Journal Metrics

  • IF value: 6.086 IF 6.086
  • IF 5-year<br/> value: 6.174 IF 5-year
    6.174
  • SNIP value: 1.812 SNIP 1.812
  • IPP value: 5.140 IPP 5.140
  • SJR value: 3.969 SJR 3.969
  • h5-index value: 29 h5-index 29
Geosci. Model Dev., 6, 17-28, 2013
www.geosci-model-dev.net/6/17/2013/
doi:10.5194/gmd-6-17-2013
© Author(s) 2013. This work is distributed
under the Creative Commons Attribution 3.0 License.
Porting marine ecosystem model spin-up using transport matrices to GPUs
E. Siewertsen1, J. Piwonski2, and T. Slawig2
1Institute for Computer Science, Christian-Albrechts Universität zu Kiel, 24098 Kiel, Germany
2Institute for Computer Science and Kiel Marine Science – Centre for Interdisciplinary Marine Science, Cluster The Future Ocean, Christian-Albrechts Universität zu Kiel, 24098 Kiel, Germany

Abstract. We have ported an implementation of the spin-up for marine ecosystem models based on transport matrices to graphics processing units (GPUs). The original implementation was designed for distributed-memory architectures and uses the Portable, Extensible Toolkit for Scientific Computation (PETSc) library that is based on the Message Passing Interface (MPI) standard. The spin-up computes a steady seasonal cycle of ecosystem tracers with climatological ocean circulation data as forcing. Since the transport is linear with respect to the tracers, the resulting operator is represented by matrices. Each iteration of the spin-up involves two matrix-vector multiplications and the evaluation of the used biogeochemical model. The original code was written in C and Fortran. On the GPU, we use the Compute Unified Device Architecture (CUDA) standard, a customized version of PETSc and a commercial CUDA Fortran compiler. We describe the extensions to PETSc and the modifications of the original C and Fortran codes that had to be done. Here we make use of freely available libraries for the GPU. We analyze the computational effort of the main parts of the spin-up for two exemplar ecosystem models and compare the overall computational time to those necessary on different CPUs. The results show that a consumer GPU can compete with a significant number of cluster CPUs without further code optimization.

Citation: Siewertsen, E., Piwonski, J., and Slawig, T.: Porting marine ecosystem model spin-up using transport matrices to GPUs, Geosci. Model Dev., 6, 17-28, doi:10.5194/gmd-6-17-2013, 2013.
 
Search GMD
Final Revised Paper
PDF XML
Citation
Discussion Paper
Share