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

51–60 of 283 posts

Re: Google supercharges machine learning tasks with TPU custom chip

#51

Post by eva1984 »

bd wrote: post #37

So now open sourcing of "crown jewels" AI software makes sense. Competitive advantage is protected by custom hardware (and huge proprietary datasets). Everything else can be shared. In fact it is now advantageous to share as much as you can, the bottleneck is a number of people who know how to use new tech.

Agree. To attract devs to using your spec, then eventually go to your platform. But since the spec are open, AMZN/MS can make their own too. So it is still a good thing.

Re: Google supercharges machine learning tasks with TPU custom chip

#52

Post by saganus »

triangleman wrote: post #45
saganus wrote: post #36

Is that a Go board stick to the side of the rack? Maybe they play one move every time someone gets to go there to fix something? or could it be just a way of numbering the racks or something eccentric like that?

It appears to be a commemorative plaque from when they defeated world champion Lee Sodol.

Ah. That makes sense.

Re: Google supercharges machine learning tasks with TPU custom chip

#53

Post by PeCaN »

DSingularity wrote: post #40
mtgx wrote: post #14

Earlier quoted context omitted.

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.

What are they doing with RISC-V?

They dumped a bunch of money into it, so presumably they're at least interested.

Re: Google supercharges machine learning tasks with TPU custom chip

#54

Post by Others »

saganus wrote: post #36

Is that a Go board stick to the side of the rack? Maybe they play one move every time someone gets to go there to fix something? or could it be just a way of numbering the racks or something eccentric like that?

The pictures have swapped captions.

Re: Google supercharges machine learning tasks with TPU custom chip

#55

Post by agumonkey »

honkhonkpants wrote: post #31
agumonkey wrote: post #16

Earlier quoted context omitted.

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

What graph?

In the talk there was a two bar graph

    {(others, ~bottom) (google, ~top)}
Couldn't see more, but after Nvidia claiming overwhelming power with their latest GPU architecture including in the ML domain .. I was surprised.

Re: Google supercharges machine learning tasks with TPU custom chip

#56

Post by agumonkey »

fiatmoney wrote: post #47
azinman2 wrote: post #41

Earlier quoted context omitted.

The fact that I can compile arbitrary programs for the GPGPU means it is general purpose. NVIDIA isn't writing softmax or backprop into silicon as a CPU instruction. Look at how much faster ASICs for bitcoin mining are than the GPU... orders of magnitude.

"Backprop" isn't even close to something that would be a "CPU instruction", it's an entire class of algorithm. It's like saying "calculus" should be a CPU instruction. Matrix multiplication & other operations, on the other hand, do neatly decompose into such instructions, which have been implemented by NVidia et al., since that's the core set of functionality they've been pushing for like a decade now. Additional die…

That was my impression too. ML under the hood was a lot of linear algebra, not very different than most shaders. But maybe Google decided to hardcode a few important ML primitives because the ROI was that good in terms of grabbing customers. Also they might have very large scale applications not found elsewhere that motivates this.

Re: Google supercharges machine learning tasks with TPU custom chip

#58

Post by j1vms »

I wouldn't be surprised if Google is looking to build (or done so already) a highly dense and parallel analog computer with limited precision ADC/DACs. I mean that's simplifying things quite a bit, but it would probably map pretty well to the Tensorflow application.

Re: Google supercharges machine learning tasks with TPU custom chip

#59

Post by mtgx »

bd wrote: post #37

So now open sourcing of "crown jewels" AI software makes sense. Competitive advantage is protected by custom hardware (and huge proprietary datasets). Everything else can be shared. In fact it is now advantageous to share as much as you can, the bottleneck is a number of people who know how to use new tech.

Indeed. I kind of realized this more recently when I saw some new chips promote that Tensorflow works on them. This is really what it was all about - getting chips everywhere to support Google's version of AI, which means that in the long term they can get those chips themselves in volume - chips that are optimized for their AI out of the box.
Post reply on HN