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

Nvidia Unveils First Mobile Supercomputer for Embedded Systems

nvidianews.nvidia.com

Post reply on HN
Print view View original

31–40 of 40 posts

Re: Nvidia Unveils First Mobile Supercomputer for Embedded Systems

#31

Post by MertsA »

fidotron wrote: post #20

I wonder if something like this could be the start of a decent key-value appliance. Hardware designed to perform the role of memcached on the network or similar.

If you wanted raw memcached performance there was an awesome paper on using an FPGA tied to 24GBs of regular DDR3 RAM and a 10G ethernet port. The result was a memcached server with 3.5 to 4.5 microsecond response time, capable of saturating the 10G port even with tiny key-value pairs, and 13 million requests per second while using 50W of power to do so.

http://0b4af6cdc2f0c5998459-c0245c5c937c5dedcca3f1764ecc9b2f...

Re: Nvidia Unveils First Mobile Supercomputer for Embedded Systems

#32

Post by robomartin »

Is this for processing USB webcam data? I'd like to use industrial or broadcast-level cameras but the board seems to be lacking support for these kinds of inputs. Also, in both of those domains cameras can deliver true 10 to 12 bits per color channel uncompressed performance. Webcams don't come close, as far as I know.

Am I wrong?

Re: Nvidia Unveils First Mobile Supercomputer for Embedded Systems

#33

Post by wmf »

robomartin wrote: post #32

Is this for processing USB webcam data? I'd like to use industrial or broadcast-level cameras but the board seems to be lacking support for these kinds of inputs. Also, in both of those domains cameras can deliver true 10 to 12 bits per color channel uncompressed performance. Webcams don't come close, as far as I know. Am I wrong?

Tegra 4 has a MIPI-CSI interface for image sensors and I would assume K1 is similar. Supposedly you can combine the ISP and GPU for image/video processing.

Re: Nvidia Unveils First Mobile Supercomputer for Embedded Systems

#34

Post by trhway »

hershel wrote: post #13

This looks pretty similar to the parallela, with better price, nicer software support and better manufacturing horizon. Oh well, that was somewhat predictable: parallela competed with nvidia in something that nvidia cared about and could execute.

no, they are very different.

NVIDIA is SIMD, a 32 thread warp doing the same instruction in lockstep (in 4 cycles usually on 8 SPs, the 192 SP chip can run 24 warps simultaneously, though specific numbers may change a bit from version to version) and heavily penalized for in-warp divergence.

Parallela - i.e. Adapteva (http://www.adapteva.com/epiphanyiv/) is 64 independent (execution-wise) RISC cores.

Re: Nvidia Unveils First Mobile Supercomputer for Embedded Systems

#36

Post by jmpe »

rhoads wrote: post #35

What about using this for bit/alt coin mining? Do you guys think it is a good ratio of performance / power consumption?

Notice they use the GigaFLOPs metric, which is a (maximum) floating point measure. Bitcoin hashing (it's been a while for me) is compute intensive on integer math. For a good ratio of performance/power you'd want to look at architectures like the GreenArray devices. But the world of bitcoin hashing is now firmly positioned in ASICs. You can't cut architecture fat beyond that so you'd have to look at (general purpose) architectures built on a faster silicon technology. Wouldn't count on it.

http://www.greenarraychips.com

Re: Nvidia Unveils First Mobile Supercomputer for Embedded Systems

#37

Post by skrowl »

pantalaimon wrote: post #30
maximux wrote: post #4

Could something like this work for a home server?

Why would you need a powerful GPU in a home server?

I've been looking for something to replace my Ouya as an XBMC box, but with enough power to support the incoming 4K content. I'm not sure this does it.

Re: Nvidia Unveils First Mobile Supercomputer for Embedded Systems

#39

Post by fidotron »

wmf wrote: post #23
noahl wrote: post #22

Earlier quoted context omitted.

Hmm. At first I thought this would be a waste, because you couldn't use all of its fast compute capabilities on doing key-value lookups. But these things also have much, much more memory bandwidth than regular CPUs (I can't remember if it's 10x or 100x, but that ballpark), and that might work well for these applications. But I don't know how the GPU's memory caching infrastructure works. If the bandwidth is only for…

K1 has about the same memory bandwidth as every other mobile SoC, which is to say not all that much. Don't compare it to discrete GPUs.

True, but in my experience if you can avoid hitting the memory the amount of computation you can do per thing is absolutely terrifying.

The main thing I had in mind here was hashing for bloom filters. i.e. do the different algos in parallel on a GPU, then pass those values for the main lookup to be done by the CPU.

Re: Nvidia Unveils First Mobile Supercomputer for Embedded Systems

#40

Post by dublinben »

skrowl wrote: post #37
pantalaimon wrote: post #30

Earlier quoted context omitted.

Why would you need a powerful GPU in a home server?

I've been looking for something to replace my Ouya as an XBMC box, but with enough power to support the incoming 4K content. I'm not sure this does it.

You'd probably be better off waiting for a 4K codec to settle out, and for hardware decoding support in new chipsets. As it stands, HDMI is barely capable of pushing 4K to the handful of displays that will accept it.
Post reply on HN