PeterPtroc commented on PR #8371: URL: https://github.com/apache/hadoop/pull/8371#issuecomment-4163618339
> Modern JDKs should be able to leverage hardware capabilities to speed up CRC32/CRC32C calculations. Have you compared this implementation with the JDK built-in one? If JDK does this well, seems we don't need to duplicate this on the Hadoop side. Great point. I agree that leveraging JDK intrinsics is the way to go if the performance is on par or better. I'm running some benchmarks to compare our implementation against the built-in CRC32/CRC32C on modern JDKs across different environments. I'll update the thread with the results once I have them. -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
