An Efficient Stream Buffer Mechanism for Dataflow Execution on Heterogeneous Platforms with GPUs
Leiden Institute of Advanced Computer Science, University of Leiden, Leiden, The Netherlands
Data-Flow Execution Models for Extreme Scale Computing (DFM 2011), 2011
@article{balevic2011efficient,
title={An Efficient Stream Buffer Mechanism for Dataflow Execution on Heterogeneous Platforms with GPUs},
author={Balevic, A. and Kienhuis, B.},
year={2011},
booktitle={Data-Flow Execution Models for Extreme Scale Computing (DFM 2011)}
}
The move towards heterogeneous parallel computing is underway as witnessed by the emergence of novel computing platforms combining architecturally diverse components such as CPUs, GPUs and special function units. We approach mapping of streaming applications onto heterogeneous architectures using a Process Network (PN) model of computation. In this paper, we present an approach for exploiting coarse-grain pipeline parallelism exposed by a data ow graph and describe its mapping onto CPU-GPU architecture. First experimental results conducted on a Tesla C2050 GPU indicate that use of a data ow model on heterogeneous platforms not only enables exploiting different forms of parallelism (such as task, pipeline and data parallelism), but also has a potential to become an effective solution for reducing I/O overheads.
October 19, 2011 by hgpu
