Updates about thread support levels.
This commit was SVN r23341.
Этот коммит содержится в:
Jeff Squyres
родитель
af33e5cd1a
Коммит
8fef296b8a
@ -1,13 +1,15 @@
|
||||
. -*- nroff -*-
|
||||
.\"Copyright 2006-2008 Sun Microsystems, Inc.
|
||||
.\" Copyright (c) 1996 Thinking Machines Corporation
|
||||
.\" Copyright (c) 2010 Cisco Systems, Inc. All rights reserved.
|
||||
.TH MPI_Init_thread 3 "#OMPI_DATE#" "#PACKAGE_VERSION#" "#PACKAGE_NAME#"
|
||||
|
||||
.
|
||||
.SH NAME
|
||||
\fBMPI_Init_thread\fP \- Initializes the MPI execution environment
|
||||
|
||||
.
|
||||
.SH SYNTAX
|
||||
.ft R
|
||||
|
||||
.
|
||||
.SH C Syntax
|
||||
.nf
|
||||
#include <mpi.h>
|
||||
@ -37,7 +39,8 @@ C/C++ only: Argument vector.
|
||||
.TP 1i
|
||||
required
|
||||
Desired level of thread support (integer).
|
||||
|
||||
.
|
||||
.
|
||||
.SH OUTPUT PARAMETERS
|
||||
.ft R
|
||||
.TP 1i
|
||||
@ -46,7 +49,8 @@ Available level of thread support (integer).
|
||||
.TP 1i
|
||||
IERROR
|
||||
Fortran only: Error status (integer).
|
||||
|
||||
.
|
||||
.
|
||||
.SH DESCRIPTION
|
||||
.ft R
|
||||
This routine, or MPI_Init, must be called before any other MPI routine
|
||||
@ -70,7 +74,8 @@ calls at one time.
|
||||
MPI_THREAD_MULTIPLE
|
||||
If the process is multithreaded, multiple threads may call MPI at once
|
||||
with no restrictions.
|
||||
.SH
|
||||
.
|
||||
.PP
|
||||
The level of thread support available to the program is set in
|
||||
\fIprovided\fP, except in C++, where it is the return value of the
|
||||
function. In Open MPI, the value is dependent on how the library was configured and built. Note that there is no guarantee that \fIprovided\fP will be greater than or equal to
|
||||
@ -90,7 +95,7 @@ them:
|
||||
MPI_Finalize();
|
||||
}
|
||||
.fi
|
||||
|
||||
.
|
||||
.SH NOTES
|
||||
.ft R
|
||||
The Fortran version does not have provisions for \fIargc\fP and
|
||||
@ -104,7 +109,58 @@ MPI_Init_thread or after an MPI_Finalize. In the Open MPI
|
||||
implementation, it should do as little as possible. In particular,
|
||||
avoid anything that changes the external state of the program, such as
|
||||
opening files, reading standard input, or writing to standard output.
|
||||
|
||||
.
|
||||
.
|
||||
.SH MPI_THREAD_MULTIPLE Support
|
||||
.
|
||||
MPI_THREAD_MULTIPLE support is included if Open MPI was configured
|
||||
with the --enable-thread-multiple configure switch. You can check the
|
||||
output of
|
||||
.BR ompi_info (1)
|
||||
to see if Open MPI has MPI_THREAD_MULTIPLE support:
|
||||
.
|
||||
.PP
|
||||
.nf
|
||||
shell$ ompi_info | grep -i thread
|
||||
Thread support: posix (mpi: yes, progress: no)
|
||||
shell$
|
||||
.fi
|
||||
.
|
||||
.PP
|
||||
The "mpi: yes" portion of the above output indicates that Open MPI was
|
||||
compiled with MPI_THREAD_MULTIPLE support.
|
||||
.
|
||||
.PP
|
||||
Note that MPI_THREAD_MULTIPLE support is only lightly tested. It
|
||||
likely does not work for thread-intensive applications. Also note
|
||||
that
|
||||
.I only
|
||||
the MPI point-to-point communication functions for the BTL's listed
|
||||
below are considered thread safe. Other support functions (e.g., MPI
|
||||
attributes) have not been certified as safe when simultaneously used
|
||||
by multiple threads.
|
||||
.
|
||||
.PP
|
||||
.nf
|
||||
tcp
|
||||
sm
|
||||
mx
|
||||
elan
|
||||
self
|
||||
.fi
|
||||
.
|
||||
.PP
|
||||
Note that Open MPI's thread support is in a fairly early stage; the
|
||||
above devices are likely to
|
||||
.IR work ,
|
||||
but the latency is likely to be fairly high. Specifically, efforts so
|
||||
far have concentrated on
|
||||
.IR correctness ,
|
||||
not
|
||||
.I performance
|
||||
(yet).
|
||||
.
|
||||
.
|
||||
.SH ERRORS
|
||||
.ft R
|
||||
Almost all MPI routines return an error value; C routines as
|
||||
@ -119,7 +175,7 @@ I/O function errors. The error handler may be changed with
|
||||
MPI_Comm_set_errhandler; the predefined error handler MPI_ERRORS_RETURN
|
||||
may be used to cause error values to be returned. Note that MPI does not
|
||||
guarantee that an MPI program can continue past an error.
|
||||
|
||||
.
|
||||
.SH SEE ALSO
|
||||
.ft R
|
||||
.nf
|
||||
|
||||
@ -1,5 +1,7 @@
|
||||
. -*- nroff -*-
|
||||
.\" Copyright (c) 2009 Cisco Systems, Inc. All rights reserved.
|
||||
.\" Copyright (c) 2008-2009 Sun Microsystems, Inc. All rights reserved.
|
||||
.\" Copyright (c) 2010 Cisco Systems, Inc. All rights reserved.
|
||||
.\"
|
||||
.\" Man page for ORTE's orterun command
|
||||
.\"
|
||||
@ -1031,13 +1033,16 @@ signal), \fImpirun\fP will print out an error message and kill the rest of the
|
||||
MPI application.
|
||||
.PP
|
||||
User signal handlers should probably avoid trying to cleanup MPI state
|
||||
(Open MPI is, currently, neither thread-safe nor async-signal-safe).
|
||||
For example, if a segmentation fault occurs in \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 \fIMPI_FINALIZE\fP, Bad Things could happen since
|
||||
Open MPI was already "in" MPI when the error occurred. Since \fImpirun\fP
|
||||
will notice that the process died due to a signal, it is probably not
|
||||
necessary (and safest) for the user to only clean up non-MPI state.
|
||||
(Open MPI is currently not async-signal-safe; see MPI_Init_thread(3)
|
||||
for details about
|
||||
.I MPI_THREAD_MULTIPLE
|
||||
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
|
||||
signal handler is invoked, if this user handler attempts to invoke
|
||||
\fIMPI_FINALIZE\fP, Bad Things could happen since Open MPI was already
|
||||
"in" MPI when the error occurred. Since \fImpirun\fP will notice that
|
||||
the process died due to a signal, it is probably not necessary (and
|
||||
safest) for the user to only clean up non-MPI state.
|
||||
.
|
||||
.
|
||||
.
|
||||
@ -1202,18 +1207,19 @@ Be sure also to see the examples throughout the sections above.
|
||||
.
|
||||
.TP 4
|
||||
mpirun -np 4 -mca btl ib,tcp,self prog1
|
||||
Run 4 copies of prog1 using the "ib", "tcp", and "self" BTL's for the transport
|
||||
of MPI messages.
|
||||
Run 4 copies of prog1 using the "ib", "tcp", and "self" BTL's for the
|
||||
transport of MPI messages.
|
||||
.
|
||||
.
|
||||
.TP 4
|
||||
mpirun -np 4 -mca btl tcp,sm,self
|
||||
.br
|
||||
--mca btl_tcp_if_include ce0 prog1
|
||||
--mca btl_tcp_if_include eth0 prog1
|
||||
.br
|
||||
Run 4 copies of prog1 using the "tcp", "sm" and "self" BTLs for the transport of
|
||||
MPI messages, with TCP using only the ce0 interface to communicate. Note that
|
||||
other BTLs have similar if_include MCA parameters.
|
||||
Run 4 copies of prog1 using the "tcp", "sm" and "self" BTLs for the
|
||||
transport of MPI messages, with TCP using only the eth0 interface to
|
||||
communicate. Note that other BTLs have similar if_include MCA
|
||||
parameters.
|
||||
.
|
||||
.\" **************************
|
||||
.\" Diagnostics Section
|
||||
@ -1243,5 +1249,5 @@ be the first rank that died but is not guaranteed to be so.
|
||||
.\" See Also Section
|
||||
.\" **************************
|
||||
.
|
||||
.\" .SH SEE ALSO
|
||||
.\" orted(1), ompi-server(1)
|
||||
.SH SEE ALSO
|
||||
MPI_Init_thread(3)
|
||||
|
||||
Загрузка…
x
Ссылка в новой задаче
Block a user