1. 27 Aug, 2013 5 commits
  2. 26 Aug, 2013 2 commits
  3. 23 Aug, 2013 2 commits
  4. 21 Aug, 2013 1 commit
    • Rob Latham's avatar
      Improve aggregation selection on Blue Gene · a51b0f04
      Rob Latham authored
      
      
      The default "aggregators per peset" value of 8 had not been changed
      since Blue Gene /L.  Further, allow one to set the environment variable
      BGMPIO_NAGG_PSET to have the same effect as setting the "bg_nodes_pset"
      hint.  Since this is all very confusing on /Q, toss in a few more (but
      no doubt not enough) comments.
      
      Reviewed-by: default avatarBob Cernohous <bobc@us.ibm.com>
      a51b0f04
  5. 20 Aug, 2013 1 commit
  6. 19 Aug, 2013 1 commit
  7. 18 Aug, 2013 2 commits
  8. 16 Aug, 2013 1 commit
  9. 15 Aug, 2013 1 commit
  10. 14 Aug, 2013 2 commits
  11. 13 Aug, 2013 2 commits
  12. 12 Aug, 2013 1 commit
    • Rob Latham's avatar
      use AS_VAR_ARITH · ec8ca992
      Rob Latham authored
      freebsd did not like this expr syntax for some reason. Since we require
      autoconf-2.67 or newer, let's use AS_VAR_ARITH and make portable shell scripts
      autoconf's problem
      ec8ca992
  13. 11 Aug, 2013 3 commits
  14. 08 Aug, 2013 6 commits
  15. 07 Aug, 2013 7 commits
  16. 06 Aug, 2013 3 commits
    • Pavan Balaji's avatar
      Make sure MPID_REQUEST_PREALLOC is always defined. · a3571f52
      Pavan Balaji authored
      
      
      Allows the minimal configure ../configure --host=powerpc64-bgq-linux
      --with-device=pamid --enable-thread-cs=per-object.  Without this
      change the MPID_REQUEST_PREALLOC symbol would be undefined.
      
      Signed-off-by: default avatarMichael Blocksome <blocksom@us.ibm.com>
      a3571f52
    • Michael Blocksome's avatar
      Clean up pamid MPID_Abort() logic · 254aa2cd
      Michael Blocksome authored and Pavan Balaji's avatar Pavan Balaji committed
      
      
      Removed the processing of the (undocumented) environment variable
      'PAMID_CORE_ON_ABORT' which was being checked to determine if the user
      does *not* want the process to core dump. On Blue Gene/Q the core dump
      was accomplished by calling 'abort()' which sends SIGSBRT to all
      processes and all processes would then write a core file. This is not
      scalable.
      
      Instead, MPID_Abort() will invoke 'exit(1)' which will terminate all
      processes in the job. This behavior is identical for both the POE and
      the Blue Gene/Q control systems.
      
      On Blue Gene/Q the user may replicate the previous core dump behavior by
      using the environment variables 'BG_COREDUMPONERROR=1' or
      'BG_COREDUMPONEXIT=1'.
      
      Finally, the 'DYNAMIC_TASKING' #ifdef is moved up so it is checked first.
      'MPIDI_NO_ASSERT' and 'DYNAMIC_TASKING' are typically defined for PE. It
      appears that the dynamic tasking code was never being invoked.
      
      (ibm) CPS 99YURA
      
      Signed-off-by: default avatarBob Cernohous <bobc@us.ibm.com>
      254aa2cd
    • Wesley Bland's avatar
      Remove the ft tests from the default test suite. · 4824c762
      Wesley Bland authored and Pavan Balaji's avatar Pavan Balaji committed
      
      
      These tests should not be distributed with the test suite when grabbing a
      release. They are still enabled for developer builds.
      
      Signed-off-by: Pavan Balaji's avatarPavan Balaji <balaji@mcs.anl.gov>
      4824c762