This paper presents a new task manager aimed to general-purpose small-scale multiprocessors. It is designed to exploit complex parallelism structures from general applications. The manager uses an explicit parallelism encoding based on a topological description of the task dependence graph. A dedicated task manager decodes the parallelism information and builds a structured representation of th...

This paper presents a new parallelism manager for multimedia multiprocessors. An analysis of new multimedia applications shows that the available parallelism moves from the data-level to the control-level. New architectures are required to be able to extract this kind of dynamic parallelism. Our proposed parallelism management describes the parallelism with a topological description of the task...

Computational problems can usually be divided into a number of (sub)tasks. The data dependencies between these tasks can be described by a so called task graph. Since the task graph scheduling problem is known to be NP-hard, researchers devised an innumerable number of heuristic algorithms to solve this problem best. Up to now, these heuristics were analyzed by using a set of task graph problem...

Following a workshop on graph data formats held with the 8th Symposium on Graph Drawing (GD 2000), a task group was formed to propose a format for graphs and graph drawings that meets current and projected requirements. On behalf of this task group, we here present GraphML (Graph Markup Language), an XML format for graph structures, as an initial step towards this goal. Its main characteristic ...

0

In order to improve the performance of Data Mining applications, an effective method is task parallelization. The scheduler on Grid plays an important role to management subtasks so as to achieve high performance. We introduce an additional component that we call serializer, whose purpose is to decompose the tasks into a series of independent tasks according the directed acyclic graph (DAG), an...

Understanding traffic scenes requires considering heterogeneous information about dynamic agents and the static infrastructure. In this work we propose SCENE, a methodology to encode diverse in graphs reason these using Graph Neural Network encoder task-specific decoders. The graphs, whose structures are defined by an ontology, consist of different nodes with type-specific node features relatio...

Task partitioning of a graph-parallel system is traditionally considered equivalent to the graph partition problem. Such equivalence exists because the properties associated with each vertex/edge are normally considered indivisible. However, this assumption is not true for many Machine Learning and Data Mining (MLDM) problems: instead of a single value, a vector of data elements is defined as t...

In this paper we present a contextual representation model of audiovisual (AV) documents for AV information systems. In the rst part, we study AV medium, and show that AV intra-document context is always related to a user task seen as a general description task. We then present the AI-Strata model for AV description: audiovisual units (pieces of AV documents) are annotated with annotation eleme...