From e12485735311b31433422e6dac79e937889b9f17 Mon Sep 17 00:00:00 2001 From: Jeff Squyres Date: Fri, 10 Nov 2006 17:41:42 +0000 Subject: [PATCH] Various updates. This commit was SVN r12540. --- README | 78 +++++++++++++++++++++++++++++++++++++++++----------------- 1 file changed, 55 insertions(+), 23 deletions(-) diff --git a/README b/README index d29109396f..b28ade591f 100644 --- a/README +++ b/README @@ -41,8 +41,40 @@ Thanks for your time. =========================================================================== +Release notes for SC 2006 beta: + +- This tarball has had some level of testing within the Open MPI + developers, but has not been widely tested with real world + applications. We'd appreciate your feedback. + +- Running heterogenious MPI jobs (e.g., different endian between + multiple hosts) is not fully working yet. + +- Some MPI jobs may not clean up properly if errors occur: + - mpirun may "hang" and have to be killed from another session + - ORTE daemons may be left orphaned on some nodes and need to be + manually killed + +- Not all items marked as resolved in the v1.1.3 section of the NEWS + file have been migrated to this 1.2 release yet. A new beta release + is expected shortly after SC 2006 that contains these fixes: + - Workaround for Intel C++ compiler bug + - MPI_SIZEOF fixes for COMPLEX types + +- MPI jobs running on OpenIB / OpenFabrics networks that + simultaneously post a large number of non-blocking sends of small + messages may fail. This issue is fixed on the Open MPI development + head, and will be included in the post-SC beta release. + +- Striping MPI messages across multiple TCP interfaces is not working. + +- See Open MPI's bug tracking system for a full list of outstanding + issues: https://svn.open-mpi.org/trac/ompi/report + +=========================================================================== + The following abbreviated list of release notes applies to this code -base as of this writing (12 Sep 2006): +base as of this writing (10 Nov 2006): - Open MPI includes support for a wide variety of supplemental hardware and software package. When configuring Open MPI, you may @@ -87,6 +119,8 @@ base as of this writing (12 Sep 2006): - Linux, 64 bit (x86), with gcc - OS X (10.3), 32 bit, with gcc - OS X (10.4), 32 bit, with gcc + - Solaris 10 update 2, SPARC and AMD, 32 and 64 bit, with Sun Studio + 10 - Other systems have been lightly (but not fully tested): - Other compilers on Linux, 32 and 64 bit @@ -197,12 +231,6 @@ base as of this writing (12 Sep 2006): shared memory, and Myrinet/GM. Myrinet/GM has only been lightly tested. -- Due to limitations in the Libtool 1.5 series, Fortran 90 MPI - bindings support can only be built as a static library. It is - expected that Libtool 2.0 (and therefore future releases of Open - MPI) will be able to support shared libraries for the Fortran 90 - bindings. - - The XGrid support is experimental - see the Open MPI FAQ and this post on the Open MPI user's mailing list for more information: @@ -226,16 +254,7 @@ base as of this writing (12 Sep 2006): - The Open Fabrics Enterprise Distribution (OFED) software package v1.0 will not work properly with Open MPI v1.2 (and later) due to how its Mellanox InfiniBand plugin driver is created. The problem - is fixed OFED v1.1 (and beyond). - -- The current version of the Open MPI point-to-point engine does not - yet support hardware-level MPI message matching. As such, MPI - message matching must be performed in software, artificially - increasing latency for short messages on certain networks (such as - MX and hardware-supported Portals). Future versions of Open MPI - will support hardware matching on networks that provide it, and will - eliminate the extra overhead of software MPI message matching where - possible. + is fixed OFED v1.1 (and later). - The Fortran 90 MPI bindings can now be built in one of three sizes using --with-mpi-f90-size=SIZE (see description below). These sizes @@ -327,13 +346,23 @@ for a full list); a summary of the more commonly used ones follows: most cases. This option is only needed for special configurations. --with-openib= - Specify the directory where the Open Fabrics (previously known as + Specify the directory where the OpenFabrics (previously known as OpenIB) libraries and header files are located. This enables Open Fabrics support in Open MPI. --with-openib-libdir= - Look in directory for the OPENIB libraries. By default, Open MPI will - look in /lib and /lib64, which covers + Look in directory for the OpenFabrics libraries. By default, Open + MPI will look in /lib and /lib64, which covers most cases. This option is only + needed for special configurations. + +--with-psm= + Specify the directory where the QLogic PSM library and header files + are located. This enables InfiniPath support in Open MPI. + +--with-psm-libdir= + Look in directory for the PSM libraries. By default, Open MPI will + look in /lib and /lib64, which covers most cases. This option is only needed for special configurations. --with-tm= @@ -601,12 +630,14 @@ MPI component frameworks: allocator - Memory allocator bml - BTL management layer -btl - MPI point-to-point byte transfer layer +btl - MPI point-to-point byte transfer layer, used for MPI + point-to-point messages on some types of networks coll - MPI collective algorithms io - MPI-2 I/O mpool - Memory pooling +mtl - Matching transport layer, used for MPI point-to-point + messages on some types of networks pml - MPI point-to-point management layer -ptl - (Outdated / deprecated) MPI point-to-point transport layer rcache - Memory registration cache topo - MPI topology routines @@ -617,6 +648,7 @@ errmgr - RTE error manager gpr - General purpose registry iof - I/O forwarding ns - Name server +odls - OpenRTE daemon local launch subsystem oob - Out of band messaging pls - Process launch system ras - Resource allocation system @@ -626,7 +658,7 @@ rmgr - Resource manager rml - RTE message layer schema - Name schemas sds - Startup / discovery service -soh - State of health monitor +smr - State-of-health monitoring subsystem Miscellaneous frameworks: -------------------------