Paper Info
Title
The future is dynamic: adaptive runtime resource management for heterogeneous computer platforms
Abstract
Software developers increasingly need to take advantage of heterogeneous hardware resources, like GPUs and DSPs, while coping with dynamic events and quality of service requirements. This demonstration shows how an adaptive resource manager that dynamically assigns components to processing elements can take advantage of heterogeneous platforms, in this case a platform consisting of multiple multi-core CPUs and GPUs. It will also demonstrate a simulator that is used to see the impact of different resource management strategies and options before actually implementing them. The application used in the demonstration will be a demanding real-world video processing application that uses the GStreamer framework, used to build componentized stream-processing applications, for which we have built several CPU- and GPU- accelerated components.
Year
DOI
Venue
2009
10.1145/1639950.1639988
OOPSLA Companion
Keywords
Field
DocType
service requirement,accelerated component,adaptive runtime resource manager,embedded software engineering,heterogeneous platform,adaptive runtime resource management,resource assignment strategy,software developer,runtime resource management,dynamic event,heterogeneous hardware resource,gstreamer framework,adaptive resource manager,real-world video processing application,heterogeneous devices,different resource management strategy,heterogeneous computer platform,multiple multi-core cpus,processing element,stream processing,video processing,embedded software,resource manager,quality of service,software development,heterogeneous computing
Resource management,Video processing,Computer science,Quality of service,Human resource management system,Software,Operating system
Conference
Citations 
PageRank 
References 
0
0.34
1
Authors
6
Name
Order
Citations
PageRank
Rogier Baert1535.41
Carolina Blanch2273.09
Paul Coene3234.05
Maja D'Hondt429627.76
Zhe Ma5153.19
Roel Wuyts683059.41