Co-optimizing application partitioning and network topology for a reconfigurable interconnect
| Autor: | John P. Morrison, Adam W. Hackett, Stephen J. Kirkland, Shoukat Ali, Deepak Ajwani |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Reconfigurable interconnect topology
Final topology Computer Networks and Communications Computer science Distributed computing Logical topology Extension topology Throughput Network configuration algorithm 0102 computer and information sciences 02 engineering and technology Parallel computing Network topology Topology-aware graph partitioning 01 natural sciences Bottleneck Theoretical Computer Science Stream-computing Computational topology Artificial Intelligence 020204 information systems 0202 electrical engineering electronic engineering information engineering Interconnection Optical circuit switch Initial topology Flow network 010201 computation theory & mathematics Hardware and Architecture Software |
| Zdroj: | Journal of Parallel and Distributed Computing. 96:12-26 |
| ISSN: | 0743-7315 |
| DOI: | 10.1016/j.jpdc.2016.04.010 |
| Popis: | To realize the full potential of a high-performance computing system with a reconfigurable interconnect, there is a need to design algorithms for computing a topology that will allow for a high-throughput load distribution, while simultaneously partitioning the computational task graph of the application for the computed topology. In this paper, we propose a new framework that exploits such reconfigurable interconnects to achieve these interdependent goals, i.e., to iteratively co-optimize the network topology configuration, application partitioning and network flow routing to maximize throughput for a given application. We also present a novel way of computing a high-throughput initial topology based on the structural properties of the application to seed our co-optimizing framework. We show the value of our approach on synthetic graphs that emulate the key characteristics of a class of stream computing applications that require high throughput. Our experiments show that the proposed technique is fast and computes high-quality partitions of such graphs for a broad range of hardware parameters that varies the bottleneck from computation to communication. Finally, we show how using a particular topology as a seed to our framework significantly reduces the time to compute the final topology. We give an algorithm to compute topologies of reconfigurable interconnect systems.We optimize, for reconfigurable networks, topology, routing, and task partitioning.We compute a high-throughput seed topology from structural properties of the task. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect