Image matrix processor for fast multidimensional computations
Abstract
An apparatus for multidimensional computation which comprises a computation engine, including a plurality of processing modules. The processing modules are configured in parallel and compute respective contributions to a computed multidimensional image of respective two dimensional data sets. A highspeed, parallel access storage system is provided which stores the multidimensional data sets, and a switching circuit routes the data among the processing modules in the computation engine and the storage system. A data acquisition port receives the two dimensional data sets representing projections through an image, for reconstruction algorithms such as encountered in computerized tomography. The processing modules include a programmable local host, by which they may be configured to execute a plurality of different types of multidimensional algorithms. The processing modules thus include an image manipulation processor, which includes a source cache, a target cache, a coefficient table, and control software for executing image transformation routines using data in the source cache and the coefficient table and loading resulting data in the target cache. The local host processor operates to load the source cache with a two dimensional data set, loads the coefficient table, and transfers resulting data out of the target cache to the storage system, or tomore »
 Inventors:

 Tracy, CA
 Livermore, CA
 Issue Date:
 Research Org.:
 Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
 OSTI Identifier:
 870645
 Patent Number(s):
 5566341
 Assignee:
 Regents of University of California (Oakland, CA)
 Patent Classifications (CPCs):

G  PHYSICS G06  COMPUTING G06F  ELECTRIC DIGITAL DATA PROCESSING
 DOE Contract Number:
 W7405ENG48
 Resource Type:
 Patent
 Country of Publication:
 United States
 Language:
 English
 Subject:
 image; matrix; processor; fast; multidimensional; computations; apparatus; computation; comprises; engine; including; plurality; processing; modules; configured; parallel; compute; respective; contributions; computed; dimensional; data; sets; highspeed; access; storage; provided; stores; switching; circuit; routes; acquisition; receives; representing; projections; reconstruction; algorithms; encountered; computerized; tomography; programmable; local; host; execute; types; manipulation; source; cache; target; coefficient; table; control; software; executing; transformation; routines; loading; resulting; operates; load; set; loads; transfers; destination; processing modules; local host; data acquisition; data set; switching circuit; data sets; resulting data; dimensional data; dimensional image; multidimensional computation; host processor; processing module; computerized tomography; /712/
Citation Formats
Roberson, George P, and Skeate, Michael F. Image matrix processor for fast multidimensional computations. United States: N. p., 1996.
Web.
Roberson, George P, & Skeate, Michael F. Image matrix processor for fast multidimensional computations. United States.
Roberson, George P, and Skeate, Michael F. Mon .
"Image matrix processor for fast multidimensional computations". United States. https://www.osti.gov/servlets/purl/870645.
@article{osti_870645,
title = {Image matrix processor for fast multidimensional computations},
author = {Roberson, George P and Skeate, Michael F},
abstractNote = {An apparatus for multidimensional computation which comprises a computation engine, including a plurality of processing modules. The processing modules are configured in parallel and compute respective contributions to a computed multidimensional image of respective two dimensional data sets. A highspeed, parallel access storage system is provided which stores the multidimensional data sets, and a switching circuit routes the data among the processing modules in the computation engine and the storage system. A data acquisition port receives the two dimensional data sets representing projections through an image, for reconstruction algorithms such as encountered in computerized tomography. The processing modules include a programmable local host, by which they may be configured to execute a plurality of different types of multidimensional algorithms. The processing modules thus include an image manipulation processor, which includes a source cache, a target cache, a coefficient table, and control software for executing image transformation routines using data in the source cache and the coefficient table and loading resulting data in the target cache. The local host processor operates to load the source cache with a two dimensional data set, loads the coefficient table, and transfers resulting data out of the target cache to the storage system, or to another destination.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {1996},
month = {1}
}
Works referenced in this record:
Practical conebeam algorithm
journal, January 1984
 Feldkamp, L. A.; Davis, L. C.; Kress, J. W.
 Journal of the Optical Society of America A, Vol. 1, Issue 6