Efficient SIMD evaluation of image processing programs
J. Wilson, and E. Riedy. Parallel and Distributed Methods for Image Processing, 3166, page 199--210. San Diego, CA, SPIE, (1997)
DOI: 10.1117/12.279618
Abstract
SIMD parallel systems have been employed for image
processing and computer vision applications since
their inception. This paper describes a system in
which parallel programs are implemented using a
machine-independent, retargetable object library
that provides SIMD execution on the Lockheed Martin
PAL-I SIMD parallel processor. Programs' performance
on this machine is improved through on-the-fly
execution analysis and scheduling. We describe the
relevant elements of the system structure, the
general scheme for execution analysis, and the
current cost model for scheduling.
%0 Conference Paper
%1 ia-cost
%A Wilson, Joseph N.
%A Riedy, E. Jason
%B Parallel and Distributed Methods for Image Processing
%C San Diego, CA
%D 1997
%E Shi, Hongchi
%E Coffield, Patrick C.
%K imagealgebra parallelalgorithms spie
%P 199--210
%R 10.1117/12.279618
%T Efficient SIMD evaluation of image processing programs
%U http://purl.oclc.org/NET/jason-riedy/resume/material/ia-cost.pdf
%V 3166
%X SIMD parallel systems have been employed for image
processing and computer vision applications since
their inception. This paper describes a system in
which parallel programs are implemented using a
machine-independent, retargetable object library
that provides SIMD execution on the Lockheed Martin
PAL-I SIMD parallel processor. Programs' performance
on this machine is improved through on-the-fly
execution analysis and scheduling. We describe the
relevant elements of the system structure, the
general scheme for execution analysis, and the
current cost model for scheduling.
@inproceedings{ia-cost,
abstract = {SIMD parallel systems have been employed for image
processing and computer vision applications since
their inception. This paper describes a system in
which parallel programs are implemented using a
machine-independent, retargetable object library
that provides SIMD execution on the Lockheed Martin
PAL-I SIMD parallel processor. Programs' performance
on this machine is improved through on-the-fly
execution analysis and scheduling. We describe the
relevant elements of the system structure, the
general scheme for execution analysis, and the
current cost model for scheduling.},
added-at = {2007-10-09T06:58:21.000+0200},
address = {San Diego, CA},
author = {Wilson, Joseph N. and Riedy, E. Jason},
biburl = {https://www.bibsonomy.org/bibtex/2b54dd0285c02f86cbd61d1ac124ad058/ejr},
booktitle = {Parallel and Distributed Methods for Image Processing},
doi = {10.1117/12.279618},
editor = {Shi, Hongchi and Coffield, Patrick C.},
ejr-withauthor = {Joseph N. Wilson},
interhash = {5129553f28c5dc0829626e8ba6a0c21b},
intrahash = {b54dd0285c02f86cbd61d1ac124ad058},
keywords = {imagealgebra parallelalgorithms spie},
organization = {SPIE},
pages = {199--210},
role = {proceedings},
timestamp = {2007-10-09T07:08:11.000+0200},
title = {Efficient {SIMD} evaluation of image processing programs},
url = {http://purl.oclc.org/NET/jason-riedy/resume/material/ia-cost.pdf},
volume = 3166,
year = 1997
}