1. 10 Apr, 2015 3 commits
  2. 27 Mar, 2015 1 commit
    • Pavan Balaji's avatar
      Bump up the bcast2/bcast3 timeouts a bit more. · 5538b7ce
      Pavan Balaji authored
      FreeBSD seems to take slightly more than 20 minutes to run these tests
      primarily because the poll() call is somehow superslow on that OS.
      This new timeout should be sufficient to cover that case.
      
      No reviewer.
      5538b7ce
  3. 09 Mar, 2015 1 commit
  4. 02 Mar, 2015 1 commit
  5. 14 Nov, 2014 1 commit
    • Min Si's avatar
      Increase bcast2 and bcast3 timelimit to 20mins. · e9a24700
      Min Si authored
      Some overloaded nightly test nodes use almost 20 minutes for running
      these tests. We increase their time limit for now to easily figure out
      other bugs reported by nightly test.
      e9a24700
  6. 13 Nov, 2014 1 commit
  7. 12 Nov, 2014 1 commit
  8. 05 Nov, 2014 1 commit
  9. 10 Jun, 2014 1 commit
    • Wesley Bland's avatar
      Add tests for new buffer aliasing checks · 5b4bdef9
      Wesley Bland authored
      
      
      Added tests to the existing test suite. Usually these tests are next to
      existing MPI_IN_PLACE tests to make sure that the IN_PLACE checks are correct.
      For the nonblocking tests, they are all in one big test (nonblocking4) since
      the other nonblocking tests were already in that format.
      
      Fixes #2049
      
      Signed-off-by: default avatarAntonio J. Pena <apenya@mcs.anl.gov>
      5b4bdef9
  10. 24 Jan, 2013 1 commit
  11. 19 Nov, 2012 1 commit
  12. 23 Oct, 2012 1 commit
  13. 19 Oct, 2012 1 commit
  14. 21 May, 2012 1 commit
  15. 09 May, 2012 1 commit
  16. 07 May, 2012 1 commit
  17. 01 May, 2012 1 commit
  18. 28 Apr, 2012 1 commit
  19. 09 Apr, 2012 1 commit
    • David Goodell's avatar
      [svn-r9686] tt#1601: disable "COLL_FT_RET" by default · 3e6cc34f
      David Goodell authored
      The problem is that the (previously on by default) collective error
      propagation functionality is implemented in a way that is fundamentally
      incompatible with the way that nonblocking collectives are implemented.
      
      Thanks to Jed Brown for the bug report and reproducer.
      
      No reviewer.
      3e6cc34f
  20. 22 Jun, 2011 1 commit
  21. 20 Jun, 2011 1 commit
    • David Goodell's avatar
      [svn-r8702] extend the timeout for the nonblocking{2,3} tests to 7 minutes · 6dc39c2d
      David Goodell authored
      The nonblocking3 test, in particular, was failing with timeouts in the nightly
      tests.  420 seconds is the value we use for bcast2 and bcast3, so it seems
      reasonable to use the same value here.  If nonblocking3 continues to fail with
      timeouts with the new value then there is probably a hang occurring in the test
      or the MPI library.
      
      No reviewer.
      6dc39c2d
  22. 23 May, 2011 1 commit
    • David Goodell's avatar
      [svn-r8604] add new nonblocking3 test · 38de9b32
      David Goodell authored
      The test "randomly" selects NBC requests to post and ways to complete
      those requests, over and over again in a loop.  This test is intended to
      stress the NBC implementation by keeping many collectives in flight
      simultaneously on multiple communicators, and by completing them with
      multiple different mechanisms.  The current NBC ops that are actually
      posted are derived from the nonblocking2 test.
      
      Reviewed by buntinas@.
      38de9b32
  23. 19 May, 2011 1 commit
  24. 31 Mar, 2011 1 commit
  25. 22 Mar, 2011 1 commit
  26. 07 Dec, 2010 1 commit
  27. 22 Oct, 2010 1 commit
    • David Goodell's avatar
      [svn-r7362] add coll/nonblocking, a sanity test for the new NBC functions · ee4b787c
      David Goodell authored
      This isn't a good test, it just helps to make sure that all 17 new
      nonblocking collective functions have sensible function prototypes,
      exist in the library, and don't explode when you call them with simple
      arguments.
      
      The test is currently disabled in the testlist since we will currently
      always fail at runtime.
      
      No reviewer.
      ee4b787c
  28. 28 Sep, 2010 1 commit
  29. 06 Aug, 2010 1 commit
    • William Gropp's avatar
      [svn-r7011] Added testing for MPI version in configure; runtest now implements... · 55624189
      William Gropp authored
      [svn-r7011] Added testing for MPI version in configure; runtest now implements an mpiversion=2.2 option for tests so that tests that require new routines are not run on older MPI implementations, and enhanced error reporting from many of the tests to help in giving more specific error messages for MPI implementations that fail the tests (these particular tests chosen because they failed on one or more versions of the IBM MPI implementation)
      55624189
  30. 28 Jul, 2010 1 commit
  31. 19 May, 2010 1 commit
  32. 24 Nov, 2009 1 commit
  33. 03 Nov, 2009 2 commits
  34. 22 Sep, 2009 1 commit
    • David Goodell's avatar
      [svn-r5362] Fix alltoall{v,w} zero count/type hangs (ticket #872). · 6ccee8e2
      David Goodell authored
      This fixes the cases in MPI_Alltoallv/MPI_Alltoallw where the send
      counts are 0 with a non-zero-sized send type and the recv counts are
      non-zero with a zero-sized recv type.  Prior to this change MPICH2 would
      hang when this situation was encountered.  This commit also includes a
      regression test for this behavior.
      
      Thanks to Michael Hofmann for reporting the bug and providing a succinct
      test case that illustrates the problem.
      
      No reviewer.
      6ccee8e2
  35. 28 Aug, 2009 1 commit
  36. 24 Aug, 2009 1 commit
    • David Goodell's avatar
      [svn-r5259] Set the is_low_group field when creating an intercomm via MPI_Comm_create. · 8e4f42c0
      David Goodell authored
      This corrects a bug that was introduced in r5249.  When the is_low_group
      field isn't set deadlocks will typically occur for "full-duplex"
      collectives over intercommunicators (such as MPI_Allreduce).
      
      This commit also runs each of the intercomm collective tests with a
      higher process count to ensure that more intercommunicator code paths
      are exercised.  In this particular case running at higher process counts
      is an effective regression test.
      
      No reviewer.
      8e4f42c0
  37. 09 Mar, 2009 1 commit