Uploaded image for project: 'SystemDS'
  1. SystemDS
  2. SYSTEMDS-446 Phase 1: Exploit GPU BLAS libraries (integration)
  3. SYSTEMDS-935

Improve the performance of sparse TSMM either by using/implement sparse dsyrk

    XMLWordPrintableJSON

Details

    • Sub-task
    • Status: Open
    • Major
    • Resolution: Unresolved
    • None
    • None
    • None
    • None

    Description

      Either by adding custom kernel or using cuSparse API.

      See org.apache.sysml.runtime.matrix.data.LibMatrixCUDA's matmultTSMM() method. Please move this to Phase 2 if custom kernel is required

      nakul02

      Attachments

        Activity

          People

            nakul02 Nakul Jindal
            niketanpansare Niketan Pansare
            Votes:
            0 Vote for this issue
            Watchers:
            1 Start watching this issue

            Dates

              Created:
              Updated: