On multi-dimensional sorting orders

Abstract

As multimedia applications grow in complexity, more requirements are imposed on software schedulers. It is not always clear that these schedulers are fair to all aspects of the system, or are controllable, in a measurable way, to favor one aspect of the system over the other. The overall goal of this research is to revolutionize the way schedulers are developed. The scheduling problem is formulated as a multi-dimensional sorting problem. Space-filling curves are used to define a linear order for sorting and scheduling objects that lie in the multi-dimensional space. The characteristics of various space-filling curves are studied for sorting and scheduling purposes. Performance measures are proposed to compare the bias, among other characteristics, of a space-filling curve towards any of its dimensions.