RFR: 8317763: Follow-up to AVX512 intrinsics for Arrays.sort() PR [v3]

Vladimir Kozlov kvn at openjdk.org
Wed Oct 11 19:38:28 UTC 2023


On Wed, 11 Oct 2023 19:06:24 GMT, Vladimir Kozlov <kvn at openjdk.org> wrote:

>> @vnkozlov Please advice if we can integrate this PR or if you would like to run some tests first.
>
> Okay. I will start testing for current changes. @sviswa7 please file RFE for Zen 4. If we get patch for it we do followup changes in that RFE.

> @vnkozlov
> Are there any options to be sure that C2 JIT compiler is used during tests?

May be you already figure out that. Use `-XX:+PrintCompilation -XX:+UnlockDiagnosticVMOptions -XX:+PrintInlining -XX:-TieredCompilation` flags (Tiered is off to use only C2) and look for something like next

     82   20             java.util.Random::next (47 bytes)
                            @ 3   java.util.Random::next (47 bytes)   inline (hot)
                              @ 8   java.util.concurrent.atomic.AtomicLong::get (5 bytes)   accessor
                              @ 32   java.util.concurrent.atomic.AtomicLong::compareAndSet (13 bytes)   inline (hot)
                                @ 9   jdk.internal.misc.Unsafe::compareAndSetLong (0 bytes)   (intrinsic)

-------------

PR Comment: https://git.openjdk.org/jdk/pull/16124#issuecomment-1758406966


More information about the hotspot-compiler-dev mailing list