# Image matrix processor for fast multi-dimensional computations

## Abstract

An apparatus for multi-dimensional 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 multi-dimensional image of respective two dimensional data sets. A high-speed, parallel access storage system is provided which stores the multi-dimensional 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 multi-dimensional 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 Lab. (LLNL), Livermore, CA (United States)

- OSTI Identifier:
- 870645

- Patent Number(s):
- 5566341

- Assignee:
- Regents of University of California (Oakland, CA) LLNL

- DOE Contract Number:
- W-7405-ENG-48

- Resource Type:
- Patent

- Country of Publication:
- United States

- Language:
- English

- Subject:
- image; matrix; processor; fast; multi-dimensional; computations; apparatus; computation; comprises; engine; including; plurality; processing; modules; configured; parallel; compute; respective; contributions; computed; dimensional; data; sets; high-speed; 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; multi-dimensional computation; host processor; processing module; computerized tomography; /712/

### Citation Formats

```
Roberson, George P., and Skeate, Michael F.
```*Image matrix processor for fast multi-dimensional computations*. United States: N. p., 1996.
Web.

```
Roberson, George P., & Skeate, Michael F.
```*Image matrix processor for fast multi-dimensional computations*. United States.

```
Roberson, George P., and Skeate, Michael F. Mon .
"Image matrix processor for fast multi-dimensional computations". United States. https://www.osti.gov/servlets/purl/870645.
```

```
@article{osti_870645,
```

title = {Image matrix processor for fast multi-dimensional computations},

author = {Roberson, George P. and Skeate, Michael F.},

abstractNote = {An apparatus for multi-dimensional 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 multi-dimensional image of respective two dimensional data sets. A high-speed, parallel access storage system is provided which stores the multi-dimensional 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 multi-dimensional 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}

}