Uploaded image for project: 'Hive'
  1. Hive
  2. HIVE-7406 Vectorize Reduce-Side
  3. HIVE-7405

Vectorize GROUP BY on the Reduce-Side (Part 1 – Basic)

    XMLWordPrintableJSON

Details

    • Sub-task
    • Status: Closed
    • Major
    • Resolution: Fixed
    • None
    • 0.14.0
    • Vectorization
    • None

    Description

      Vectorize the basic case that does not have any count distinct aggregation.

      Add a 4th processing mode in VectorGroupByOperator for reduce where each input VectorizedRowBatch has only values for one key at a time. Thus, the values in the batch can be aggregated quickly.

      Attachments

        1. HIVE-7405.1.patch
          1.58 MB
          Matt McCline
        2. HIVE-7405.2.patch
          1.62 MB
          Matt McCline
        3. HIVE-7405.3.patch
          1.62 MB
          Matt McCline
        4. HIVE-7405.4.patch
          1.64 MB
          Matt McCline
        5. HIVE-7405.5.patch
          1.64 MB
          Matt McCline
        6. HIVE-7405.6.patch
          84 kB
          Matt McCline
        7. HIVE-7405.7.patch
          61 kB
          Matt McCline
        8. HIVE-7405.8.patch
          88 kB
          Matt McCline
        9. HIVE-7405.9.patch
          593 kB
          Matt McCline
        10. HIVE-7405.91.patch
          67 kB
          Matt McCline
        11. HIVE-7405.92.patch
          108 kB
          Matt McCline
        12. HIVE-7405.93.patch
          106 kB
          Matt McCline
        13. HIVE-7405.94.patch
          107 kB
          Matt McCline
        14. HIVE-7405.95.patch
          107 kB
          Matt McCline
        15. HIVE-7405.96.patch
          107 kB
          Matt McCline
        16. HIVE-7405.97.patch
          124 kB
          Matt McCline
        17. HIVE-7405.98.patch
          85 kB
          Matt McCline
        18. HIVE-7405.99.patch
          88 kB
          Matt McCline
        19. HIVE-7405.991.patch
          88 kB
          Matt McCline
        20. HIVE-7405.994.patch
          87 kB
          Matt McCline
        21. HIVE-7405.995.patch
          101 kB
          Matt McCline
        22. HIVE-7405.996.patch
          100 kB
          Matt McCline

        Issue Links

          is related to

          Sub-task - The sub-task of the issue HIVE-7537 Output vectorized GROUP BY with only primitive aggregate fields as columns so downstream operators will be vectorized

          • Major - Major loss of function.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. HIVE-5701 vectorized groupby should work with vectorized reduce sink

          • Major - Major loss of function.
          • Resolved
          links to

          Web Link RB #24291

          Activity

            People

              mmccline Matt McCline
              mmccline Matt McCline
              Votes:
              0 Vote for this issue
              Watchers:
              6 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: