2006-01-19 18:21:53 +03:00
|
|
|
Copyright (c) 2004-2006 The Trustees of Indiana University and Indiana
|
2005-11-22 02:00:12 +03:00
|
|
|
University Research and Technology
|
|
|
|
Corporation. All rights reserved.
|
2006-01-20 15:33:31 +03:00
|
|
|
Copyright (c) 2004-2006 The University of Tennessee and The University
|
2005-11-22 02:00:12 +03:00
|
|
|
of Tennessee Research Foundation. All rights
|
|
|
|
reserved.
|
2006-01-20 15:33:31 +03:00
|
|
|
Copyright (c) 2004-2006 High Performance Computing Center Stuttgart,
|
2005-11-22 02:00:12 +03:00
|
|
|
University of Stuttgart. All rights reserved.
|
2006-01-20 15:33:31 +03:00
|
|
|
Copyright (c) 2004-2006 The Regents of the University of California.
|
2005-11-22 02:00:12 +03:00
|
|
|
All rights reserved.
|
2006-04-06 15:43:24 +04:00
|
|
|
Copyright (c) 2006 Cisco Systems, Inc. All rights reserved.
|
2006-04-24 18:15:22 +04:00
|
|
|
Copyright (c) 2006 Voltaire, Inc. All rights reserved.
|
2005-11-22 02:00:12 +03:00
|
|
|
$COPYRIGHT$
|
|
|
|
|
|
|
|
Additional copyrights may follow
|
|
|
|
|
|
|
|
$HEADER$
|
|
|
|
|
|
|
|
===========================================================================
|
|
|
|
|
|
|
|
This file contains the main features as well as overviews of specific
|
|
|
|
bug fixes (and other actions) for each version of Open MPI since
|
|
|
|
version 1.0.
|
|
|
|
|
2006-06-16 17:37:25 +04:00
|
|
|
1.2
|
|
|
|
---
|
|
|
|
|
|
|
|
- Addition of OpenIB-based unreliable datagram BTL ("ud").
|
|
|
|
- Addition of UDAPL BTL ("udapl").
|
|
|
|
|
|
|
|
|
|
|
|
Post 1.1 -- not yet decided if 1.2 or 1.1.1
|
|
|
|
-------------------------------------------
|
|
|
|
|
|
|
|
- Allow propagation of SIGUSR1 and SIGUSR2 signals from mpirun to
|
|
|
|
back-end MPI processes.
|
|
|
|
- Add -V/--version switch to mpirun.
|
|
|
|
|
|
|
|
|
2005-11-22 02:00:12 +03:00
|
|
|
1.1
|
|
|
|
---
|
2006-02-13 00:25:11 +03:00
|
|
|
|
2006-06-16 17:37:25 +04:00
|
|
|
- Various MPI datatype fixes, optimizations.
|
|
|
|
- Fixed various problems on the SPARC architecture (e.g., not
|
|
|
|
correctly aligning addresses within structs).
|
|
|
|
- Addition of "dr" pml component (data reliability) for running in
|
|
|
|
unreliable networks (such as those at high altitudes). Includes
|
|
|
|
functionality for retransmission due to problems with end-to-end
|
|
|
|
data content checking or loss of data in the network.
|
|
|
|
- Improvements in various run-time error messages to be more clear
|
|
|
|
about what they mean and where the errors are occurring.
|
|
|
|
- Various fixes to mpirun's handling of --prefix.
|
|
|
|
- Updates and fixes for Cray/Red Storm support.
|
Bring over changes from the /tmp/fortran-stuff series:
- Make the F90 bindings compile and link properly with gfortran 4.0,
4.1, Intel 9.0, PGI 6.1, Sun (don't know version offhand -- the most
current as of this writing, I think), and NAG 5.2, although some
have limitations (e.g., NAG can't seem to handle the medium and
large sizes)
- Building the F90 "small" module size is now the default, even for
developers
- Split up mpif.h into multiple files because parts of it were toxic
to the F90 bindings
- Properly specify unsized/unshaped arrays to make the bindings work
on all known compilers
- Make ompi_info show Fortran 90 bindings size
- XML somewhat lags the generated scripts as of this commit, but
functionality was my main goal -- the XML can be updated later (if
at all).
This commit was SVN r10118.
2006-05-30 18:37:41 +04:00
|
|
|
- Major improvements to the Fortran 90 MPI bindings:
|
|
|
|
- General improvements in compile/linking time and portability
|
|
|
|
between different F90 compilers.
|
2006-06-16 17:37:25 +04:00
|
|
|
- Addition of "trivial", "small" (the default), and "medium"
|
|
|
|
Fortran 90 MPI module sizes (v1.0.x's F90 module was
|
Bring over changes from the /tmp/fortran-stuff series:
- Make the F90 bindings compile and link properly with gfortran 4.0,
4.1, Intel 9.0, PGI 6.1, Sun (don't know version offhand -- the most
current as of this writing, I think), and NAG 5.2, although some
have limitations (e.g., NAG can't seem to handle the medium and
large sizes)
- Building the F90 "small" module size is now the default, even for
developers
- Split up mpif.h into multiple files because parts of it were toxic
to the F90 bindings
- Properly specify unsized/unshaped arrays to make the bindings work
on all known compilers
- Make ompi_info show Fortran 90 bindings size
- XML somewhat lags the generated scripts as of this commit, but
functionality was my main goal -- the XML can be updated later (if
at all).
This commit was SVN r10118.
2006-05-30 18:37:41 +04:00
|
|
|
equivalent to "medium"). See the README file for more
|
|
|
|
explanation.
|
|
|
|
- Fix various MPI F90 interface functions and constant types to
|
|
|
|
match. Thanks to Michael Kluskens for pointing out the problems
|
|
|
|
to us.
|
2006-05-25 16:29:17 +04:00
|
|
|
- Allow short messagees to use RDMA (vs. send/receive semantics) to a
|
|
|
|
limited number peers in both the mvapi and openib BTL components.
|
|
|
|
This reduces communication latency over IB channels.
|
2006-04-13 08:24:32 +04:00
|
|
|
- Numerous performance improvements throughout the entire code base.
|
|
|
|
- Many minor threading fixes.
|
2006-04-07 08:57:53 +04:00
|
|
|
- Add a define OMPI_SKIP_CXX to allow the user to skip the mpicxx.h from
|
|
|
|
being included in mpi.h. It allows the user to compile C code with a CXX
|
|
|
|
compiler without including the CXX bindings.
|
2006-04-13 08:24:32 +04:00
|
|
|
- PERUSE support has been added. In order to activate it add
|
|
|
|
--enable-peruse to the configure options. All events described in
|
|
|
|
the PERUSE 2.0 draft are supported, plus one Open MPI
|
2006-03-31 21:20:11 +04:00
|
|
|
extension. PERUSE_COMM_REQ_XFER_CONTINUE allow to see how the data
|
|
|
|
is segmented internally, using multiple interfaces or the pipeline
|
|
|
|
engine. However, this version only support one event of each type
|
|
|
|
simultaneously attached to a communicator.
|
2006-03-25 06:02:44 +03:00
|
|
|
- Add support for running jobs in heterogeneous environments.
|
|
|
|
Currently supports environments with different endianness and
|
|
|
|
different representations of C++ bool and Fortran LOGICAL.
|
|
|
|
Mismatched sizes for other datatypes is not supported.
|
|
|
|
- Open MPI now includes an implementation of the MPI-2 One-Sided
|
|
|
|
Communications specification.
|
2006-02-12 18:13:14 +03:00
|
|
|
- Open MPI is now configurable in cross-compilation environments.
|
|
|
|
Several Fortran 77 and Fortran 90 tests need to be pre-seeded with
|
|
|
|
results from a config.cache-like file.
|
2005-11-22 02:00:12 +03:00
|
|
|
- Add --debug option to mpirun to generically invoke a parallel debugger.
|
2006-03-04 17:24:44 +03:00
|
|
|
|
2005-11-22 02:00:12 +03:00
|
|
|
|
2006-04-13 22:56:02 +04:00
|
|
|
1.0.3
|
|
|
|
-----
|
|
|
|
|
2006-06-16 17:37:25 +04:00
|
|
|
- Require that the openib BTL find <sysfs/libsysfs.h>. Thanks to Josh
|
|
|
|
Aune for the suggestion.
|
|
|
|
- Include updates to support the upcoming Autoconf 2.60 and Libtool
|
|
|
|
2.0. Thanks to Ralf Wildenhues for all the work!
|
|
|
|
- Fix bug with infinite loop in the "round robin" process mapper.
|
|
|
|
Thanks to Paul Donohue for reporting the problem.
|
|
|
|
- Enusre that memory hooks are removed properly during MPI_FINALIZE.
|
|
|
|
Thanks to Neil Ludban for reporting the problem.
|
|
|
|
- Various fixes to the included support for ROMIO.
|
2006-05-26 16:21:52 +04:00
|
|
|
- Fix to ensure that MPI_LONG_LONG and MPI_LONG_LONG_INT are actually
|
|
|
|
synonyms, as defined by the MPI standard. Thanks to Martin Audet
|
|
|
|
for reporting this.
|
2006-05-26 16:09:41 +04:00
|
|
|
- Fix Fortran 90 configure tests to properly utilize LDFLAGS and LIBS.
|
|
|
|
Thanks to Terry Reeves for reporting the problem.
|
2006-05-25 16:28:04 +04:00
|
|
|
- Fix shared memory progression in asynchronous progress scenarios.
|
|
|
|
Thanks to Mykael Bouquey for reporting the problem.
|
2006-05-23 22:28:41 +04:00
|
|
|
- Fixed back-end operations for predefined MPI_PROD for some
|
|
|
|
datatypes. Thanks to Bert Wesarg for reporting this.
|
2006-05-19 01:25:56 +04:00
|
|
|
- Adapted configure to be able to handle Torque 2.1.0p0's (and above)
|
|
|
|
new library name. Thanks to Brock Palen for pointing this out and
|
|
|
|
providing access to a Torque 2.1.0p0 cluster to test with.
|
2006-05-18 19:43:32 +04:00
|
|
|
- Fixed situation where mpirun could set a shell pipeline's stdout
|
|
|
|
to non-blocking, causing the shell pipeline to prematurely fail.
|
|
|
|
Thanks to Darrell Kresge for figuring out what was happening.
|
2006-05-17 04:06:30 +04:00
|
|
|
- Fixed problems with leave_pinned that could cause Badness with the
|
|
|
|
mvapi BTL.
|
2006-05-15 20:45:32 +04:00
|
|
|
- Fixed problems with MPI_FILE_OPEN and non-blocking MPI-2 IO access.
|
2006-05-11 07:05:09 +04:00
|
|
|
- Fixed various InfiniBand port matching issues during startup.
|
|
|
|
Thanks to Scott Weitzenkamp for identifying these problems.
|
2006-05-25 16:28:04 +04:00
|
|
|
- Fixed various configure, build and run-time issues with ROMIO.
|
|
|
|
Thanks to Dries Kimpe for bringing them to our attention.
|
2006-05-05 16:00:33 +04:00
|
|
|
- Fixed error in MPI_COMM_SPLIT when dealing with intercommunicators.
|
|
|
|
Thanks to Bert Wesarg for identifying the problem.
|
2006-05-05 06:27:43 +04:00
|
|
|
- Fixed backwards handling of "high" parameter in MPI_INTERCOMM_MERGE.
|
|
|
|
Thanks to Michael Kluskens for pointing this out to us.
|
2006-05-02 18:39:11 +04:00
|
|
|
- Fixed improper handling of string arguments in Fortran bindings
|
|
|
|
for MPI-IO functionality
|
2006-04-24 01:14:03 +04:00
|
|
|
- Fixed segmentation fault with 64 bit applications on Solaris when
|
|
|
|
using the shared memory transports.
|
2006-04-13 22:56:02 +04:00
|
|
|
- Fixed MPI_COMM_SELF attributes to free properly at the beginning of
|
|
|
|
MPI_FINALIZE. Thanks to Martin Audet for bringing this to our
|
|
|
|
attention.
|
2006-04-14 19:46:30 +04:00
|
|
|
- Fixed alignment tests for cross-compiling to not cause errors with
|
|
|
|
recent versions of GCC.
|
2006-04-13 22:56:02 +04:00
|
|
|
|
|
|
|
|
2005-12-13 01:15:29 +03:00
|
|
|
1.0.2
|
|
|
|
-----
|
|
|
|
|
2006-04-06 15:43:24 +04:00
|
|
|
- Fixed assembly race condition on AMD64 platforms.
|
|
|
|
- Fixed residual .TRUE. issue with copying MPI attributes set from
|
|
|
|
Fortran.
|
|
|
|
- Remove unnecessary logic from Solaris pty I/O forwarding. Thanks to
|
|
|
|
Francoise Roch for bringing this to our attention.
|
2006-04-04 08:34:08 +04:00
|
|
|
- Fixed error when count = 0 was given for multiple completion MPI
|
|
|
|
functions (MPI_TESTSOME, MPI_TESTANY, MPI_TESTALL, MPI_WAITSOME,
|
|
|
|
MPI_WAITANY, MPI_WAITALL).
|
2006-04-06 15:43:24 +04:00
|
|
|
- Better handling in MPI_ABORT for when peer processes have already
|
|
|
|
died, especially under some resource managers.
|
|
|
|
- Random updates to README file, to include notes about the Portland
|
|
|
|
compilers.
|
|
|
|
- Random, small threading fixes to prevent deadlock.
|
2006-03-24 18:39:09 +03:00
|
|
|
- Fixed a problem with handling long mpirun app files. Thanks to Ravi
|
|
|
|
Manumachu for identifying the problem.
|
2006-03-16 17:46:58 +03:00
|
|
|
- Fix handling of strings in several of the Fortran 77 bindings.
|
2006-03-16 17:40:03 +03:00
|
|
|
- Fix LinuxPPC assembly issues. Thanks to Julian Seward for reporting
|
|
|
|
the problem.
|
2006-03-11 20:56:30 +03:00
|
|
|
- Enable pty support for standard I/O forwarding on platforms that
|
|
|
|
have ptys but do not have openpty(). Thanks to Pierre Valiron for
|
|
|
|
bringing this to our attention.
|
2006-03-10 07:09:41 +03:00
|
|
|
- Disable inline assembly for PGI compilers to avoid compiler errors.
|
|
|
|
Thanks to Troy Telford for bringing this to our attention.
|
2006-03-09 20:07:29 +03:00
|
|
|
- Added MPI_UNSIGNED_CHAR and MPI_SIGNED_CHAR to the allowed reduction
|
|
|
|
types.
|
2006-03-09 15:14:16 +03:00
|
|
|
- Fix a segv in variable-length message displays on Opterons running
|
|
|
|
Solaris. Thanks to Pierre Valiron for reporting the issue.
|
2006-03-04 21:35:33 +03:00
|
|
|
- Added MPI_BOOL to the intrinsic reduction operations MPI_LAND,
|
|
|
|
MPI_LOR, MPI_LXOR. Thanks to Andy Selle for pointing this out to us.
|
2006-02-23 05:03:59 +03:00
|
|
|
- Fixed TCP BTL network matching logic during MPI_INIT; in some cases
|
|
|
|
on multi-NIC nodes, a NIC could get paired with a NIC on another
|
|
|
|
network (typically resulting in deadlock). Thanks to Ken Mighell
|
|
|
|
for pointing this out to us.
|
2006-02-16 23:40:23 +03:00
|
|
|
- Change the behavior of orterun (mpirun, mpirexec) to search for
|
|
|
|
argv[0] and the cwd on the target node (i.e., the node where the
|
|
|
|
executable will be running in all systems except BProc, where the
|
|
|
|
searches are run on the node where orterun is invoked).
|
2006-02-16 23:14:33 +03:00
|
|
|
- Fix race condition in shared memory transport that could cause
|
|
|
|
crashes on machines with weak memory consistency models (including
|
|
|
|
POWER/PowerPC machines).
|
2006-02-16 07:41:38 +03:00
|
|
|
- Fix warnings about setting read-only MCA parameters on bproc systems.
|
2006-02-16 01:46:40 +03:00
|
|
|
- Change the exit status set by mpirun when an application process is
|
|
|
|
killed by a signal. The exit status is now set to signo + 128, which
|
|
|
|
conforms with the behavior of (almost) all shells.
|
2006-02-13 00:25:11 +03:00
|
|
|
- Correct a datatype problem with the convertor when partially
|
|
|
|
unpacking data. Now we can position the convertor to any position
|
|
|
|
not only on the predefined types boundaries. Thanks to Yvan Fournier
|
|
|
|
for reporting this to us.
|
2006-02-05 02:28:48 +03:00
|
|
|
- Fix a number of standard I/O forwarding issues, including the
|
|
|
|
ability to background mpirun and a loss of data issue when
|
|
|
|
redirecting mpirun's standard input from a file.
|
2006-02-11 03:19:57 +03:00
|
|
|
- Fixed bug in ompi_info where rcache and bml MCA parameters would not
|
|
|
|
be displayed.
|
|
|
|
- Fixed umask issues in the session directory. Thanks to Glenn Morris
|
|
|
|
for reporting this to us.
|
2006-02-02 09:26:55 +03:00
|
|
|
- Fixed tcsh-based LD_LIBRARY_PATH issues with --prefix. Thanks to
|
|
|
|
Glen Morris for identifying the problem and suggesting the fix.
|
2006-02-02 08:50:15 +03:00
|
|
|
- Removed extraneous \n's when setting PATH and LD_LIBRARY_PATH in the
|
|
|
|
rsh startup. Thanks to Glen Morris for finding these typos.
|
2006-02-01 19:01:32 +03:00
|
|
|
- Fixed missing constants in MPI C++ bindings.
|
2006-01-20 15:33:31 +03:00
|
|
|
- Fixed some errors caused by threading issues.
|
2006-01-19 18:34:41 +03:00
|
|
|
- Fixed openib BTL flow control logic to not overrun the number of
|
|
|
|
send wqes available.
|
|
|
|
- Update to match newest OpenIB user-level library API. Thanks to
|
|
|
|
Roland Dreier for submitting this patch.
|
|
|
|
- Report errors properly when failing to register memory in the openib
|
|
|
|
BTL.
|
|
|
|
- Reduce memory footprint of openib BTL.
|
2006-01-19 18:21:53 +03:00
|
|
|
- Fix parsing problem with mpirun's "-tv" switch. Thanks to Chris
|
|
|
|
Gottbrath for supplying the fix.
|
2006-01-12 06:39:51 +03:00
|
|
|
- Fix Darwin net/if.h configure warning.
|
|
|
|
- The GNU assembler unbelievably defaults to making stacks executable.
|
|
|
|
So when using gas, add flags to explicitly tell it to not make
|
|
|
|
stacks executable (lame but necessary).
|
2006-01-09 21:10:12 +03:00
|
|
|
- Add missing MPI::Request::Get_status() methods. Thanks to Bill
|
|
|
|
Saphir for pointing this out to us.
|
2006-01-05 17:55:00 +03:00
|
|
|
- Improved error messages on memory registration errors (e.g., when
|
|
|
|
using high-speed networks).
|
|
|
|
- Open IB support now checks firmware for how many outstanding RDMA
|
|
|
|
requests are supported. Thanks to Mellanox for pointing this out to
|
|
|
|
us.
|
|
|
|
- Enable printing of stack traces in MPI processes upon SIGBUS,
|
|
|
|
SIGSEGV, and SIGFPE if the platform supports it.
|
|
|
|
- Fixed F90 compilation support for the Lahey compiler.
|
|
|
|
- Fixed issues with ROMIO shared library support.
|
|
|
|
- Fixed internal accounting problems with rsh support.
|
2005-12-20 16:39:00 +03:00
|
|
|
- Update to GNU Libtool 1.5.22.
|
2005-12-20 03:49:59 +03:00
|
|
|
- Fix error in configure script when setting CCAS to ias (the Intel
|
2006-03-16 17:40:03 +03:00
|
|
|
assembler).
|
2005-12-16 22:19:14 +03:00
|
|
|
- Added missing MPI::Intercomm collectives.
|
|
|
|
- Fixed MPI_IN_PLACE handling for Fortran collectives.
|
2005-12-16 00:24:42 +03:00
|
|
|
- Fixed some more C++ const_cast<> issues. Thanks for Martin Audet
|
|
|
|
(again) for bringing this to our attention.
|
2005-12-15 22:24:50 +03:00
|
|
|
- Updated ROMIO with the version from MPICH 1.2.7p1, marked as version
|
|
|
|
2005-06-09.
|
2005-12-13 01:15:29 +03:00
|
|
|
- Fixes for some cases where the use of MPI_BOTTOM could cause
|
|
|
|
problems.
|
2005-12-13 23:30:36 +03:00
|
|
|
- Properly handle the case where an mVAPI does not have shared receive
|
|
|
|
queue support (such as the one shipped by SilverStorm / Infinicon
|
|
|
|
for OS X).
|
2005-12-13 01:15:29 +03:00
|
|
|
|
|
|
|
|
2005-11-22 02:00:12 +03:00
|
|
|
1.0.1
|
|
|
|
-----
|
|
|
|
|
2005-12-08 16:04:38 +03:00
|
|
|
- Fixed assembly on Solaris AMD platforms. Thanks to Pierre Valiron
|
|
|
|
for bringing this to our attention.
|
2005-12-06 22:13:42 +03:00
|
|
|
- Fixed long messages in the send-to-self case.
|
|
|
|
- Ensure that when the "leave_pinned" option is used, the memory hooks
|
|
|
|
are also enabled. Thanks to Gleb Natapov for pointing this out.
|
2005-12-01 21:37:32 +03:00
|
|
|
- Fixed compile errors for IRIX.
|
2005-12-13 01:15:29 +03:00
|
|
|
- Allow hostfiles to have integer host names (for BProc clusters).
|
2005-12-01 21:07:15 +03:00
|
|
|
- Fixed a problem with message matching of out-of-order fragments in
|
|
|
|
multiple network device scenarios.
|
2005-11-30 14:07:40 +03:00
|
|
|
- Converted all the C++ MPI bindings to use proper const_cast<>'s
|
|
|
|
instead of old C-style casts to get rid of const-ness. Thanks to
|
|
|
|
Martin Audet for raising the issue with us.
|
|
|
|
- Converted MPI_Offset to be a typedef instead of a #define because it
|
|
|
|
causes problems for some C++ parsers. Thanks to Martin Audet for
|
|
|
|
bringing this to our attention.
|
2005-11-30 02:44:56 +03:00
|
|
|
- Improved latency of TCP BTL.
|
|
|
|
- Fixed index value in MPI_TESTANY to be MPI_UNDEFINED if some
|
|
|
|
requests were not MPI_REQUEST_NULL, but no requests finished.
|
2005-11-29 21:43:27 +03:00
|
|
|
- Fixed several Fortran MPI API implementations that incorrectly used
|
|
|
|
integers instead of logicals or address-sized integers.
|
2005-11-29 04:06:44 +03:00
|
|
|
- Fix so that Open MPI correctly handles the Fortran value for .TRUE.,
|
|
|
|
regardless of what the Fortran compiler's value for .TRUE. is.
|
2005-11-28 23:09:46 +03:00
|
|
|
- Improved scalability of MX startup.
|
2005-11-28 22:39:07 +03:00
|
|
|
- Fix datatype offset handling in the coll basic component's
|
|
|
|
MPI_SCATTERV implementation.
|
2005-11-28 22:36:59 +03:00
|
|
|
- Fix EOF handling on stdin.
|
2005-11-22 18:33:04 +03:00
|
|
|
- Fix missing MPI_F_STATUS_IGNORE and MPI_F_STATUSES_IGNORE
|
|
|
|
instanatiations. Thanks to Anthony Chan for pointing this out.
|
2005-11-22 02:00:12 +03:00
|
|
|
- Add a missing value for MPI_WIN_NULL in mpif.h.
|
|
|
|
- Bring over some fixes for the sm btl that somehow didn't make it
|
|
|
|
over from the trunk before v1.0. Thanks to Beth Tibbitts and Bill
|
|
|
|
Chung for helping identify this issue.
|
|
|
|
- Bring over some fixes for the iof that somehow didn't make it over
|
|
|
|
from the trunk before v1.0.
|
|
|
|
- Fix for --with-wrapper-ldflags handling. Thanks to Dries Kimpe for
|
|
|
|
pointing this out to us.
|
|
|
|
|
|
|
|
|
|
|
|
1.0
|
|
|
|
---
|
|
|
|
|
|
|
|
Initial public release.
|