GoDEL: A Multidirectional Dataflow Execution Model for Large-Scale Computing
As the emerging trends in hardware architecture guided by performance, power efficiency and complexity drive one towards massive processor parallelism; there has been a renewed interest in dataflow models for large-scale computing. Dataflow programming models, being declarative in nature, lead to improved programmability at scale by implicitly managing the computation and communication for the application. In this paper, the authors present GoDEL, a multidirectional dataflow execution model based on propagation networks. Propagator networks allow general-purpose parallel computation on partial data. Implemented with efficiency and programmer productivity as its goals, they describe the syntax and semantics of the GoDEL language and discuss its implementation and runtime.