Image matrix processor for fast multi-dimensional computations
Patent
·
OSTI ID:870645
- Tracy, CA
- Livermore, CA
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.
- Research Organization:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA
- DOE Contract Number:
- W-7405-ENG-48
- Assignee:
- Regents of University of California (Oakland, CA)
- Patent Number(s):
- US 5566341
- OSTI ID:
- 870645
- Country of Publication:
- United States
- Language:
- English
Practical cone-beam algorithm
|
journal | January 1984 |
Similar Records
Image matrix processor for fast multi-dimensional computations
Mechanism of supporting sub-communicator collectives with o(64) counters as opposed to one counter for each sub-communicator
Mechanism of supporting sub-communicator collectives with O(64) counters as opposed to one counter for each sub-communicator
Patent
·
Tue Oct 15 00:00:00 EDT 1996
·
OSTI ID:379935
Mechanism of supporting sub-communicator collectives with o(64) counters as opposed to one counter for each sub-communicator
Patent
·
Mon Jan 25 23:00:00 EST 2016
·
OSTI ID:1236466
Mechanism of supporting sub-communicator collectives with O(64) counters as opposed to one counter for each sub-communicator
Patent
·
Tue Sep 03 00:00:00 EDT 2013
·
OSTI ID:1092900
Related Subjects
/712/
access
acquisition
algorithms
apparatus
cache
circuit
coefficient
comprises
computation
computations
compute
computed
computerized
computerized tomography
configured
contributions
control
data
data acquisition
data set
data sets
destination
dimensional
dimensional data
dimensional image
encountered
engine
execute
executing
fast
high-speed
host
host processor
image
including
load
loading
loads
local
local host
manipulation
matrix
modules
multi-dimensional
multi-dimensional computation
operates
parallel
plurality
processing
processing module
processing modules
processor
programmable
projections
provided
receives
reconstruction
representing
respective
resulting
resulting data
routes
routines
set
sets
software
source
storage
stores
switching
switching circuit
table
target
tomography
transfers
transformation
types
access
acquisition
algorithms
apparatus
cache
circuit
coefficient
comprises
computation
computations
compute
computed
computerized
computerized tomography
configured
contributions
control
data
data acquisition
data set
data sets
destination
dimensional
dimensional data
dimensional image
encountered
engine
execute
executing
fast
high-speed
host
host processor
image
including
load
loading
loads
local
local host
manipulation
matrix
modules
multi-dimensional
multi-dimensional computation
operates
parallel
plurality
processing
processing module
processing modules
processor
programmable
projections
provided
receives
reconstruction
representing
respective
resulting
resulting data
routes
routines
set
sets
software
source
storage
stores
switching
switching circuit
table
target
tomography
transfers
transformation
types