Neural processing unit: Difference between revisions

Revision as of 03:55, 17 June 2016

Revision as of 03:56, 17 June 2016

Line 39:

* [[Adapteva epiphany]] is targeted as a [[coprocessor]], featuring a [[network on a chip]] [[scratchpad memory]] model, suitable for a dataflow programming model, which should be suitable for many machine learning tasks.

* [[Kalray]] productproduce an [[MPPA]] <ref>{{cite web|title=kalray MPPA|url=http://www.hotchips.org/wp-content/uploads/hc_archives/hc27/HC27.24-Monday-Epub/HC27.24.20-Multimedia-Epub/HC27.24.240-DeDinechin-KalrayMMPA-Kalray-v4.pdf}}</ref> which reports 12x efficiency gains over GPUs for convolutional neural nets.

==References==