'fieldsMAGMA': A MAGMA-accelerated extension to the 'fields' spatial statistics R package

AMS Citation:
Paige, J., D. Nychka, and D. Hammerling, 2015: 'fieldsMAGMA': A MAGMA-accelerated extension to the 'fields' spatial statistics R package. NCAR Technical Note NCAR/TN-520+STR, 42 pp, doi:10.5065/D6FX77HJ.
Resource Type:technical report
Title:'fieldsMAGMA': A MAGMA-accelerated extension to the 'fields' spatial statistics R package
Abstract: This report introduces the 'fieldsMAGMA' R package, an extension to the 'fields' package for spatial data analysis that is available on github. fieldsMAGMA uses the Cholesky decomposition functionality of the MAGMA multi-GPU, multi-CPU computing library and eliminates some unnecessary distance and covariance calculations to create accelerated versions of spatial statistics methods in fields. We demonstrate the performance of fieldsMAGMA's accelerated functions when applied to simulated datasets and the CO2 dataset available in fields. We show that using the single precision Cholesky decomposition in particular has the potential for vast improvements in the Cholesky decomposition and in spatial likelihood computation time, yet the accuracy of the likelihood maximization is not significantly reduced. We gather some of our timing results on a 2014 MacBook Pro with a stock graphics processing unit (GPU), an NVIDIA GeForce GT 750M with 2048 MB GDDR5 RAM.
Subject(s):Spatial statistics, Kriging, High-performance computing, GPU, MAGMA
Peer Review:Non-refereed
Copyright Information:Copyright Author(s). This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
OpenSky citable URL: ark:/85065/d7xs5tt1
Publisher's Version: 10.5065/D6FX77HJ
  • John Paige - NCAR/UCAR
  • Doug Nychka - NCAR/UCAR
  • Dorit Hammerling - NCAR/UCAR
  • Random Profile


    Recent & Upcoming Visitors