Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Physical Sciences and Mathematics
Simulated Performance Of A Reduction-Based Multiprocessing System, Robert M. Keller, Frank C. H. Lin
Simulated Performance Of A Reduction-Based Multiprocessing System, Robert M. Keller, Frank C. H. Lin
All HMC Faculty Publications and Research
Multiprocessing systems have the potential for increasing system speed over what is now offered by device technology. They must provide the means of generating work for the processors, getting the work to processors, and coherently collecting the results from the processors. For most applications, they should also ensure the repeatability of behavior, i.e., determinacy, speed-independence, or elimination of "critical races." Determinacy can be destroyed, for example, by permitting-in separate, concurrent processes statements such as "x: = x + 1" and "if x = 0 then… else…", which share a common variable. Here, there may be a critical race, in that …
Rediflow Multiprocessing, Robert M. Keller, Frank C. H. Lin, Jiro Tanaka
Rediflow Multiprocessing, Robert M. Keller, Frank C. H. Lin, Jiro Tanaka
All HMC Faculty Publications and Research
We discuss the concepts underlying Rediflow, a multiprocessing system being designed to support concurrent programming through a hybrid model of reduction, dataflow, and von Neumann processes. The techniques of automatic load-balancing in Rediflow are described in some detail.
Hierarchical Analysis Of A Distributed Evaluator, Robert M. Keller, Gary Lindstrom
Hierarchical Analysis Of A Distributed Evaluator, Robert M. Keller, Gary Lindstrom
All HMC Faculty Publications and Research
We outline the analysis of a distributed evaluator for an applicative language FGL (Function Graph Language). Our goal is to show that the least fixed point semantics of FGL are faithfully implemented by the hardware evaluator envisioned in the Applicative Multi-Processor System AMPS. Included in the analysis are a formalization of demand-driven computation , the introduction of an intermediate graphic language IGL to aid in our proofs, and discussion of pragmatic issues involved in the AMPS machine language design.