dgord - compute sparse matrix orderings of graphs in parallel
dgord [options] [gfile] [ofile] [lfile]
The
dgord program computes, in a parallel way, an ordering of a Scotch
source graph representing the pattern of some symmetric sparse matrix.
Source graph file
gfile is either a centralized graph file, or a set of
files representing fragments of a distributed graph. The resulting ordering is
stored in file
ofile. Eventual logging information (such as the one
produced by option
-v) is sent to file
lfile. When file names
are not specified, data is read from standard input and written to standard
output. Standard streams can also be explicitely represented by a dash '-'.
When the proper libraries have been included at compile time,
dgord can
directly handle compressed graphs, both as input and output. A stream is
treated as compressed whenever its name is postfixed with a compressed file
extension, such as in 'brol.grf.bz2' or '-.gz'. The compression formats which
can be supported are the bzip2 format ('.bz2'), the gzip format ('.gz'), and
the lzma format ('.lzma').
dgord bases on implementations of the MPI interface to spread work across
the processing elements. It is therefore not likely to be run directly, but
instead through some launcher command such as
mpirun.
- -c?opt
- Choose default ordering strategy according to one or
several options among:
- b
- enforce load balance as much as possible.
- q
- privilege quality over speed (default).
- s
- privilege speed over quality.
- t
- enforce safety.
- x
- enforce scalability.
- -h
- Display some help.
- -m?mfile
- Save column block mapping data to file mfile.
Mapping data specifies, for each vertex, the index of the column block to
which this vertex belongs.
- -o?strat
- Use parallel graph ordering strategy strat (see
PT-Scotch user's manual for more information).
- -r?pnum
- Set root process for centralized files (default is 0).
- -t?tfile
- Save partitioning tree data to file tfile.
Partitioning tree data specifies, for each vertex, the index of the first
vertex of the parent block of the block to which the vertex belongs.
Altogether with the mapping data provided in file mfile, it allows
one to rebuild the separator tree of the nested dissection process.
- -V
- Display program version and copyright.
- -v?verb
- Set verbose mode to verb. It is a set of one of more
characters which can be:
- s
- strategy information.
- t
- timing information.
Run
dgord on 5 processing elements to reorder matrix graph brol.grf and
save the resulting ordering to file brol.ord, using the default sequential
graph ordering strategy:
$ mpirun -np 5 dgord brol.grf brol.ord
Run
dgord on 5 processing elements to reorder the distributed matrix
stored on graph fragment files brol5-0.dgr to brol5-4.dgr, and save the
resulting ordering to file brol.ord (see
dgscat(1) for an explanation
of the '%p' and '%r' sequences in names of distributed graph fragments).
$ mpirun -np 5 dgord brol%p-%r.dgr brol.ord
dgtst(1),
dgscat(1),
gmk_hy(1),
gord(1).
PT-Scotch user's manual.
Francois Pellegrini <
[email protected]>