Algorithm and architecture for multi-argument associative operations that minimizes the number of components using a latency of the components

摘要

An algorithm and architecture are disclosed for performing multi-argument associative operations. The algorithm and architecture can be used to schedule operations on multiple facilities for computations or can be used in the development of a model in a modeling environment. The algorithm and architecture resulting from the algorithm use the latency of the components that are used to process the associative operations. The algorithm minimizes the number of components necessary to produce an output of multi-argument associative operations and also can minimize the number of inputs each component receives.

主权项

1. A method comprising:
interacting with a modeling environment using a processor, where the modeling environment:
executes a model, anddetermines a number of a plurality of facilities for computations to perform one or more associative operations in the model; and scheduling the plurality of facilities for computations to perform the one or more associative operations, the scheduling comprising:
interacting with a representation of the plurality of facilities for computations, wherein:
the representation comprises a first facility for computation and a second facility for computation from among the plurality of facilities for computations,the first facility for computation has a first latency, the first latency representing an amount of time for the first facility for computation to perform a first computation,the first facility for computation has a first position within the model and provides an output to a receiving facility for computation,the second facility for computation has a second latency, the second latency:
representing an amount of time for the second facility for computation to perform a second computation, andrepresenting a smaller amount of time than the first latency, andthe second facility for computation has a second position in the model;anddynamically reconfiguring the plurality of facilities for computations, the dynamically reconfiguring comprising:
comparing the first latency to the second latency to determine that an overall latency of the model may be reduced by swapping the first position of the first facility for computation and the second position of the second facility for computation so that the second facility for computation provides an output to the receiving facility for computation, andswapping the first position of the first facility for computation with the second position of the second facility for computation in the model.