[mpich-commits] [mpich] MPICH primary repository branch, master, updated. v3.0.4-316-g1deb8ae

mysql vizuser noreply at mpich.org
Sat Jun 22 10:02:52 CDT 2013

This is an automated email from the git hooks/post-receive script. It was
generated because a ref change was pushed to the repository containing
the project "MPICH primary repository".

The branch, master has been updated
       via  1deb8ae7c393928272bc29ad27ad27ecdafd4116 (commit)
       via  c5b009001f1ccda595ada8db42e831208c4dbdb4 (commit)
      from  6f05c767e32172545cf8a50538762943d7ff5618 (commit)

Those revisions listed above that are new to this repository have
not appeared on any other notification email; so we list those
revisions in full, below.

- Log -----------------------------------------------------------------

commit 1deb8ae7c393928272bc29ad27ad27ecdafd4116
Author: Pavan Balaji <balaji at mcs.anl.gov>
Date:   Sat Jun 22 09:50:19 2013 -0500

    General cleanup of RELEASE_NOTES.
    Removed parts that are no longer relevant due to deprecated features
    in MPICH or in the MPI standard.

index ab5a914..20c3b0f 100644
@@ -10,19 +10,15 @@
 ### Large counts
  * The new MPI-3 "large count" routines (e.g., MPI_Type_size_x) do not
    work correctly due to 64-bit to 32-bit truncations occurring inside
    the MPICH library.  We expect to fix this in upcoming releases.
-### Known runtime failures
- * MPI_Alltoall might fail in some cases because of the newly added
-   fault-tolerance features. If you are seeing this error, try setting
-   the environment variable MPICH_ENABLE_COLL_FT_RET=0.
-### Threads
+### Fine-grained thread safety
  * ch3:sock does not (and will not) support fine-grained threading.
@@ -74,14 +70,6 @@
- * The MPD process manager can only handle relatively small amounts of
-   data on stdin and may also have problems if there is data on stdin
-   that is not consumed by the program.
- * The SMPD process manager does not work reliably with threaded MPI
-   processes. MPI_Comm_spawn() does not currently work for >= 256
-   arguments with smpd.
 ### Performance issues
@@ -96,12 +84,3 @@
    operations may erroneously fail. By explicitly completed, we mean
    that the request associated with the operation is completed by one
    of the MPI_Test or MPI_Wait routines.
-### C++ Binding:
- * The MPI datatypes corresponding to Fortran datatypes are not
-   available (e.g., no MPI::DOUBLE_PRECISION).
- * MPI::ERRORS_RETURN may still throw exceptions in the event of an
-   error rather than silently returning.


commit c5b009001f1ccda595ada8db42e831208c4dbdb4
Author: Pavan Balaji <balaji at mcs.anl.gov>
Date:   Sat Jun 22 09:42:36 2013 -0500

    Added a note on the ABI issues.

index 49f2e7e..ab5a914 100644
@@ -2,6 +2,14 @@
                         KNOWN ISSUES
+### ABI issues
+ * The format of MPI_INFO_ENV was changed between v3.0 and v3.0.1 in
+   an ABI incompatible way.  The change was not caught, unfortunately,
+   and the ABI string not updated appropriately.
+   http://trac.mpich.org/projects/mpich/ticket/1719
 ### Large counts
  * The new MPI-3 "large count" routines (e.g., MPI_Type_size_x) do not


Summary of changes:
 RELEASE_NOTES |   33 ++++++++++-----------------------
 1 files changed, 10 insertions(+), 23 deletions(-)

MPICH primary repository

More information about the commits mailing list