RFR: 8309583: AArch64: Optimize firstTrue() when amount of elements < 8

Andrew Haley aph at openjdk.org
Mon Jun 19 09:55:08 UTC 2023


On Mon, 19 Jun 2023 07:53:23 GMT, Chang Peng <duke at openjdk.org> wrote:

> Sorry for the delay. Original performance was measured by a simple benchmark only measuring firstTrue()'s performance written by myself. When I wanted to add it to JDK I found an existing benchmark used to measure different mask operations' performance ([jdk/test/micro/org/openjdk/bench/jdk/incubator/vector/MaskQueryOperationsBenchmark.java at master · openjdk/jdk · GitHub](https://github.com/openjdk/jdk/blob/master/test/micro/org/openjdk/bench/jdk/incubator/vector/MaskQueryOperationsBenchmark.java)). I tried to measure firstTrue()'s performance by this benchmark, but I found Blackhole‘s proportion of hottest region is too high, like following:

Can you please send the entire output of JMH? Blackhole should not appear at all in the output because it's been intrinsified. I'd like to know why the intrinsic isn't working for you.

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

PR Comment: https://git.openjdk.org/jdk/pull/14373#issuecomment-1596871646


More information about the hotspot-compiler-dev mailing list