Experiments with data flow on a general-purpose parallel computer. Memorandum report
The MIT J-Machine, a massively-parallel computer, is an experiment in providing general-purpose mechanisms for communication, synchronization, and naming that will support a wide variety of parallel models of computation. Having universal mechanisms allows the separation of issues of language design and machine organization. The authors have developed two experimental dataflow programming systems for the J-Machine. For the first system, they adapted Papadopoulos' explicit token store to implement static and then dynamic dataflow. Each node in a dataflow graph is expanded into a sequence of code, each of which is scheduled individually at runtime. For a later system, they made use of Iannucci's hybrid execution model to combine several dataflow graph nodes into a single sequence, decreasing scheduling overhead. By combining the strengths of the two systems, it is possible to produce a system with competitive performance. They have demonstrated the feasibility of efficiently executing dataflow programs on a general purpose parallel computer.
- Research Organization:
- Massachusetts Inst. of Tech., Cambridge, MA (United States). Artificial Intelligence Lab.
- OSTI ID:
- 5216076
- Report Number(s):
- AD-A-235521/2/XAB; AI-M-1272; CNN: N00014-85-K-0124; N00014-88-K-0738
- Resource Relation:
- Other Information: Sponsored in part by Contract N00014-87-K-0825 and MIP-8657531
- Country of Publication:
- United States
- Language:
- English
Similar Records
ARENA: Asynchronous Reconfigurable Accelerator Ring to Enable Data-Centric Parallel Computing
Executing a program on the MIT tagged-token dataflow architecture