Alternative parallel implementations of an AR-modified covariance spectral estimator for diagnostic ultrasonic blood flow studies

Ruano, M. Graça; Nocetti, D. F. G.; Fish, P. J.; Fleming, P. J.

http://hdl.handle.net/10400.1/5888

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
1993_Alternative_ParallelComputing_19.pdf		8.71 MB	Adobe PDF	Download

Send Feedback

Authors

Abstract(s)

The work described here is part of a research program aiming to increase the sensitivity to desease detection using Doppler ultrasound by reducing the effects of the measurement procedure on the estimation of blood velocity and detection of flow disturbance. The paper presents a summary of autoregressive spectral estimation, focusing the attention on a specific estimator - the modified covariance method. This method has been realized in parallel to achieve a fast computer processing. The new parallel version of this algorithm has been developed and implemented on a multiprocessing transputer-based system. Two different approaches to the problem of parallel partitioning the algorithm into a number of tasks were considered - a fine and a medium grain task scheme. The medium grain scheme is mapped onto a transputer-based system, by means of a processor farm computational structure. Two approaches to this farm model were adopted: a linear and a tree topology. For different model parameters, performance measurements were obtained revealing that the tree topology offers a higher performance. © 1993.