jianmu
/
lammps
forked from lijiext/lammps
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

git-svn-id: svn://svn.icms.temple.edu/lammps-ro/trunk@7369 f3b2605a-c512-4ea7-a41b-209d697bcdaa

This commit is contained in:
sjplimp 2011-12-15 00:27:35 +00:00
parent fb16c0eb30
commit 59165f7114
2 changed files with 28 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
doc/processors.html
View File

@ -137,24 +137,24 @@ provide options for this ordering, e.g. via environment variable
settings.
</P>
<P>The <I>numa</I> style operates similar to the <I>twolevel</I> keyword except
that it auto-detects the core count within the nodes. Currently, it
does this in only 2 levels, but it may be extended in the future to
account for socket topology and other non-uniform memory access (NUMA)
costs. It also uses a different algorithm (iterative) than the
that it auto-detects which cores are running on which nodes.
Currently, it does this in only 2 levels, but it may be extended in
the future to account for socket topology and other non-uniform memory
access (NUMA) costs. It also uses a different algorithm than the
<I>twolevel</I> keyword for doing the two-level factorization of the
simulation box into a 3d processor grid to minimize off-node
communication, and it does its own mapping of nodes and cores to the
logical 3d grid. Thus it may produce a different or improved layout
of the processors.
communication, and it does its own MPI-based mapping of nodes and
cores to the logical 3d grid. Thus it may produce a different layout
of the processors than the <I>twolevel</I> options.
</P>
<P>The <I>numa</I> style will give an error if (a) there are less than 4 cores
per node, or (b) the number of MPI processes is not divisible by the
number of cores used per node, or (c) only 1 node is allocated, or (d)
any of the Px or Py of Pz values is greater than 1.
<P>The <I>numa</I> style will give an error if the number of MPI processes is
not divisible by the number of cores used per node, or any of the Px
or Py of Pz values is greater than 1.
</P>
<P>IMPORTANT NOTE: For the <I>numa</I> style to work correctly, it assumes
the MPI ranks of processors LAMMPS is running on are ordered by core
and then by node. See the same note for the <I>twolevel</I> keyword.
<P>IMPORTANT NOTE: Unlike the <I>twolevel</I> style, the <I>numa</I> style does not
require any particular ordering of MPI ranks i norder to work
correctly. This is because it auto-detects which processes are
running on which nodes.
</P>
<P>The <I>custom</I> style uses the file <I>infile</I> to define both the 3d
factorization and the mapping of processors to the grid.

28
doc/processors.txt
View File

@ -130,24 +130,24 @@ provide options for this ordering, e.g. via environment variable
settings.
The {numa} style operates similar to the {twolevel} keyword except
that it auto-detects the core count within the nodes. Currently, it
does this in only 2 levels, but it may be extended in the future to
account for socket topology and other non-uniform memory access (NUMA)
costs. It also uses a different algorithm (iterative) than the
that it auto-detects which cores are running on which nodes.
Currently, it does this in only 2 levels, but it may be extended in
the future to account for socket topology and other non-uniform memory
access (NUMA) costs. It also uses a different algorithm than the
{twolevel} keyword for doing the two-level factorization of the
simulation box into a 3d processor grid to minimize off-node
communication, and it does its own mapping of nodes and cores to the
logical 3d grid. Thus it may produce a different or improved layout
of the processors.
communication, and it does its own MPI-based mapping of nodes and
cores to the logical 3d grid. Thus it may produce a different layout
of the processors than the {twolevel} options.
The {numa} style will give an error if (a) there are less than 4 cores
per node, or (b) the number of MPI processes is not divisible by the
number of cores used per node, or (c) only 1 node is allocated, or (d)
any of the Px or Py of Pz values is greater than 1.
The {numa} style will give an error if the number of MPI processes is
not divisible by the number of cores used per node, or any of the Px
or Py of Pz values is greater than 1.
IMPORTANT NOTE: For the {numa} style to work correctly, it assumes
the MPI ranks of processors LAMMPS is running on are ordered by core
and then by node. See the same note for the {twolevel} keyword.
IMPORTANT NOTE: Unlike the {twolevel} style, the {numa} style does not
require any particular ordering of MPI ranks i norder to work
correctly. This is because it auto-detects which processes are
running on which nodes.
The {custom} style uses the file {infile} to define both the 3d
factorization and the mapping of processors to the grid.