Advanced search

Message boards : Number Crunching : CNN with OpenCl and Fpga

Author Message
[VENETO] boboviz
Send message
Joined: 10 Aug 14
Posts: 99
Combined Credit: 387,515
DNA@Home: 184,990
SubsetSum@Home: 1,636
Wildlife@Home: 200,890
Wildlife@Home Watched: 0s
Wildlife@Home Events: 0
Climate Tweets: 0
Images Observed: 0

    
Message 7360 - Posted: 21 Nov 2017, 15:56:40 UTC

Fpga CNN

Object classification using a low profile Nallatech 385A PCIe accelerator card with a discrete Intel Arria 10 FPGA accelerator programmed using Intel’s OpenCL Software Development Kit. Built on the BVLC Caffe deep learning framework, an FPGA interface and IP accelerate processing intensive components of the algorithm. Nallatech IP is capable of processing an image through the AlexNet neural network in nine milliseconds. The Arria10-based 385A™ board has the capacity to process six CNN images in parallel allowing classification of 660 images per second.

Alexander
Send message
Joined: 11 Aug 14
Posts: 41
Combined Credit: 23,861,254
DNA@Home: 428,269
SubsetSum@Home: 1,125,177
Wildlife@Home: 22,307,809
Wildlife@Home Watched: 0s
Wildlife@Home Events: 0
Climate Tweets: 0
Images Observed: 0

      
Message 7367 - Posted: 29 Nov 2017, 13:08:28 UTC - in response to Message 7360.

Maybe you have forgotten to say that this card cost 3,990.- USD

[VENETO] boboviz
Send message
Joined: 10 Aug 14
Posts: 99
Combined Credit: 387,515
DNA@Home: 184,990
SubsetSum@Home: 1,636
Wildlife@Home: 200,890
Wildlife@Home Watched: 0s
Wildlife@Home Events: 0
Climate Tweets: 0
Images Observed: 0

    
Message 7400 - Posted: 30 Jan 2018, 16:15:53 UTC - in response to Message 7367.

Maybe you have forgotten to say that this card cost 3,990.- USD


Yeap, but the important part is that you can use OpenCl to accelerate CNN over a lot of hw. An example: Imagination PowerVR SDK


Post to thread

Message boards : Number Crunching : CNN with OpenCl and Fpga