IPAS: a design framework for analysis, synthesis and optimization of image processing applications for heterogenous computing architectures

Special Issue Paper

DOI: 10.1007/s11554-016-0587-x

Cite this article as:
Hartmann, C., Häublein, K., Reichenbach, M. et al. J Real-Time Image Proc (2016). doi:10.1007/s11554-016-0587-x
  • 121 Downloads

Abstract

Recent trends in the image processing field have led to the use of more heterogeneous hardware architectures. The reason for this increase is that specialized cores, compared to standard CPUs, offer a more efficient way of achieving image processing applications. Specialized cores have less power, resource, and area consumption. On the other hand, designing such a heterogenous system with specialized cores is a challenging, error-prone and time-consuming task. Therefore, new frameworks are necessary for bringing an image processing application onto a given target platform by means of a tool chain. Some frameworks exist, but they do not address each need of a heterogeneous image processing application. Common weaknesses are (1) the low utilization of the image processing domain, (2) the inflexibility of the programming paradigms for different hardware architectures. Therefore, we define our own domain-specific design language called IPOL. To automate the derivation and optimization process, a synthesis tool named Image Processing Architecture Synthesis was created. This tool will be the focus of this work.

Keywords

Image processing Design framework Optimization  System accuracy System analysis 

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  • C. Hartmann
    • 1
  • K. Häublein
    • 1
  • M. Reichenbach
    • 1
  • D. Fey
    • 1
  1. 1.Chair of Computer ArchitectureUniversity of Erlangen-NurembergErlangenGermany

Personalised recommendations