Uploaded image for project: 'JDK'
  1. JDK
  2. JDK-8204353

AARCH64: optimize FPU load and stores in macroAssembler

    Details

    • Type: Enhancement
    • Status: Resolved
    • Priority: P3
    • Resolution: Fixed
    • Affects Version/s: 10, 11
    • Fix Version/s: 11
    • Component/s: hotspot
    • Labels:
    • Subcomponent:
    • Resolved In Build:
      b19
    • CPU:
      aarch64
    • OS:
      linux

      Backports

        Description

        push_call_clobbered_registers, pop_call_clobbered_registers, push_CPU_state, pop_CPU_state methods are using 2-fpu-registers-per-instruction approach, while it can use 4-fpu-registers-per-instruction, which will make respective code up to 2 times shorter

          Attachments

            Issue Links

              Activity

                People

                • Assignee:
                  dpochepk Dmitrij Pochepko
                  Reporter:
                  dpochepk Dmitrij Pochepko
                • Votes:
                  0 Vote for this issue
                  Watchers:
                  2 Start watching this issue

                  Dates

                  • Created:
                    Updated:
                    Resolved: