Early Experiences in Running Many-Task Computing Workloads on GPGPUs
Department of Computer Science, Illinois Institute of Technology
XSEDE, 2012
@article{krieder2012early,
title={Early experiences in running many-task computing workloads on gpgpus},
author={Krieder, Scott J and Grimmer, Benjamin and Raicu, Ioan},
journal={XSEDE Poster Session},
year={2012}
}
This work aims to enable Swift to efficiently use accelerators (such as NVIDIA GPUs) to further accelerate a wide range of applications. This work presents preliminary results in the costs associated with managing and launching concurrent kernels on NVIDIA Kepler GPUs. We expect our results to be applicable to several XSEDE resources, such as Forge, Keeneland, and Lonestar, where currently Swift can only use the general processors to execute workloads and the GPUs are left idle.
October 19, 2013 by hgpu
