Dataflow architectures are general computation engines optimized for the execution of fme-grain parallel algorithms. Neural networks can be simulated on these systems with certain advantages. In this paper, we review dataflow architectures, examine neural network simulation performance on a new generation dataflow machine, compare that performance to other simulation alternatives, and discuss the benefits and drawbacks of the dataflow approach. Dataflow architectures are general computation engines that treat each instruction of a program as a separate task which is scheduled in an asynchronous, data-driven fashion. Dataflow programs are compiled into graphs which explicitly describe the data dependencies of the computation.

You're probably familiar with the scenario: Waiting on hold as you get transferred to the second, third or fourth customer service agent that is in'the right department' to resolve your issue. You've told them your account details, answered all of the security questions but when you finally get through, they start by asking for your account number (again). For anyone who has experienced this – and that's most of us – it leaves a bitter taste in the mouth. But the real question here is, what are businesses doing to end this cycle? Zendesk's recent Customer Experience Trends Report, which looks at data from 45,000 companies worldwide, tells a story of how this sort of experience is far too common.

Dataflow architectures are general computation engines optimized for the execution of fme-grain parallel algorithms. Neural networks can be simulated on these systems with certain advantages. In this paper, we review dataflow architectures, examine neural network simulation performance on a new generation dataflow machine, compare that performance to other simulation alternatives, and discuss the benefits and drawbacks of the dataflow approach.

Dataflow architectures are general computation engines optimized for the execution of fme-grain parallel algorithms. Neural networks can be simulated on these systems with certain advantages. In this paper, we review dataflow architectures, examine neural network simulation performance on a new generation dataflow machine, compare that performance to other simulation alternatives, and discuss the benefits and drawbacks of the dataflow approach.

Dataflow architectures are general computation engines optimized for the execution of fme-grain parallel algorithms. Neural networks can be simulated on these systems with certain advantages. In this paper, we review dataflow architectures, examine neural network simulation performance on a new generation dataflow machine, compare that performance to other simulation alternatives, and discuss the benefits and drawbacks of the dataflow approach.