A Heterogeneous Von Neumann/Explicit Dataflow Processor

Decades-old explicit dataflow architectures eliminate many of the overheads of general-purpose processors but have not been successful because of their lack of sufficient control speculation and the latency overhead of explicit communication. This article observes a synergy between out-of-order (OoO) and explicit dataflow processors, in which dynamically switching between them according to program phases can greatly improve performance and energy efficiency.