Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Google supercharges machine learning tasks with TPU custom chip

cloudplatform.googleblog.com

Post reply on HN
Print view View original

11–20 of 283 posts

Re: Google supercharges machine learning tasks with TPU custom chip

#11

Post by reitzensteinm »

jhartmann wrote: post #7

3 generations ahead of moore law??? I really wonder how they are accomplishing this beyond implementing the kernels in hardware. I suspect they are using specialized memory and an extremely wide architecture. Sounds they also used this for AlphaGo. I wonder how badly we were off on AlphaGo's power estimates. Seems everyone assumed they were using GPU's, sounds like they were not. At least partially. I would really LO…

But isn't 3 generations ahead just 8x? Which doesn't sound at all unreasonable for a custom hardware.

Re: Google supercharges machine learning tasks with TPU custom chip

#12

Post by BooneJS »

jhartmann wrote: post #7

3 generations ahead of moore law??? I really wonder how they are accomplishing this beyond implementing the kernels in hardware. I suspect they are using specialized memory and an extremely wide architecture. Sounds they also used this for AlphaGo. I wonder how badly we were off on AlphaGo's power estimates. Seems everyone assumed they were using GPU's, sounds like they were not. At least partially. I would really LO…

From the article: "TPU is tailored to machine learning applications, allowing the chip to be more tolerant of reduced computational precision, which means it requires fewer transistors per operation."

Re: Google supercharges machine learning tasks with TPU custom chip

#14

Post by mtgx »

semisight wrote: post #3

This is huge. If they really do offer such a perf/watt advantage, they're serious trouble for NVIDIA. Google is one of only a handful of companies with the upfront cash to make a move like this. I hope we can at least see some white papers soon about the architecture--I wonder how programmable it is.

Quantum computers, OpenPower, RISC-V, and now this - I'm really liking Google's recent focus on designing new types of chips and bringing some real competition into the chip market.

Re: Google supercharges machine learning tasks with TPU custom chip

#15

Post by DannyBee »

harigov wrote: post #6

How is this different from - say - synthetic neurons that IBM is working on, or what nvidia is building?

Without sounding crass:

1. It works already (IE it's already in use)

2. It works really well (or else they wouldn't be using it so broadly)

3. Considering how long this was said to be in development, it also likely means they are working on the next big improvement before these guys have even gotten the current one working.

Re: Google supercharges machine learning tasks with TPU custom chip

#16

Post by agumonkey »

semisight wrote: post #3

This is huge. If they really do offer such a perf/watt advantage, they're serious trouble for NVIDIA. Google is one of only a handful of companies with the upfront cash to make a move like this. I hope we can at least see some white papers soon about the architecture--I wonder how programmable it is.

I'm surprised by the perf claims. Nvidia isn't doing kids play. The graph implied they were untouchable in terms of perf...

Re: Google supercharges machine learning tasks with TPU custom chip

#18

Post by daveguy »

harigov wrote: post #6

How is this different from - say - synthetic neurons that IBM is working on, or what nvidia is building?

They are already using it in production and have been for over a year? That is a huge difference compared to what people are working on and building. They beat Lee Sedol using this hardware. Over 100 teams at Google are using machine learning. This hardware already accelerates their projects.

Re: Google supercharges machine learning tasks with TPU custom chip

#19

Post by azinman2 »

cschmidt wrote: post #17

This seems very similar to the "Fathom Neural Compute Stick" from Movidius: http://www.movidius.com/solutions/machine-vision-algorithms/... TensorFlow on a chip....

Although that stuff seems to be more about on the fly reasoning at low wattage so you can embed a drone with neural nets... This is more for servers.

Re: Google supercharges machine learning tasks with TPU custom chip

#20

Post by obulpathi »

abritishguy wrote: post #9

I think this shows a fundamental difference between Amazon (AWS) and Google Cloud. AWSs offerings seem fairly vanilla and boring. Google are offering more and more really useful stuff: - cloud machine learning - custom hardware - live migration of hosts without downtime - Cold storage with access in seconds - bigquery - dataflow

- Google Container Engine

- Cloud Shell

to name a couple more.

Post reply on HN