Taylor says for now, convolutional and recurrent neural networks are critical but that sparse neural networks are growing in importance. The answer starts with what types of deep learning frameworks and workloads are most important. The biggest question is what architecture will best fit the bill. It’s been a persistently growing demand on our infrastructure and now is the right time for Facebook to start preparing for having hardware accelerators in our datacenters.” But in four to five years, he says, they will have picked one, perhaps two, architectures that will fit the bill at scale at narrow that down to a single SKU, adding perhaps a seventh server type to the lineup.įacebook has been running deep learning workloads for years now, but as Taylor tells The Next Platform, “We’ve done all inference on just traditional CPUs and I think what we expect is that with the amount of inference we’ll be doing in the future is going to be such that we will want more hardware acceleration. For now, they are experimenting with many new devices, trying to understand the right balance of memory, compute, and how that yields for efficiency. Taylor says the same thing will be true with inference. As we wrote back in March 2016, there are six types of servers for specific workloads in their datacenters, which means that once the company picks an architecture, it builds around it for the long haul. The takeaway is that at scale, CPUs are not up to the task-a tough thing to admit for Facebook that takes great pride in its limited SKUs for all of its workloads.
0 Comments
Leave a Reply. |