Uploaded image for project: 'JDK'
  1. JDK
  2. JDK-8312425

[vectorapi] AArch64: Optimize vector math operations with SLEEF

XMLWordPrintable

    • Icon: Enhancement Enhancement
    • Resolution: Fixed
    • Icon: P4 P4
    • 24
    • 22, 23, 24
    • hotspot
    • b23
    • aarch64

      Currently the floating-point math APIs like "SIN/COS/TAN..." are not intrinsified on AArch64 platform. This makes these APIs have large performance gap on AArch64. Note that those APIs are intrinsified by C2 compiler on X86 platforms. They are implemented by calling the Intel's SVML library [1]. We'd like to optimize these APIs for AArch64 by intrinsifying them with a vector library called libsleef [2][3].

      [1] https://github.com/openjdk/jdk/pull/3638
      [2] https://sleef.org/
      [3] https://packages.debian.org/bookworm/libsleef-dev

            mli Hamlin Li
            xgong Xiaohong Gong
            Votes:
            0 Vote for this issue
            Watchers:
            5 Start watching this issue

              Created:
              Updated:
              Resolved: