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

Intel to buy deep-learning startup Nervana Systems for at least $350M

recode.net

Post reply on HN
Print view View original

41–46 of 46 posts

Re: Intel to buy deep-learning startup Nervana Systems for at least $350M

#41

Post by p1esk »

mastazi wrote: post #25
p1esk wrote: post #23

Earlier quoted context omitted.

it would be even better if we also get an open-source software stack that can compete with Nvidia's proprietary CUDA stack You've already got that. It's called OpenCL.

Parent said "that can compete" so no, in practice, we don't have that. (Of course I hope the situation will improve!!) https://en.wikipedia.org/wiki/Comparison_of_deep_learning_so... (see column "Open CL support")

Oh, so you (or OP) want Intel/Nervana to create yet another programming model which will succeed where OpenCL fails (e.g. beat CUDA)? Seems unlikely...

Re: Intel to buy deep-learning startup Nervana Systems for at least $350M

#42

Post by Katydid »

p1esk wrote: post #2

Here are some details about their upcoming chip: http://www.nextplatform.com/2016/08/08/deep-learning-chip-up... Summary: - 28nm - looks similar to P100 (interposer with HBM) - 55 teraops/s performance - custom number format (variable length fixed point?) - simplified memory architecture (no cache?) - no info about power consumption

Most of the questions asked in these threads on HN are answered in an update article they posted this morning about 14 nanometer, the Neon framework's future and such. Also, looks like everyone who broke the news did got the acquisition amount wrong. http://www.nextplatform.com/2016/08/10/nervana-ceo-intel-acq...

Re: Intel to buy deep-learning startup Nervana Systems for at least $350M

#43

Post by camuel »

Alphasite_ wrote: post #38
mastazi wrote: post #24

Earlier quoted context omitted.

> You're just being silly now. CUDA isn't a standard, it's proprietary to NVIDIA I would love to agree with you but the reality is that CUDA is the de-facto industry standard e.g. [1]. > and this isn't a general purpose processor anyway. The "GP" part in GPGPU would like to disagree... [2] [1] https://en.wikipedia.org/wiki/Comparison_of_deep_learning_so... [2] http://www.nvidia.com/object/cuda_home_new.html

Google has implemented their own deep learning chip with no CUDA support and its serving their purposes well. Why not another industry giant, Intel?

Google is very different from Intel on these fronts at least: 1. Google's open framework TensorFlow is exploding in popularity effectively moving the common interface up from CUDA. 2. Google has a huge need for internal AI/DeepLearning 3. Google has cloud and AI/DeepLearning as a service business 4. Google doesn't sells hardware

However, Intel dominance is not to be underestimated, they definitely can make industry wide impact quickly. Just saying you can not easily draw parallels here

Re: Intel to buy deep-learning startup Nervana Systems for at least $350M

#44

Post by sctb »

PeCaN wrote: post #21
modeless wrote: post #14

Earlier quoted context omitted.

> Intel probably bought 'em to work on integrated GPUs or Xeon Phi or something. Ha, ha. Yeah… no. > there's no mention of its power consumption Can't be tremendously higher than Pascal for reasons of physics. > sure, you can get a million TFlops without cache, now try to get that chip to do anything useful "Without cache" is certainly an exaggeration. It won't have a globally coherent cache hierarchy in the style of…

> > Intel probably bought 'em to work on integrated GPUs or Xeon Phi or something. > Ha, ha. Yeah… no. Oh? You don't think they'd acquihire a machine learning startup to work on their compute/machine learning offering in Xeon Phi? I would be very, very surprised if Intel introduces a new machine-learning-oriented processor—though that would be quite interesting, so let's hope you're right. > Can't be tremendously hig…

> I'm not sure if you're a troll, an overly zealous brogrammer buying into deep learning buzzwords, or retarded, but maybe you should cut it out.

Personal attacks are not OK on Hacker News. Please leave these out of comments.

Re: Intel to buy deep-learning startup Nervana Systems for at least $350M

#45

Post by PeCaN »

sctb wrote: post #44
PeCaN wrote: post #21

Earlier quoted context omitted.

> > Intel probably bought 'em to work on integrated GPUs or Xeon Phi or something. > Ha, ha. Yeah… no. Oh? You don't think they'd acquihire a machine learning startup to work on their compute/machine learning offering in Xeon Phi? I would be very, very surprised if Intel introduces a new machine-learning-oriented processor—though that would be quite interesting, so let's hope you're right. > Can't be tremendously hig…

> I'm not sure if you're a troll, an overly zealous brogrammer buying into deep learning buzzwords, or retarded, but maybe you should cut it out. Personal attacks are not OK on Hacker News. Please leave these out of comments.

sieg heil

Re: Intel to buy deep-learning startup Nervana Systems for at least $350M

#46

Post by Alphasite_ »

camuel wrote: post #43
Alphasite_ wrote: post #38

Earlier quoted context omitted.

Google has implemented their own deep learning chip with no CUDA support and its serving their purposes well. Why not another industry giant, Intel?

Google is very different from Intel on these fronts at least: 1. Google's open framework TensorFlow is exploding in popularity effectively moving the common interface up from CUDA. 2. Google has a huge need for internal AI/DeepLearning 3. Google has cloud and AI/DeepLearning as a service business 4. Google doesn't sells hardware However, Intel dominance is not to be underestimated, they definitely can make industry w…

What's stopping them provinding a backend for tensorflow? But yes'm, it's obviously not a given.
Post reply on HN