1. 19 Feb, 2015 3 commits
  2. 18 Feb, 2015 1 commit
  3. 17 Feb, 2015 3 commits
    • Kenneth Moreland's avatar
      To not reallocate to smaller buffers. · 16032a52
      Kenneth Moreland authored
      Previously, if a state buffer was needed and the existing one did not
      match the size and type exactly, the old buffer was freed and a new
      buffer was malloced. However, malloc can be slow and it is possible to
      reuse a buffer if the new one being asked for is smaller than the old
      one. Thus, change the semantics to use a previously allocated buffer if
      it is at least as big as needed. This might leave pools of data larger
      than what we need, but will reduce the overall number of malloc calls
      needed.
      16032a52
    • Kenneth Moreland's avatar
      Merge branch 'FixTypo' · 0ea1ad63
      Kenneth Moreland authored
      0ea1ad63
    • Kenneth Moreland's avatar
      Fix erroneous backslash at end of line · 1401947f
      Kenneth Moreland authored
      I'm sure this is from a mistaken keypress while navigating the file a
      while ago.
      1401947f
  4. 10 Feb, 2015 9 commits
  5. 05 Feb, 2015 6 commits
    • Kenneth Moreland's avatar
      Merge branch 'ShorterTimingLogs' · 0b9cf86f
      Kenneth Moreland authored
      0b9cf86f
    • Kenneth Moreland's avatar
      Remove reporting of no error in tests · 33d017c8
      Kenneth Moreland authored
      At the end of each test each process reported whether it got an IceT or
      OpenGL error including if it is no error. That can be helpful in part to
      know that the process successfully completed, but for tests on very
      large processes it generated excessively large log files. Instead
      suppress the report if there is no error.
      33d017c8
    • Kenneth Moreland's avatar
      Merge branch 'FixImageSplitStudy' · 57a0bbe8
      Kenneth Moreland authored
      57a0bbe8
    • Kenneth Moreland's avatar
      Make max image split study more complete in SimpleTiming. · 90eede98
      Kenneth Moreland authored
      The usage of the -max-image-split-study of SimpleTiming states that it
      tries doubling the max split. For some reason I implemented it by
      multipling by the magic k value each time. Change it so it actually just
      doubles the max image split and does a more complete search.
      90eede98
    • Kenneth Moreland's avatar
      Merge branch 'CollectTiming' · 2e1ecdbc
      Kenneth Moreland authored
      2e1ecdbc
    • Kenneth Moreland's avatar
      Collect timing in SimpleTiming before printing · 22ce5549
      Kenneth Moreland authored
      Previously, the root process would print the log at the end of
      SimpleTimingDoRender. The problem is that in the scaling studies the
      world communicator is partitioned so that there are multiple root
      processes running at once. I've been having trouble with log entries
      stomping over each other.
      
      This change holds all the timings in a buffer rather than print them.
      After scaling studies are complete, all log entries are collected to the
      world root and printed out there.
      22ce5549
  6. 03 Feb, 2015 2 commits
  7. 27 Jan, 2015 2 commits
  8. 22 Jan, 2015 5 commits
  9. 21 Jan, 2015 2 commits
  10. 20 Jan, 2015 3 commits
    • Kenneth Moreland's avatar
      Add ability to do factor-of-2-3 scaling studies. · 9e1c92fa
      Kenneth Moreland authored
      Add to SimpleTiming another scaling study that introduces lots of
      intermediate job sizes that have factors of 3. This studies around
      algorithms that might be optimized for power of 2.
      9e1c92fa
    • Kenneth Moreland's avatar
      Add ability to do factor-of-2 scaling studies. · adbc57b0
      Kenneth Moreland authored
      SimpleTiming has an option to try all processor combinations that are
      powers of 2 up to the job size. Jobs of small size are run concurrently,
      which should speed the overall job time but will probably result in some
      communication contention.
      adbc57b0
    • Kenneth Moreland's avatar
      Add ability to subset a communicator. · e611cd8e
      Kenneth Moreland authored
      For now, I'm just interested in adding the ability to do a scaling study
      in the testing harness, but it may be useful in the future to divide
      communicators and collect data.
      e611cd8e
  11. 05 Nov, 2014 2 commits
  12. 09 Oct, 2014 2 commits