Model-integrated program synthesis environment for parallel/real-time image processing
Parallel and Distributed Methods for Image Processing
In this paper, it is shown that, through the use of Model-Integrated Program Synthesis MIPS, parallel real-time implementations of image processing data ows can be synthesized from high level graphical speci cations. The complex details inherent to parallel and real-time software development become transparent to the programmer, enabling the cost-e ective exploitation of parallel hardware for building more exible and powerful real-time imaging systems. The Model Integrated Real-Time Imagine
... essing System MIRTIS is presented as an example. MIRTIS employs the Multigraph Architecture MGA, a framework and set of tools for building MIPS systems, to generate parallel real-time image processing software which runs under the control of a parallel run-time kernel on a network of Texas Instruments TMS320C40 DSPs C40s. The MIRTIS models contain graphical declarations of the image processing computations to be performed, the available hardware resources, and the timing constraints of the application. The MIRTIS model interpreter performs the parallelization, scaling, and mapping of the computations to the resources automatically or determines that the timing constraints cannot be met with the available resources. MIRTIS is a clear example of how parallel real-time image processing systems can be built which are 1 coste ectively programmable, 2 exible, 3 scalable, and 4 built from Commercial O -The-Shelf COTS components. Note that the de nition does not require that the computation traverse the image in raster order, or that the operations be simple. The statement w as made to drive home that fact that the de nition encompasses at least those types of algorithms.