Enhanced ATAMM for increased throughput performance of multicomputer data flow architecturesThe Algorithm To Architecture Mapping Model (ATAMM) is a Petri-net-based model which provides a strategy for periodic execution of a class of real-time algorithms on multicomputer dataflow architectures. The problem domain of particular interest is the execution of large-grained, decision-free algorithms on homogeneous processing elements. Design techniques are discussed and performance measurements are defined. A multiple-graph execution strategy is shown to increase throughput performance. It is shown that the same increase in performance is attainable with minor modifications to the existing ATAMM.
Document ID
19920065825
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Jones, R. L. (NASA Langley Research Center Hampton, VA, United States)
Hayes, P. J. (NASA Langley Research Center Hampton, VA, United States)
Andrews, A. M. (Lockheed Engineering and Sciences Co. Hampton, VA, United States)
Som, S. (NASA Langley Research Center Hampton, VA, United States)
Stoughton, J. W. (NASA Langley Research Center Hampton, VA, United States)
Mielke, R. R. (Old Dominion University Norfolk, VA, United States)
Date Acquired
August 15, 2013
Publication Date
January 1, 1991
Subject Category
Systems Analysis
Meeting Information
Meeting: NAECON 91: IEEE National Aerospace and Electronics Conference