Article 3RVK4 Training a neural network in phase-change memory beats GPUs

Training a neural network in phase-change memory beats GPUs

by
John Timmer
from Ars Technica - All content on (#3RVK4)
GettyImages-172686184-800x1067.jpg

Enlarge (credit: Miguel Navarro / Getty Images)

Compared to a typical CPU, a brain is remarkably energy-efficient, in part because it combines memory, communications, and processing in a single execution unit, the neuron. A brain also has lots of them, which lets it handle lots of tasks in parallel.

Attempts to run neural networks on traditional CPUs run up against these fundamental mismatches. Only a few things can be executed at a time, and shuffling data to memory is a slow process. As a result, neural networks have tended to be both computationally and energy intensive. A few years back, IBM announced a new processor design that was a bit closer to a collection of neurons and could execute neural networks far more efficiently. But this didn't help much with training the networks in the first place.

Now, IBM is back with a hardware design that's specialized for training neural networks. And it does this in part by directly executing the training in a specialized type of memory.

Read 15 remaining paragraphs | Comments

index?i=0F6h5-nw8Hc:HzKBLRUcSKo:V_sGLiPB index?i=0F6h5-nw8Hc:HzKBLRUcSKo:F7zBnMyn index?d=qj6IDK7rITs index?d=yIl2AUoC8zA
External Content
Source RSS or Atom Feed
Feed Location http://feeds.arstechnica.com/arstechnica/index
Feed Title Ars Technica - All content
Feed Link https://arstechnica.com/
Reply 0 comments