vs AWS? How would adjusting for it effect the cost/images ratio?
[ Parent | on HN ]
Re:Comparing Google’s TPUv2 against Nvidia’s V100 on ResNet-50 by shaklee3 on Thursday April 26, 2018 @11:27AM (#16932741)
This is why my previous comment mentioned that GCP is a better benchmark for this since you can select the number of CPUs to match with the GPUs to some extent. You can get a rough idea of the savings by looking at their P100 instances.
[ Parent | on HN ]
Re:Comparing Google’s TPUv2 against Nvidia’s V100 on ResNet-50 by puzzle on Thursday April 26, 2018 @12:11PM (#16933167)
The TPU is not really just the chip. It has an actual machine that is provisioned behind the scenes and accepts RPC calls. Good luck finding out its specs. All you're supposed to care about are the address and port it answers at.
[ Parent | on HN ]