On Fri, 1 Dec 2023 08:48:52 GMT, Xiaohong Gong <xg...@openjdk.org> wrote:
>> Currently the vector floating-point math APIs like >> `VectorOperators.SIN/COS/TAN...` are not intrinsified on AArch64 platform, >> which causes large performance gap on AArch64. Note that those APIs are >> optimized by C2 compiler on X86 platforms by calling Intel's SVML code [1]. >> To close the gap, we would like to optimize these APIs for AArch64 by >> calling a third-party vector library called libsleef [2], which are >> available in mainstream Linux distros (e.g. [3] [4]). >> >> SLEEF supports multiple accuracies. To match Vector API's requirement and >> implement the math ops on AArch64, we 1) call 1.0 ULP accuracy with FMA >> instructions used stubs in libsleef for most of the operations by default, >> and 2) add the vector calling convention to apply with the runtime calls to >> stub code in libsleef. Note that for those APIs that libsleef does not >> support 1.0 ULP, we choose 0.5 ULP instead. >> >> To help loading the expected libsleef library, this patch also adds an >> experimental JVM option (i.e. `-XX:UseSleefLib`) for AArch64 platforms. >> People can use it to denote the libsleef path/name explicitly. By default, >> it points to the system installed library. If the library does not exist or >> the dynamic loading of it in runtime fails, the math vector ops will >> fall-back to use the default scalar version without error. But a warning is >> printed out if people specifies a nonexistent library explicitly. >> >> Note that this is a part of the original proposed patch in panama-dev [5], >> just with some initial review comments addressed. And now we'd like to get >> some wider feedbacks from more hotspot experts. >> >> [1] https://github.com/openjdk/jdk/pull/3638 >> [2] https://sleef.org/ >> [3] https://packages.fedoraproject.org/pkgs/sleef/sleef/ >> [4] https://packages.debian.org/bookworm/libsleef3 >> [5] https://mail.openjdk.org/pipermail/panama-dev/2022-December/018172.html > > Xiaohong Gong has updated the pull request with a new target base due to a > merge or a rebase. The incremental webrev excludes the unrelated changes > brought in by the merge/rebase. The pull request contains ten additional > commits since the last revision: > > - Separate neon and sve functions into two source files > - Merge branch 'jdk:master' into JDK-8312425 > - Rename vmath to sleef in configure > - Address review comments in build system > - Add a bundled native lib in jdk as a bridge to libsleef > - Merge 'jdk:master' into JDK-8312425 > - Disable sleef by default > - Merge 'jdk:master' into JDK-8312425 > - 8312425: [vectorapi] AArch64: Optimize vector math operations with SLEEF The final thing we need to resolve properly is the SVE compiler test. @theRealAph says: > arm_sve.h is part of GCC. It was added to GCC in 2019. A more relevant question is what version of gcc it was added, and if that also implies that the compiler knows about `-march=armv8-a+sve`. If so, then this test could basically be framed as a gcc version check. I'm still leaning towards failing configure if the SVE code cannot be compiled. Under what circumstances can this test possibly fail, so SVE_CFLAGS would not be set? ------------- PR Comment: https://git.openjdk.org/jdk/pull/16234#issuecomment-1836444674