oertl commented on PR #20359: URL: https://github.com/apache/kafka/pull/20359#issuecomment-3489667902
@ijuma > Is it worth doing a separate PR that brings back these optimizations? What's the performance difference of adding them back? The biggest performance gain comes from the main loop. The code could potentially be further optimized for small inputs. However, these (potential) additional performance gains are not so clear and might require some benchmarking on different platforms to get confident results. > Also, please specify the Java version used for your benchmark runs. The version of Java was OpenJDK 24. However, I no longer have all the details about it. The benchmark was part of this PR, though, so you can easily run it again. > There has been work at the JVM level to automatically perform optimizations like this one (an example is https://github.com/openjdk/jdk/pull/24023). Interesting, but it does not seem to have been merged yet. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
