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

11–20 of 46 posts

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

#11

Post by scott-gray »

dharma1 wrote: post #6
mgreg wrote: post #4

Likely a good move for Intel to get in on one of the faster growing areas of computing. Let's the compete with the GPU folks and offer something to the cloud players eventually (a la Tensor Processing Unit). Nice to see the competition. Also lets Nervana scale and potentially get their Neon deep learning framework out there in the face of bigger players (a la TensorFlow). All in all it's good to see the competition i…

Neon has been fast in benchmarks because of hand optimised kernels, but their kernel guy (Scott Gray) recently left to OpenAI. I wonder why

I was aware of this deal before leaving. I made out pretty well with my vested shares but was more interested in working on the cutting edge of research than in continuing on with pure hardware optimization and design. I wish Nervana/Intel the best and I'm looking forward to seeing their hardware come to market. I'm mainly working on TensorFlow now, but would love to see Nervana finish the graph backend they've been working on.

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

#12

Post by lettergram »

Having done a technical review of what Nervana has to offer... Why Intel?

My assumption, is that Intel will lease the chips + software, similar to the way HP, Dell, etc. Lease GPU machines.

Nervana honestly woukd have been obsolete and dead pretty soon without this. I see this as an acuire-hire.

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

#13

Post by PeCaN »

modeless wrote: post #10
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

Wow, really important details here; very interesting. Now imagine this chip, but shrunk to Intel's latest 14nm process. If they make that chip I have no doubt that it will revolutionize the entire field.

> If they make that chip I have no doubt that it will revolutionize the entire field.

Ha, ha. Yeah… no. For one thing, there's no mention of its power consumption, no CUDA support, questionable memory design (sure, you can get a million TFlops without cache, now try to get that chip to do anything useful), etc.

Intel probably bought 'em to work on integrated GPUs or Xeon Phi or something.

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

#14

Post by modeless »

PeCaN wrote: post #13
modeless wrote: post #10

Earlier quoted context omitted.

Wow, really important details here; very interesting. Now imagine this chip, but shrunk to Intel's latest 14nm process. If they make that chip I have no doubt that it will revolutionize the entire field.

> If they make that chip I have no doubt that it will revolutionize the entire field. Ha, ha. Yeah… no. For one thing, there's no mention of its power consumption, no CUDA support, questionable memory design (sure, you can get a million TFlops without cache, now try to get that chip to do anything useful), etc. Intel probably bought 'em to work on integrated GPUs or Xeon Phi or something.

> 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 CPUs. It certainly will have various on chip memories to hold intermediate results. Neural net workloads are incredibly predictable and homogeneous and are essentially the perfect scenario for hand optimization of data flows to beat automatic caching.

> no CUDA support

You're just being silly now. CUDA isn't a standard, it's proprietary to NVIDIA and this isn't a general purpose processor anyway.

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

#16

Post by byebyetech »

lettergram wrote: post #12

Having done a technical review of what Nervana has to offer... Why Intel? My assumption, is that Intel will lease the chips + software, similar to the way HP, Dell, etc. Lease GPU machines. Nervana honestly woukd have been obsolete and dead pretty soon without this. I see this as an acuire-hire.

>> an acquire-hire.

For $350 million is not an acquire-hire.

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

#18

Post by pjscott »

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

> simplified memory architecture (no cache?)

No automatic cache hierarchy. There is local memory, which you manage explicitly. More info here:

https://www.nervanasys.com/nervana-engine-delivers-deep-lear...

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

#19

Post by argonaut »

modeless wrote: post #10
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

Wow, really important details here; very interesting. Now imagine this chip, but shrunk to Intel's latest 14nm process. If they make that chip I have no doubt that it will revolutionize the entire field.

What PeCaN is driving at, is that saying something like you "have no doubt that it will revolutionize the entire field," is simply hyperbole that is not supported. We'll see. Nervana didn't really gain that much traction, which is why it's being acquired. Intel hasn't had much of a deep learning presence so far, which is why they are acquiring.

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

#20

Post by ericjang »

scott-gray wrote: post #11
dharma1 wrote: post #6

Earlier quoted context omitted.

Neon has been fast in benchmarks because of hand optimised kernels, but their kernel guy (Scott Gray) recently left to OpenAI. I wonder why

I was aware of this deal before leaving. I made out pretty well with my vested shares but was more interested in working on the cutting edge of research than in continuing on with pure hardware optimization and design. I wish Nervana/Intel the best and I'm looking forward to seeing their hardware come to market. I'm mainly working on TensorFlow now, but would love to see Nervana finish the graph backend they've been…

Love your work. We welcome open source contributions to TensorFlow :)
Post reply on HN