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

131–140 of 283 posts

Re: Google supercharges machine learning tasks with TPU custom chip

#131

Post by Merovius »

arcanus wrote: post #72
mike_hearn wrote: post #67

Earlier quoted context omitted.

Google has always been strategic about announcing what it was doing, even since the early days (I used to work there too). Think about the impact the first MapReduce and GFS/BigTable papers had. My guess as to why they're announcing the TPU is that they are feeling the pressure from Facebook and other AI labs, and want to reinforce their reputation as being the best place to do AI research. By revealing that AlphaGo…

> By revealing that AlphaGo was based on this hardware Interesting, as the nature/science paper made no mention of this, it was exclusively trained on GPUs.

Note that the version of AlphaGo that beat Fan Hui and was presented in Nature is significantly different from the Version that played Lee Sedol. Unless you believe that they didn't work on it for half a year.

Re: Google supercharges machine learning tasks with TPU custom chip

#132

Post by rdtsc »

randyrand wrote: post #124
rdtsc wrote: post #108

Earlier quoted context omitted.

"We have an FPGA, oh but need to go faster, ok, build an ASIC then" is a natural thing to come up with. That's kind of what bitcoin farms did. Obviously details and plans how it was done is where all the good stuff is, so that being hidden is understandable.

I'm not even a hardware or AI person, and even I could have told you ASICs would make way more sense than GPUs or FPGAs for machine learning. It's all about data locality. Fetching memory is the most costly thing a GPU does, and for ML (DNNs) there no big need for global access memory 99% of the time. Anyone the casually follows AI knows that people have been talking about making DNN ASICS for some time. It was all a…

> Google is finally publicaly saying that "we did it first ;)"

Makes sense. In that respect yeah, they probably wanted to keep it under wraps to avoid Facebook/others from getting a timeline estimate out of it and jump ahead.

Re: Google supercharges machine learning tasks with TPU custom chip

#133

Post by mtgx »

randyrand wrote: post #124
rdtsc wrote: post #108

Earlier quoted context omitted.

"We have an FPGA, oh but need to go faster, ok, build an ASIC then" is a natural thing to come up with. That's kind of what bitcoin farms did. Obviously details and plans how it was done is where all the good stuff is, so that being hidden is understandable.

I'm not even a hardware or AI person, and even I could have told you ASICs would make way more sense than GPUs or FPGAs for machine learning. It's all about data locality. Fetching memory is the most costly thing a GPU does, and for ML (DNNs) there no big need for global access memory 99% of the time. Anyone the casually follows AI knows that people have been talking about making DNN ASICS for some time. It was all a…

> It's all about data locality.

That's kind of what Movidius says, too, about its Myriad 2 VPU, which is kind of a GPU (SIMD-VLIW) with larger amounts of local memory combined with hardware accelerators.

Re: Google supercharges machine learning tasks with TPU custom chip

#134

Post by micro_cam »

Retric wrote: post #43
dgacmu wrote: post #32

Earlier quoted context omitted.

No - tensorflow is open source and you can run it on many platforms. TPUs are about efficiency. You might not be able to do image recognition as efficiently without one, but you can still perform exactly the same tasks. (I work on TF this year.)

I would be shocked if tensorflow optimizations where useful 1:1 for stock Intel chips or GPU's. So, there is still plenty of lock-in even if your process runs. GPU vendors love to play this game by helping optimize games.

All of the comparable tools are practically locked into nVidia gpus/CUDA. TensorFlow is rapidly reaching performance parity on that hardware [1] and can now be run on this so it's actually sort of the least locked in framework.

[1] It has been climbing the charts at https://github.com/soumith/convnet-benchmarks for example.

Re: Google supercharges machine learning tasks with TPU custom chip

#136

Post by rcpt »

luu wrote: post #63

I'm happy to hear that this is finally public so I can actually talk about the work I did when I was at Google :-). I'm a bit surprised they announced this, though. When I was there, there was this pervasive attitude that if "we" had some kind of advantage over the outside world, we shouldn't talk about it lest other people get the same idea. To be clear, I think that's pretty bad for the world and I really wished th…

> it's impossible to deploy GPUs at scale, let alone ASICs

A bit old but cf. DE Shaw and Anton https://en.m.wikipedia.org/wiki/Anton_(computer)

Re: Google supercharges machine learning tasks with TPU custom chip

#137

Post by agumonkey »

azinman2 wrote: post #100
agumonkey wrote: post #56

Earlier quoted context omitted.

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.

Ok I was obviously oversimplifying things but my point is since we can only speculate, it's clear that when you know specific algorithms/math operations/memory layouts/applications you want to optimize for you can create dedicated chips that optimize and do that quickly. That bitcoin miners are all dedicated chips and run circles around GPUs demonstrates exactly this fact. Furthermore the fact that ML can be error to…

tbh I felt like realizing what you meant earlier at the end of my comment. I should have ps'd it.

Re: Google supercharges machine learning tasks with TPU custom chip

#138

Post by placeybordeaux »

rando3826 wrote: post #135

Why use an ANKY in the title? Using an ANKY(Acronym no one knows yet) is bad writing, makes readers feel dumb, etc. Google JUST NOW invented that acronym, sticking it in the title like just another word we should understand is absolutely ridiculous.

I honestly didn't find it that hard to understand as they recently released a machine learning library that started with a T.

Re: Google supercharges machine learning tasks with TPU custom chip

#139

Post by hendler »

Krakulf wrote: post #111
mike_hearn wrote: post #67

Earlier quoted context omitted.

Google has always been strategic about announcing what it was doing, even since the early days (I used to work there too). Think about the impact the first MapReduce and GFS/BigTable papers had. My guess as to why they're announcing the TPU is that they are feeling the pressure from Facebook and other AI labs, and want to reinforce their reputation as being the best place to do AI research. By revealing that AlphaGo…

It really boosts Google Cloud Platform with image and prestige, they're coming out with what is pretty much tensorflow as a service with their machine learning product. Coming out saying they can give you a service no one else can right down to a custom chip may sway a few buyers in the market. https://cloud.google.com/ml/

For me this is true. GPUs on Amazon are not cheap, and if google passes the savings on from performance power consumption I'd certainly offload some work to Google cloud.

Re: Google supercharges machine learning tasks with TPU custom chip

#140

Post by hristov »

It is interesting that they would make this into an ASIC, provided how notoriously high the development costs for ASICs are. Are those costs coming down? If so life will get very hard for the FPGA makers of the world soon.

It would be interesting to see what the economics of this project are. I.e., what are the development costs and costs per chip. Of course it is very doubtful I will ever get to see the economics of this project, it would be interesting.

Post reply on HN