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

Apple Is Working on a Dedicated Chip to Power AI on Devices

bloomberg.com

Post reply on HN
Print view View original

71–80 of 123 posts

Re: Apple Is Working on a Dedicated Chip to Power AI on Devices

#71

Post by themihai »

panic wrote: post #69
Retric wrote: post #66

Earlier quoted context omitted.

There is a tiny one in the iPhone 7. But, that's for flexibility on current tasks not future proofing. In terms of AI there is little reason to run it on the phone unless it's heavily used or needs or be low latency. Consider if they add a 100$ of computing power to a phone that sits unused 99% of the time they can just build a server using those same 100$ worth of parts that can then serve 100 phones saving 90+$ per…

Privacy is another reason to keep the computation local.

I believe that's actually the main reason to choose a "local" AI.

Re: Apple Is Working on a Dedicated Chip to Power AI on Devices

#72

Post by taneq »

panic wrote: post #69
Retric wrote: post #66

Earlier quoted context omitted.

There is a tiny one in the iPhone 7. But, that's for flexibility on current tasks not future proofing. In terms of AI there is little reason to run it on the phone unless it's heavily used or needs or be low latency. Consider if they add a 100$ of computing power to a phone that sits unused 99% of the time they can just build a server using those same 100$ worth of parts that can then serve 100 phones saving 90+$ per…

Privacy is another reason to keep the computation local.

Good luck getting any of the big players to acknowledge that. >.<

Re: Apple Is Working on a Dedicated Chip to Power AI on Devices

#74

Post by fnbr »

JumpCrisscross wrote: post #34

Could this mean on-device ANI? My deal breaker with Amazon, Google, Microsoft and even Siri is their role in normalising the hoovering up of sensitive data.

I think so- they acquired a company a few years back, percept.io, that did on device learning. I wouldn't be surprised if they were starting to put it in production.

Re: Apple Is Working on a Dedicated Chip to Power AI on Devices

#76

Post by pjscott »

protomyth wrote: post #12
MBCook wrote: post #7

Earlier quoted context omitted.

Google has their Tensor Flow. chips, I would imagine it is similar.

Is there released documentation on the instruction set of the Google Cloud TPU?

They list the main ones on pages 3-4 of this paper:

https://drive.google.com/file/d/0Bx4hafXDDq2EMzRNcy1vSUxtcEk...

It's mainly moving memory around, matrix multiplication, convolution, and applying activation functions (sigmoid, tanh, relu, etc.). Very simple, high-level stuff. This has the handy side-effect of making timing very predictable, which makes the latency a lot more deterministic.

Re: Apple Is Working on a Dedicated Chip to Power AI on Devices

#77

Post by djrogers »

taneq wrote: post #72
panic wrote: post #69

Earlier quoted context omitted.

Privacy is another reason to keep the computation local.

Good luck getting any of the big players to acknowledge that. >.<

That's exactly why Apple does things like analyze your photo library locally on the phone - for privacy.

Re: Apple Is Working on a Dedicated Chip to Power AI on Devices

#78

Post by DannyBee »

djrogers wrote: post #77
taneq wrote: post #72

Earlier quoted context omitted.

Good luck getting any of the big players to acknowledge that. >.<

That's exactly why Apple does things like analyze your photo library locally on the phone - for privacy.

Yes, surely this has no relation to their inability to build reliable cloud products ....

Re: Apple Is Working on a Dedicated Chip to Power AI on Devices

#79

Post by djrogers »

rch wrote: post #53
djrogers wrote: post #52

Earlier quoted context omitted.

You don't put an FPGA in a device you're going to sell 200M+ of. The cost per unit would be way higher than an asic, and your just going to come out with a better version next year anyway so why bother? I foresee it as similar to their M series co-processors - the first one was pretty basic, and more sensors and jobs have been given to the newer ones each year.

IIRC there's already an FPGA in the iPhone.

You are correct, but we're talking about an entirely different magnitude of fpga for AI purposes than the tiny little one in the iPhone 7.

Re: Apple Is Working on a Dedicated Chip to Power AI on Devices

#80

Post by hn_throwaway_99 »

wklauss wrote: post #55
jacquesm wrote: post #41

Earlier quoted context omitted.

I'd bet on this being an ASIC, doing this on an FPGA with any serious size matrix would require a very expensive FPGA, whereas an ASIC would allow more gates in a smaller volume and would consume less power to boot. From the manufacturers point of view phones not being future proof is a feature, not a bug, that way you'll upgrade to that new shiny item which will keep the profits rolling in.

> From the manufacturers point of view phones not being future proof is a feature, not a bug, that way you'll upgrade to that new shiny item which will keep the profits rolling in. I don't think a better AI chip will be a convincing argument to change a phone one year later.

I think you underestimate the power of marketing.
Post reply on HN