Restoration of star-field images using high-level languages and core libraries

R. Bruce, C. Ruet, M. Devlin, S. Marshall

Research output: Contribution to conferencePaper

Abstract

Research into the use of FPGAs in Image Processing began in earnest at the beginning of the 1990s. Since then, many thousands of publications have pointed to the computational capabilities of FPGAs. During this time, FPGAs have seen the application space to which they are applicable grow in tandem with their logic densities. When investigating a particular application, researchers compare FPGAs with alternative technologies such as Digital Signal Processors (DSPs), Application-Specific Integrated Cir-cuits (ASICs), microprocessors and vector processors. The metrics for comparison depend on the needs of the application, and include such measurements as: raw performance, power consumption, unit cost, board footprint, non-recurring engineering cost, design time and design cost. The key metrics for a par-ticular application may also include ratios of these metrics, e.g. power/performance, or performance/unit cost. The work detailed in this paper compares a 90nm-process commodity microprocessor with a plat-form based around a 90nm-process FPGA, focussing on design time and raw performance.
The application chosen for implementation was a minimum entropy restoration of star-field images (see [1] for an introduction), with simulated annealing used to converge towards the globally-optimum solution. This application was not chosen in the belief that it would particularly suit one technology over another, but was instead selected as being representative of a computationally intense image-processing application.

Conference

Conference3rd Manchester Reconfigurable Supercomputing Conference
Abbreviated titleMRSC 2007
CountryUnited Kingdom
CityManchester
Period28/03/0729/03/07

Fingerprint

High level languages
Restoration
Stars
Field programmable gate arrays (FPGA)
Microprocessor chips
Costs
Image processing
Space applications
Digital signal processors
Simulated annealing
Electric power utilization
Entropy

Keywords

  • star-formation
  • star-field images
  • floating-point cost function
  • convolution
  • high-level languages
  • core libraries

Cite this

Bruce, R., Ruet, C., Devlin, M., & Marshall, S. (2007). Restoration of star-field images using high-level languages and core libraries. Paper presented at 3rd Manchester Reconfigurable Supercomputing Conference, Manchester, United Kingdom.
Bruce, R. ; Ruet, C. ; Devlin, M. ; Marshall, S. / Restoration of star-field images using high-level languages and core libraries. Paper presented at 3rd Manchester Reconfigurable Supercomputing Conference, Manchester, United Kingdom.27 p.
@conference{eea819a6d39f4a07a1a106f8095de46f,
title = "Restoration of star-field images using high-level languages and core libraries",
abstract = "Research into the use of FPGAs in Image Processing began in earnest at the beginning of the 1990s. Since then, many thousands of publications have pointed to the computational capabilities of FPGAs. During this time, FPGAs have seen the application space to which they are applicable grow in tandem with their logic densities. When investigating a particular application, researchers compare FPGAs with alternative technologies such as Digital Signal Processors (DSPs), Application-Specific Integrated Cir-cuits (ASICs), microprocessors and vector processors. The metrics for comparison depend on the needs of the application, and include such measurements as: raw performance, power consumption, unit cost, board footprint, non-recurring engineering cost, design time and design cost. The key metrics for a par-ticular application may also include ratios of these metrics, e.g. power/performance, or performance/unit cost. The work detailed in this paper compares a 90nm-process commodity microprocessor with a plat-form based around a 90nm-process FPGA, focussing on design time and raw performance. The application chosen for implementation was a minimum entropy restoration of star-field images (see [1] for an introduction), with simulated annealing used to converge towards the globally-optimum solution. This application was not chosen in the belief that it would particularly suit one technology over another, but was instead selected as being representative of a computationally intense image-processing application.",
keywords = "star-formation, star-field images, floating-point cost function , convolution, high-level languages , core libraries",
author = "R. Bruce and C. Ruet and M. Devlin and S. Marshall",
year = "2007",
language = "English",
note = "3rd Manchester Reconfigurable Supercomputing Conference, MRSC 2007 ; Conference date: 28-03-2007 Through 29-03-2007",

}

Bruce, R, Ruet, C, Devlin, M & Marshall, S 2007, 'Restoration of star-field images using high-level languages and core libraries' Paper presented at 3rd Manchester Reconfigurable Supercomputing Conference, Manchester, United Kingdom, 28/03/07 - 29/03/07, .

Restoration of star-field images using high-level languages and core libraries. / Bruce, R.; Ruet, C.; Devlin, M.; Marshall, S.

2007. Paper presented at 3rd Manchester Reconfigurable Supercomputing Conference, Manchester, United Kingdom.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Restoration of star-field images using high-level languages and core libraries

AU - Bruce, R.

AU - Ruet, C.

AU - Devlin, M.

AU - Marshall, S.

PY - 2007

Y1 - 2007

N2 - Research into the use of FPGAs in Image Processing began in earnest at the beginning of the 1990s. Since then, many thousands of publications have pointed to the computational capabilities of FPGAs. During this time, FPGAs have seen the application space to which they are applicable grow in tandem with their logic densities. When investigating a particular application, researchers compare FPGAs with alternative technologies such as Digital Signal Processors (DSPs), Application-Specific Integrated Cir-cuits (ASICs), microprocessors and vector processors. The metrics for comparison depend on the needs of the application, and include such measurements as: raw performance, power consumption, unit cost, board footprint, non-recurring engineering cost, design time and design cost. The key metrics for a par-ticular application may also include ratios of these metrics, e.g. power/performance, or performance/unit cost. The work detailed in this paper compares a 90nm-process commodity microprocessor with a plat-form based around a 90nm-process FPGA, focussing on design time and raw performance. The application chosen for implementation was a minimum entropy restoration of star-field images (see [1] for an introduction), with simulated annealing used to converge towards the globally-optimum solution. This application was not chosen in the belief that it would particularly suit one technology over another, but was instead selected as being representative of a computationally intense image-processing application.

AB - Research into the use of FPGAs in Image Processing began in earnest at the beginning of the 1990s. Since then, many thousands of publications have pointed to the computational capabilities of FPGAs. During this time, FPGAs have seen the application space to which they are applicable grow in tandem with their logic densities. When investigating a particular application, researchers compare FPGAs with alternative technologies such as Digital Signal Processors (DSPs), Application-Specific Integrated Cir-cuits (ASICs), microprocessors and vector processors. The metrics for comparison depend on the needs of the application, and include such measurements as: raw performance, power consumption, unit cost, board footprint, non-recurring engineering cost, design time and design cost. The key metrics for a par-ticular application may also include ratios of these metrics, e.g. power/performance, or performance/unit cost. The work detailed in this paper compares a 90nm-process commodity microprocessor with a plat-form based around a 90nm-process FPGA, focussing on design time and raw performance. The application chosen for implementation was a minimum entropy restoration of star-field images (see [1] for an introduction), with simulated annealing used to converge towards the globally-optimum solution. This application was not chosen in the belief that it would particularly suit one technology over another, but was instead selected as being representative of a computationally intense image-processing application.

KW - star-formation

KW - star-field images

KW - floating-point cost function

KW - convolution

KW - high-level languages

KW - core libraries

UR - http://skinto.files.wordpress.com/2008/07/mrsc07.ppt

UR - http://skinto.files.wordpress.com/2008/07/mrsc07.doc

M3 - Paper

ER -

Bruce R, Ruet C, Devlin M, Marshall S. Restoration of star-field images using high-level languages and core libraries. 2007. Paper presented at 3rd Manchester Reconfigurable Supercomputing Conference, Manchester, United Kingdom.