Pull requests

#135 Merged
Repository
MatthewTurk MatthewTurk
Branch
yt
Repository
yt_analysis yt_analysis
Branch
yt

Parallel time series

Author
  1. Matthew Turk
Reviewers
Description

This change will add a call to parallel_objects for Time Series Data, which will by-default parallelize one-pf-per-core when running in parallel. The results come back ordered correctly.

Comments (1)

  1. Nathan Goldbaum

    Hi Matt, I'm running the script I've pasted here: http://paste.yt-project.org/show/2276/

    I get the following output when running in serial on a small enzo dataset: http://paste.yt-project.org/show/2277/

    and the following when I run in parallel: http://paste.yt-project.org/show/2278/

    I think that the final result is fine, but it doesn't look like the filenames are being distributed over the MPI workgroup correctly. Instead, the whole workgroup is working together on each filename. If I want this behavior, I think I should specify Parallel = 1, just like if I were using parallel_objects to loop over a list of filenames.

    Oops, sorry, I wasn't running your changeset. Sorry for the noise! I'm accepting the PR.