Paper Info
Title
Cost-aware function migration in heterogeneous systems
Abstract
Today's approaches towards heterogeneous computing rely on either the programmer or dedicated programming models to efficiently integrate heterogeneous components. In this work, we propose an adaptive cost-aware function-migration mechanism built on top of a light-weight hardware abstraction layer. With this mechanism, the highly dynamic task of choosing the most beneficial processing unit will be hidden from the programmer while causing only minor variation in the work and program flow. The migration mechanism transparently adapts to the current workload and system environment without the necessity of JIT compilation or binary translation. Evaluation shows that our approach successfully adapts to new circumstances and predicts the most beneficial processing unit (PU). Through fine-grained PU selection, our solution achieves a speedup of up to 2.27 for the average kernel execution time but introduces only a marginal overhead in case its services are not required.
Year
DOI
Venue
2011
10.1145/1944862.1944883
HiPEAC
Keywords
Field
DocType
heterogeneous component,jit compilation,binary translation,average kernel execution time,heterogeneous computing,heterogeneous system,current workload,fine-grained pu selection,migration mechanism,cost-aware function migration,beneficial processing unit,adaptive cost-aware function-migration mechanism,adaptive system,heterogeneity,programming model,adaptive systems,programming models
Computer science,Symmetric multiprocessor system,Real-time computing,Binary translation,Just-in-time compilation,Speedup,Distributed computing,Kernel (linear algebra),Programmer,Programming paradigm,Adaptive system,Parallel computing,Embedded system
Conference
Citations 
PageRank 
References 
12
0.69
10
Authors
3
Name
Order
Citations
PageRank
Mario Kicherer1293.63
Rainer Buchty214318.44
Wolfgang Karl337234.84