Main Help → All Commands → Main Header → Processors
The Processors
command sets the number of processors to use when running parallel code:
Command (num)
where (num)
is the number of processors in the calcualtions. Use of this command implies the code preferences are set to run a parallel version of the code engines.
For MPM calculations, the grid is automatically divided into equally sized patches. If the automatic patching is not ideal for a specific simulation, you can override that calculation with custom patching with the following embedded XML element in the MPM Header.
XMLData "MPMHeader" <PatchGrid x="xnum" y="ynum" z="znum"> <Xpatches>n1,n2,...nxnum-1</Xpatches> <Ypatches>n1,n2,...nynum-1</Ypatches> <Zpatches>n1,n2,...nznum-1</Ypatches> </PatchGrid> EndXMLData
where xnum
, ynum
, and znum
are the number of patches in the x, y, and z direction (z only used for 3D patching). Their product must be equal to the number of processors used in the calculations. If unequal patch sizes can improve parallel scaling, they can be created using X(Y)(Z)patches
elements. Each patches element must contain exactly inum-1
(i = x, y, or z) monotonically increasing numbers between zero and one for the fractional break points between patches. The patches elements are optional. Any omitted axes will use equally sizes patches.
XML
input files, you can use the comment <!--processors #-->
to set number of process to the number in #. This comment method only works when running the job in NairnFEAMPM. When submitting jobs with XML
files on a command line, you must select number of processes with the code engine's -np
parameter instead of a comment.