MPI_Comm_spawn_multiple(3) LAM/MPI MPI_Comm_spawn_multiple(3)
MPI_Comm_spawn_multiple - Spawn a dynamic MPI process from multiple executables
MPI_Comm_spawn_multiple(int count, char **commands, char ***argvs,
int *maxprocs, MPI_Info *infos, int root,
MPI_Comm comm, MPI_Comm *intercomm,
count - number of commands (only significant at root)
- commands to be executed (only significant at root)
argvs - arguments for commands (only significant at root)
- max number of processes for each command (only significant at root)
infos - startup hints for each command
root - rank of process to perform the spawn
comm - parent intracommunicator
- child intercommunicator containing spawned processes
- one code per process
A group of processes can create another group of processes with MPI_Comm_spawn_multiple
. This function is a collective operation over the parent communicator. The child group
starts up like any MPI application. The processes must begin by calling MPI_Init , after
which the pre-defined communicator, MPI_COMM_WORLD , may be used. This world communicator
contains only the child processes. It is distinct from the MPI_COMM_WORLD of the parent
MPI_Comm_spawn_multiple is used to manually specify a group of different executables and
arguments to spawn. MPI_Comm_spawn is used to specify one executable and set of arguments
(although a LAM/MPI appschema(5) can be provided to MPI_Comm_spawn via the "file" info
Communication With Spawned Processes
The natural communication mechanism between two groups is the intercommunicator. The sec-
ond communicator argument to MPI_Comm_spawn_multiple returns an intercommunicator whose
local group contains the parent processes (same as the first communicator argument) and
whose remote group contains child processes. The child processes can access the same
intercommunicator by using the MPI_Comm_get_parent call. The remote group size of the
parent communicator is zero if the process was created by mpirun (1) instead of one of the
spawn functions. Both groups can decide to merge the intercommunicator into an intracom-
municator (with the MPI_Comm_merge () function) and take advantage of other MPI collective
operations. They can then use the merged intracommunicator to create new communicators
and reach other processes in the MPI application.
Note that no MPI_Info keys are recognized by this implementation of MPI_Comm_spawn_multi-
. To use the "file" info key to specify an appschema(5), use LAM's MPI_Comm_spawn
. This may be preferable to MPI_Comm_spawn_multiple because it allows the arbitrary
specification of what nodes and/or CPUs should be used to launch jobs (either SPMD or
MPMD). See MPI_Comm_spawn(3) for more details.
The value of MPI_INFO_NULL should be given for each value in infos (the infos array is not
currently examined by LAM/MPI, so specifying non-NULL values for the array values is not
harmful). LAM schedules the given number of processes onto LAM nodes by starting with CPU
0 (or the lowest numbered CPU), and continuing through higher CPU numbers, placing one
process on each CPU. If the process count is greater than the CPU count, the procedure
The maxprocs array parameter to MPI_Comm_spawn_multiple specifies the exact number of pro-
cesses to be started. If it is not possible to start the desired number of processes,
MPI_Comm_spawn_multiple will return an error code. Note that even though maxprocs is only
relevant on the root, all ranks must have an errcodes array long enough to handle an inte-
ger error code for every process that tries to launch, or give MPI constant
MPI_ERRCODES_IGNORE for the errcodes argument. While this appears to be a contradiction,
it is per the MPI-2 standard. :-\
Frequently, an application wishes to chooses a process count so as to fill all processors
available to a job. MPI indicates the maximum number of processes recommended for a job
in the pre-defined attribute, MPI_UNIVERSE_SIZE , which is cached on MPI_COMM_WORLD
. The typical usage is to subtract the value of MPI_UNIVERSE_SIZE from the number of
processes currently in the job and spawn the difference. LAM sets MPI_UNIVERSE_SIZE to
the number of CPUs in the user's LAM session (as defined in the boot schema [bhost(5)] via
Locating an Executable Program
The executable program file must be located on the node(s) where the process(es) will run.
On any node, the directories specified by the user's PATH environment variable are
searched to find the program.
All MPI runtime options selected by mpirun (1) in the initial application launch remain in
effect for all child processes created by the spawn functions.
The argvs array parameter to MPI_Comm_spawn_multiple should not contain the program name
since it is given in the first parameter. The command line that is passed to the newly
launched program will be the program name followed by the strings in corresponding entry
in the argvs array.
USAGE WITH IMPI EXTENSIONS
The IMPI standard only supports MPI-1 functions. Hence, this function is currently not
designed to operate within an IMPI job.
If an error occurs in an MPI function, the current MPI error handler is called to handle
it. By default, this error handler aborts the MPI job. The error handler may be changed
with MPI_Errhandler_set ; the predefined error handler MPI_ERRORS_RETURN may be used to
cause error values to be returned (in C and Fortran; this error handler is less useful in
with the C++ MPI bindings. The predefined error handler MPI::ERRORS_THROW_EXCEPTIONS
should be used in C++ if the error value needs to be recovered). Note that MPI does not
guarantee that an MPI program can continue past an error.
All MPI routines (except MPI_Wtime and MPI_Wtick ) return an error value; C routines as
the value of the function and Fortran routines in the last argument. The C++ bindings for
MPI do not return error values; instead, error values are communicated by throwing excep-
tions of type MPI::Exception (but not by default). Exceptions are only thrown if the
error value is not MPI::SUCCESS
Note that if the MPI::ERRORS_RETURN handler is set in C++, while MPI functions will return
upon an error, there will be no way to recover what the actual error value was.
- No error; MPI routine completed successfully.
- Invalid communicator. A common error is to use a null communicator in a call
(not even allowed in MPI_Comm_rank ).
- Spawn error; one or more of the applications attempting to be launched failed.
Check the returned error code array.
- Invalid argument. Some argument is invalid and is not identified by a specific
error class. This is typically a NULL pointer or other such error.
- Invalid root. The root must be specified as a rank in the communicator. Ranks
must be between zero and the size of the communicator minus one.
- Other error; use MPI_Error_string to get more information about this error code.
- An internal error has been detected. This is fatal. Please send a bug report to
the LAM mailing list (see http://www.lam-mpi.org/contact.php ).
appschema(5), bhost(5), lamboot(1), MPI_Comm_get_parent(3), MPI_Comm_merge(3),
MPI_Comm_spawn_multiple(3), MPI_Info_create(3), MPI_Info_set(3), MPI_Info_delete(3),
MPI_Info_free(3), MPI_Init(3), mpirun(1)
For more information, please see the official MPI Forum web site, which contains the text
of both the MPI-1 and MPI-2 standards. These documents contain detailed information about
each MPI function (most of which is not duplicated in these man pages).
The LAM Team would like the thank the MPICH Team for the handy program to generate man
pages ("doctext" from ftp://ftp.mcs.anl.gov/pub/sowing/sowing.tar.gz ), the initial for-
matting, and some initial text for most of the MPI-1 man pages.
LAM/MPI 6.5.8 11/10/2002 MPI_Comm_spawn_multiple(3)