Executing a Program on the MIT Tagged-Token Dataflow Architecture

By Arvind, R. Nikhil. 1987

Subfields: ML Systems & Hardware

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In ML Systems & Hardware

1. Derek Gordon Murray
2. Michael Isard
3. Martín Abadi
4. John Hughes
5. Simon L. Peyton Jones
6. Paul Hudak
7. Philip Wadler
8. Geoffrey E. Hinton

Citations in the corpus

• A computational model for TensorFlow: an introduction (2017, methodology): “In the TensorFlow implementation, they are mapped to dataflow primitives, as in tagged dataflow architectures [6, 7].”
• A history of Haskell: being lazy with class (2007, methodology): “While SASL and KRC were untyped, Miranda added strong polymorphic typing and type inference, ideas that had proven very successful in ML. • Lazy ML (LML), pioneered at Chalmers by Augustsson and Johnsson, and taken up at University College London by Peyton Jones.”
• Dynamic control flow in large-scale machine learning (2018, unknown): “In our work, high-level control-flow constructs are compiled to dataflow graphs that include a few simple, powerful primitives similar to those of dynamic dataflow machines [4, 5].”
• HPX: A Task Based Programming Model in a Global Address Space (2014, background): “• Dataflow objects [38, 46, 47] provide a powerful mechanism for managing data dependencies without the use of global barriers.”