mpirun.1in: whitespace cleanup
Whitespace cleanup only; no content changes.
Этот коммит содержится в:
родитель
9529289319
Коммит
206eade32c
@ -4,7 +4,7 @@
|
|||||||
.\" $COPYRIGHT$
|
.\" $COPYRIGHT$
|
||||||
.\"
|
.\"
|
||||||
.\" Man page for ORTE's orterun command
|
.\" Man page for ORTE's orterun command
|
||||||
.\"
|
.\"
|
||||||
.\" .TH name section center-footer left-footer center-header
|
.\" .TH name section center-footer left-footer center-header
|
||||||
.TH MPIRUN 1 "#OMPI_DATE#" "#PACKAGE_VERSION#" "#PACKAGE_NAME#"
|
.TH MPIRUN 1 "#OMPI_DATE#" "#PACKAGE_VERSION#" "#PACKAGE_NAME#"
|
||||||
.\" **************************
|
.\" **************************
|
||||||
@ -27,7 +27,7 @@ other. Using any of the names will produce the same behavior.
|
|||||||
Single Process Multiple Data (SPMD) Model:
|
Single Process Multiple Data (SPMD) Model:
|
||||||
|
|
||||||
.B mpirun
|
.B mpirun
|
||||||
[ options ]
|
[ options ]
|
||||||
.B <program>
|
.B <program>
|
||||||
[ <args> ]
|
[ <args> ]
|
||||||
.P
|
.P
|
||||||
@ -41,8 +41,8 @@ Multiple Instruction Multiple Data (MIMD) Model:
|
|||||||
[ <args1> ] :
|
[ <args1> ] :
|
||||||
[ local_options2 ]
|
[ local_options2 ]
|
||||||
.B <program2>
|
.B <program2>
|
||||||
[ <args2> ] :
|
[ <args2> ] :
|
||||||
... :
|
... :
|
||||||
[ local_optionsN ]
|
[ local_optionsN ]
|
||||||
.B <programN>
|
.B <programN>
|
||||||
[ <argsN> ]
|
[ <argsN> ]
|
||||||
@ -164,7 +164,7 @@ List of hosts on which to invoke processes.
|
|||||||
.TP
|
.TP
|
||||||
.B
|
.B
|
||||||
-hostfile\fR,\fP --hostfile \fR<hostfile>\fP
|
-hostfile\fR,\fP --hostfile \fR<hostfile>\fP
|
||||||
Provide a hostfile to use.
|
Provide a hostfile to use.
|
||||||
.\" JJH - Should have man page for how to format a hostfile properly.
|
.\" JJH - Should have man page for how to format a hostfile properly.
|
||||||
.
|
.
|
||||||
.
|
.
|
||||||
@ -190,7 +190,7 @@ execute (i.e., neither the "-np" nor its synonyms are provided on the command
|
|||||||
line), Open MPI will automatically execute a copy of the program on
|
line), Open MPI will automatically execute a copy of the program on
|
||||||
each process slot (see below for description of a "process slot"). This
|
each process slot (see below for description of a "process slot"). This
|
||||||
feature, however, can only be used in the SPMD model and will return an
|
feature, however, can only be used in the SPMD model and will return an
|
||||||
error (without beginning execution of the application) otherwise.
|
error (without beginning execution of the application) otherwise.
|
||||||
.
|
.
|
||||||
.
|
.
|
||||||
.TP
|
.TP
|
||||||
@ -636,9 +636,9 @@ There may be other options listed with \fImpirun --help\fP.
|
|||||||
.TP
|
.TP
|
||||||
.B MPIEXEC_TIMEOUT
|
.B MPIEXEC_TIMEOUT
|
||||||
The maximum number of seconds that
|
The maximum number of seconds that
|
||||||
.I mpirun
|
.I mpirun
|
||||||
.RI ( mpiexec )
|
.RI ( mpiexec )
|
||||||
will run. After this many seconds,
|
will run. After this many seconds,
|
||||||
.I mpirun
|
.I mpirun
|
||||||
will abort the launched job and exit.
|
will abort the launched job and exit.
|
||||||
.
|
.
|
||||||
@ -1078,7 +1078,7 @@ hostnames, indexed from 0. For example:
|
|||||||
Starting with Open MPI v1.7, all socket/core slot locations are be
|
Starting with Open MPI v1.7, all socket/core slot locations are be
|
||||||
specified as
|
specified as
|
||||||
.I logical
|
.I logical
|
||||||
indexes (the Open MPI v1.6 series used
|
indexes (the Open MPI v1.6 series used
|
||||||
.I physical
|
.I physical
|
||||||
indexes). You can use tools such as HWLOC's "lstopo" to find the
|
indexes). You can use tools such as HWLOC's "lstopo" to find the
|
||||||
logical indexes of socket and cores.
|
logical indexes of socket and cores.
|
||||||
@ -1107,7 +1107,7 @@ If a relative directory is specified, it must be relative to the initial
|
|||||||
working directory determined by the specific starter used. For example when
|
working directory determined by the specific starter used. For example when
|
||||||
using the rsh or ssh starters, the initial directory is $HOME by default. Other
|
using the rsh or ssh starters, the initial directory is $HOME by default. Other
|
||||||
starters may set the initial directory to the current working directory from
|
starters may set the initial directory to the current working directory from
|
||||||
the invocation of \fImpirun\fP.
|
the invocation of \fImpirun\fP.
|
||||||
.
|
.
|
||||||
.
|
.
|
||||||
.
|
.
|
||||||
@ -1135,7 +1135,7 @@ that node), then Open MPI will use the default directory determined by
|
|||||||
the starter.
|
the starter.
|
||||||
.PP
|
.PP
|
||||||
All directory changing occurs before the user's program is invoked; it
|
All directory changing occurs before the user's program is invoked; it
|
||||||
does not wait until \fIMPI_INIT\fP is called.
|
does not wait until \fIMPI_INIT\fP is called.
|
||||||
.
|
.
|
||||||
.
|
.
|
||||||
.
|
.
|
||||||
@ -1163,7 +1163,7 @@ using the typical shell redirection procedure on \fImpirun\fP.
|
|||||||
Note that in this example \fIonly\fP the MPI_COMM_WORLD rank 0 process will
|
Note that in this example \fIonly\fP the MPI_COMM_WORLD rank 0 process will
|
||||||
receive the stream from \fImy_input\fP on stdin. The stdin on all the other
|
receive the stream from \fImy_input\fP on stdin. The stdin on all the other
|
||||||
nodes will be tied to /dev/null. However, the stdout from all nodes will
|
nodes will be tied to /dev/null. However, the stdout from all nodes will
|
||||||
be collected into the \fImy_output\fP file.
|
be collected into the \fImy_output\fP file.
|
||||||
.
|
.
|
||||||
.
|
.
|
||||||
.
|
.
|
||||||
@ -1199,8 +1199,8 @@ MPI application.
|
|||||||
.PP
|
.PP
|
||||||
User signal handlers should probably avoid trying to cleanup MPI state
|
User signal handlers should probably avoid trying to cleanup MPI state
|
||||||
(Open MPI is currently not async-signal-safe; see MPI_Init_thread(3)
|
(Open MPI is currently not async-signal-safe; see MPI_Init_thread(3)
|
||||||
for details about
|
for details about
|
||||||
.I MPI_THREAD_MULTIPLE
|
.I MPI_THREAD_MULTIPLE
|
||||||
and thread safety). For example, if a segmentation fault occurs in
|
and thread safety). For example, if a segmentation fault occurs in
|
||||||
\fIMPI_SEND\fP (perhaps because a bad buffer was passed in) and a user
|
\fIMPI_SEND\fP (perhaps because a bad buffer was passed in) and a user
|
||||||
signal handler is invoked, if this user handler attempts to invoke
|
signal handler is invoked, if this user handler attempts to invoke
|
||||||
@ -1279,7 +1279,7 @@ The \fI--prefix\fR option is not sufficient if the installation paths
|
|||||||
on the remote node are different than the local node (e.g., if "/lib"
|
on the remote node are different than the local node (e.g., if "/lib"
|
||||||
is used on the local node, but "/lib64" is used on the remote node),
|
is used on the local node, but "/lib64" is used on the remote node),
|
||||||
or if the installation paths are something other than a subdirectory
|
or if the installation paths are something other than a subdirectory
|
||||||
under a common prefix.
|
under a common prefix.
|
||||||
.PP
|
.PP
|
||||||
Note that executing \fImpirun\fR via an absolute pathname is
|
Note that executing \fImpirun\fR via an absolute pathname is
|
||||||
equivalent to specifying \fI--prefix\fR without the last subdirectory
|
equivalent to specifying \fI--prefix\fR without the last subdirectory
|
||||||
@ -1322,7 +1322,7 @@ The \fI<key>\fP argument generally specifies which MCA module will receive the v
|
|||||||
For example, the \fI<key>\fP "btl" is used to select which BTL to be used for
|
For example, the \fI<key>\fP "btl" is used to select which BTL to be used for
|
||||||
transporting MPI messages. The \fI<value>\fP argument is the value that is
|
transporting MPI messages. The \fI<value>\fP argument is the value that is
|
||||||
passed.
|
passed.
|
||||||
For example:
|
For example:
|
||||||
.
|
.
|
||||||
.TP 4
|
.TP 4
|
||||||
mpirun -mca btl tcp,self -np 1 foo
|
mpirun -mca btl tcp,self -np 1 foo
|
||||||
@ -1389,7 +1389,7 @@ are spawned by that job are designated "secondary" jobs):
|
|||||||
.IP \[bu] 2
|
.IP \[bu] 2
|
||||||
if all processes in the primary job normally terminate with exit status 0, we return 0
|
if all processes in the primary job normally terminate with exit status 0, we return 0
|
||||||
.IP \[bu]
|
.IP \[bu]
|
||||||
if one or more processes in the primary job normally terminate with non-zero exit status,
|
if one or more processes in the primary job normally terminate with non-zero exit status,
|
||||||
we return the exit status of the process with the lowest MPI_COMM_WORLD rank to have a non-zero status
|
we return the exit status of the process with the lowest MPI_COMM_WORLD rank to have a non-zero status
|
||||||
.IP \[bu]
|
.IP \[bu]
|
||||||
if all processes in the primary job normally terminate with exit status 0, and one or more
|
if all processes in the primary job normally terminate with exit status 0, and one or more
|
||||||
@ -1435,7 +1435,7 @@ transport of MPI messages.
|
|||||||
.
|
.
|
||||||
.
|
.
|
||||||
.TP 4
|
.TP 4
|
||||||
mpirun -np 4 -mca btl tcp,sm,self
|
mpirun -np 4 -mca btl tcp,sm,self
|
||||||
.br
|
.br
|
||||||
--mca btl_tcp_if_include eth0 prog1
|
--mca btl_tcp_if_include eth0 prog1
|
||||||
.br
|
.br
|
||||||
|
Загрузка…
x
Ссылка в новой задаче
Block a user