Uploaded image for project: 'IMPALA'
  1. IMPALA
  2. IMPALA-6357

Use faster carries in decimal arithmetic

Attach filesAttach ScreenshotAdd voteVotersWatch issueWatchersCreate sub-taskLinkCloneUpdate Comment AuthorReplace String in CommentUpdate Comment VisibilityDelete Comments
    XMLWordPrintableJSON

    Details

    • Type: Improvement
    • Status: Open
    • Priority: Major
    • Resolution: Unresolved
    • Affects Version/s: None
    • Fix Version/s: None
    • Component/s: Perf Investigation
    • Labels:
    • Epic Color:
      ghx-label-9

      Description

      Recent x86-64 machines often include instructions for faster additions and multiplications with different carry flag behavior, which can increase performance of 128-bit and 256-bit arithmetic. See

      https://www.intel.com/content/dam/www/public/us/en/documents/white-papers/ia-large-integer-arithmetic-paper.pdf

      Impala could take advantage of this via Intel intrinsics (https://software.intel.com/sites/landingpage/IntrinsicsGuide/#othertechs=ADX,BMI2) or perhaps via codegen

        Attachments

        Issue Links

          Activity

            People

            • Assignee:
              Unassigned
              Reporter:
              jbapple Jim Apple

              Dates

              • Created:
                Updated:

                Issue deployment