Abstract

This chapter discusses some grid experiences in solving the problem of generating large astronomical image mosaics by composing multiple small images, from the team that has developed Montage (http://montage. ipac. caltech. edu/). The problem of generating these mosaics is complex in that individual images must be projected into a common coordinate space, overlaps between images calculated, the images processed so that the backgrounds match, and images composed while using a variety of techniques to handle the presence of multiple pixels in the same output space. To accomplish these tasks, a suite of software tools called Montage has been developed. The modules in this suite can be run on a single processor computer using a simple shell script, and can additionally be run using a combination of parallel approaches. These include running MPI versions of some modules, and using standard grid tools. In the latter case, processing workflows are automatically generated, and appropriate data sources are located and transferred to a variety of parallel processing environments for execution. As a result, it is now possible to generate large-scale mosaics on-demand in timescales that support iterative, scientific exploration. In this chapter, we describe Montage, how it was modified to execute in the grid environment, the tools that were used to support its execution, as well as performance results.

Date

January 1, 2006

Authors

Carl Kesselman