Uploaded image for project: 'Lucene - Core'
  1. Lucene - Core
  2. LUCENE-9636

Exact and operation to get a SIMD optimize

    XMLWordPrintableJSON

    Details

    • Type: Improvement
    • Status: Closed
    • Priority: Trivial
    • Resolution: Fixed
    • Affects Version/s: None
    • Fix Version/s: main (9.0), 8.8
    • Component/s: core/codecs
    • Labels:
      None
    • Lucene Fields:
      New

      Description

      In decode6(), decode7(), decode14(), decode15(), decode24() longs always `&` a same mask and do some shift. By printing assemble language, i find that JIT did not optimize them with SIMD instructions. But when we extract all `&` operations and do them first, JIT will use SIMD optimize on them.

       

       

        Attachments

          Issue Links

            Activity

              People

              • Assignee:
                Unassigned
                Reporter:
                gf2121 Feng Guo
              • Votes:
                0 Vote for this issue
                Watchers:
                5 Start watching this issue

                Dates

                • Created:
                  Updated:
                  Resolved:

                  Time Tracking

                  Estimated:
                  Original Estimate - Not Specified
                  Not Specified
                  Remaining:
                  Remaining Estimate - 0h
                  0h
                  Logged:
                  Time Spent - 40m
                  40m