Cellprofiler analyst download how to#Here's how to access the folders on your local computer. In $PROJ you can store the scripts needed to start the computation, and also the results. You need to copy your image data in the $WRKDIR directory. There are two important folders on Ukko2: $WRKDIR and $PROJ (see OBSOLETE - Ukko2 User Guide#FilesystemPolicies). Mount Ukko2 folders on the local computer A speedup like this could be quite significant: analyses that you used to let run over night could now be repeated several times times during the day with different parameters. The benefit of Ukko2 was that you would get 8 times more images processed simultaneously. In this case the time it took to process one image set was about the same on Ukko2 and HCA workstation. The pipeline was reasonably heavy, with texture measurements etc., and the run would take 10-15 minutes. For a test data set of 144 images sets the processing used 12 cores on each of the 4 nodes (total of 48 cores), with each core processing 3 image sets. How many of those will actually be used depends also on the data set size. At the moment there is some problem when trying to use all cores, but using even just half still gives 56 cores (CP workers). One node has 28 cores, giving 112 cores in total. On Ukko2, a modest resource request that based on the testing done so far is usually granted immediately is 4 nodes (sometimes the job would be in queue for maybe 5 minutes). When analysing Molecular Devices Nano data (2048x2048) on LMU HCA workstation you can run only 6 workers before getting memory problems.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |