Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

The effect of subject measurement error on joint kinematics in the conventional gait model: Insights from the open-source pyCGM tool using high performance computing methods

Fig 5

Abstraction diagram of distributed computation of multiple files on the HPC.

(1) The dynamic trial, static trial, and subject measurements are stored on the IO Luster system. (2) The rank 0 core loads the data from the luster system. (3) Rank 0 calculates all variations of subject measurements and distributes them over the available ranks using the MPI.scatter method. (4) Rank 0 uses MPI.bcast method to distribute the dynamic trial, static trial, and subject measurements to all ranks. (5) Each rank saves the resulting data directly to the luster system.

Fig 5

doi: https://doi.org/10.1371/journal.pone.0189984.g005