US5566341A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Image matrix processor for fast multi-dimensional computations
Assignee: University of California
•
Filing: 1992-10-05
•
Granted: 1996-10-15
•
Expires: 2012-10-05
Abstract
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 to another destination.
Inventors
- 👤 George P. Roberson
- 👤 Michael F. Skeate
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 16:45
CPC Classifications
G; G06; G06F; G06F17/00; G06F17/10; G06F17/16
Claims Analysis
Total Claims: 22
Claim 1
Independent Claim
134 words
An apparatus for multi-dimensional computations, comprising: a computation engine including a plurality of processing modules, the processing modules in the plurality configured in parallel and computing respective contributions to a computed multi-dimensional image of respective two dimensional data sets; storage means for storing multi-dimensional data sets; and at least one fast packet routing switch coupled to the plurality of processing modules in the computation engine and to the storage means, for routing data among the plurality of processing modules in the computation engine and the storage means, wherein said at least one fast packet routing switch is capable of a dynamic topology wherein any geometric matrix of processors and said processing modules can be attained and there is a direct connection of any said processing module to all other said plurality of processing modules.
Claim 2
Independent Claim
134 words
An apparatus for multi-dimensional computations, comprising: a computation engine including a plurality of processing modules, the processing modules in the plurality configured in parallel and computing respective contributions to a computed multi-dimensional image of respective two dimensional data sets; storage means for storing multi-dimensional data sets; and at least one fast packet routing switch coupled to the plurality of processing modules in the computation engine and to the storage means, for routing data among the plurality of processing modules in the computation engine and the storage means, wherein said at least one fast packet routing switch is capable of a dynamic topology wherein any geometric matrix of processors and said processing modules can be attained and there is a direct connection of any said processing module to all other said plurality of processing modules.
Claim 3
Dependent Claim
29 words
The apparatus of claim 1, further including: a data acquisition port, coupled to the switching means, for receiving two dimensional data sets representing two-dimensional tomographic projections through an object.
Claim 4
Dependent Claim
35 words
The apparatus of claim 1, wherein the computation engine includes means, coupled with the plurality of processing modules, for configuring the plurality of processing modules to execute a plurality of different types of multi-dimensional algorithms.
Claim 5
Dependent Claim
93 words
The apparatus of claim 1, wherein at least one of the processing modules in the plurality comprises: an image manipulation processor, including a source cache, a target cache, a coefficient table, and control for executing image transformation routines using data in the source cache and the coefficient table, and for loading resulting data in the target cache; a local host processor including means for loading the source cache with a two-dimensional data set, means for loading the coefficient table with coefficients, and means for transferring the resulting data out of the target cache.
Claim 6
Dependent Claim
26 words
The apparatus of claim 4, wherein the means for loading the source cache in the local host processor includes: means for filtering the two-dimensional data set.
Claim 7
Dependent Claim
73 words
The apparatus of claim 4, wherein the image manipulation processor includes: means, coupled with the source cache, coefficient table and target cache, for generating addresses for the source cache, coefficient table and target cache; and means, coupled with the source cache, coefficient table and target cache, for arithmetic processing of data from addressed locations in the source cache and coefficient table and for supplying resulting data to addressed locations in the target cache.
Claim 8
Dependent Claim
24 words
The apparatus of claim 1, wherein the storage means comprises: a plurality of memory cells with parallel access paths for high speed data transfers.
Claim 9
Dependent Claim
15 words
The apparatus of claim 7, wherein the memory cells comprise independent direct access storage devices.
Claim 10
Dependent Claim
28 words
The apparatus of claim 1, further including: display means, coupled to the switching means, for displaying an image in response to multi-dimensional data sets in the storage means.
Claim 11
Dependent Claim
186 words
A plurality of processing modules for computation of a multi-dimensional image from projection data representing a two dimensional projection, wherein at least one processing module of said plurality of processing modules comprises: an image manipulation processor, including a source cache, a target cache, a coefficient table, and control for executing image transformation routines using data in the source cache and the coefficient table, and for loading resulting data in the target cache; a local host processor including means for loading the source cache with projection data, means for loading the coefficient table with coefficients, and means for transferring the resulting data out of the target cachet, and at least one fast packet routing switch coupled to the plurality of processing modules and to the source cache, for routing data among the plurality of processing modules and the source cache, wherein said at least one fast packet routing switch is capable of a dynamic topology wherein any geometric matrix of processors and said processing modules can be attained and there is a direct connection of any said processing module to all other said plurality of processing modules.
Claim 12
Dependent Claim
186 words
A plurality of processing modules for computation of a multi-dimensional image from projection data representing a two dimensional projection, wherein at least one processing module of said plurality of processing modules comprises: an image manipulation processor, including a source cache, a target cache, a coefficient table, and control for executing image transformation routines using data in the source cache and the coefficient table, and for loading resulting data in the target cache; a local host processor including means for loading the source cache with projection data, means for loading the coefficient table with coefficients, and means for transferring the resulting data out of the target cachet, and at least one fast packet routing switch coupled to the plurality of processing modules and to the source cache, for routing data among the plurality of processing modules and the source cache, wherein said at least one fast packet routing switch is capable of a dynamic topology wherein any geometric matrix of processors and said processing modules can be attained and there is a direct connection of any said processing module to all other said plurality of processing modules.
Claim 13
Dependent Claim
25 words
The apparatus of claim 10, wherein the means for loading the source cache in the local host processor includes: means for filtering the projection data.
Claim 14
Dependent Claim
73 words
The apparatus of claim 10, wherein the image manipulation processor includes: means, coupled with the source cache, coefficient table and target cache, for generating addresses for the source cache, coefficient table and target cache; and means, coupled with the source cache, coefficient table and target cache, for arithmetic processing of data from addressed locations in the source cache and coefficient table and for supplying resulting data to addressed locations in the target cache.
Claim 15
Dependent Claim
112 words
The apparatus of claim 10, wherein the image manipulation processor includes: addressing means, coupled with the source cache, coefficient table and target cache, for generating addresses for the source cache, coefficient table and target cache; and execution means, coupled with the source cache, coefficient table and target cache, for arithmetic processing of data from addressed locations in the source cache and coefficient table and for supplying resulting data to addressed locations in the target cache; and wherein the local host processor includes programming means, coupled with the addressing means and the execution means, for configuring the execution means and the addressing means to execute a plurality of different types of multi-dimensional algorithms.
Claim 16
Independent Claim
309 words
An apparatus for executing a cone-beam image reconstruction algorithm from a plurality of cone-beam projections through an object, comprising; a data acquisition port for receiving two dimensional projection data; a reconstruction engine, coupled to the data acquisition port, including a plurality of processing modules, the processing modules in the plurality configured in parallel and including an image manipulation processor, including a source cache, a target cache, a coefficient table, and control for executing programmable image transformation routines using data in the source cache and the coefficient table, and for loading resulting data in the target cache; a local host processor including means for loading the source cache with projection data from a respective cone-beam projection, means for loading the coefficient table with coefficients, means for configuring the image manipulation processor, and means for transferring the resulting data out of the target cache to compute respective contributions to a reconstructed image of respective cone-beam projections; storage means, coupled to the reconstruction engine, for storing the respective contributions in a data set representing a reconstructed image, including a plurality of memory cells with parallel access paths for high speed data transfers; at least one fast packet routing switch coupled to the data acquisition port, the plurality of processing modules in the reconstruction engine, and the storage means, for routing data among the data acquisition port, the plurality of processing modules in the reconstruction engine, and the storage means, wherein said at least one fast packet routing switch is capable of a dynamic topology wherein any geometric matrix of processors and said processing modules can be attained and there is a direct connection of any said processing module to all other said plurality of processing modules; and display means, coupled to the switching means, for displaying an image in response to the data set representing the reconstructed image in the storage means.
Claim 17
Independent Claim
309 words
An apparatus for executing a cone-beam image reconstruction algorithm from a plurality of cone-beam projections through an object, comprising; a data acquisition port for receiving two dimensional projection data; a reconstruction engine, coupled to the data acquisition port, including a plurality of processing modules, the processing modules in the plurality configured in parallel and including an image manipulation processor, including a source cache, a target cache, a coefficient table, and control for executing programmable image transformation routines using data in the source cache and the coefficient table, and for loading resulting data in the target cache; a local host processor including means for loading the source cache with projection data from a respective cone-beam projection, means for loading the coefficient table with coefficients, means for configuring the image manipulation processor, and means for transferring the resulting data out of the target cache to compute respective contributions to a reconstructed image of respective cone-beam projections; storage means, coupled to the reconstruction engine, for storing the respective contributions in a data set representing a reconstructed image, including a plurality of memory cells with parallel access paths for high speed data transfers; at least one fast packet routing switch coupled to the data acquisition port, the plurality of processing modules in the reconstruction engine, and the storage means, for routing data among the data acquisition port, the plurality of processing modules in the reconstruction engine, and the storage means, wherein said at least one fast packet routing switch is capable of a dynamic topology wherein any geometric matrix of processors and said processing modules can be attained and there is a direct connection of any said processing module to all other said plurality of processing modules; and display means, coupled to the switching means, for displaying an image in response to the data set representing the reconstructed image in the storage means.
Claim 18
Dependent Claim
35 words
The apparatus of claim 14, wherein the reconstruction engine includes means, coupled with the plurality of processing modules, for configuring the plurality of processing modules to execute a plurality of different types of reconstruction algorithms.
Claim 19
Dependent Claim
25 words
The apparatus of claim 14, wherein the means for loading the source cache in the local host processor includes: means for filtering the projection data.
Claim 20
Dependent Claim
73 words
The apparatus of claim 14, wherein the image manipulation processor includes: means, coupled with the source cache, coefficient table and target cache, for generating addresses for the source cache, coefficient table and target cache; and means, coupled with the source cache, coefficient table and target cache, for arithmetic processing of data from addressed locations in the source cache and coefficient table and for supplying resulting data to addressed locations in the target cache.
Claim 21
Dependent Claim
20 words
The apparatus of claim 14, wherein the local host processors comprise transputers having a plurality of high speed communication ports.
Claim 22
Dependent Claim
15 words
The apparatus of claim 14, wherein the memory cells comprise independent direct access storage devices.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1999-10-15 | 2000-04-15 | 2000-10-15 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2003-10-15 | 2004-04-15 | 2004-10-15 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2007-10-15 | 2008-04-15 | 2008-10-15 | $7700.00 | Window Closed / Lapsed |