Image matrix processor for fast multi-dimensional computations
- 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 (United States)
- 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
Center for Technology for Advanced Scientific Componet Software (TASCS)
Data Locality Enhancement of Dynamic Simulations for Exascale Computing (Final Report)
Related Subjects
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/