RFR: 8376164: Optimize AES/ECB/PKCS5Padding implementation using full-message intrinsic stub and parallel RoundKey addition [v5]

[Marc Chevalier]

On Thu, 26 Feb 2026 12:44:48 GMT, xinyangwu <duke at openjdk.org> wrote:

> Were there any additional JVM flags or test parameters used in your run?

Only `-XX:UseAVX=3 -XX:+UnlockDiagnosticVMOptions -XX:+UseKNLSetting`

> Did you run only TestAESMain.java, or was this part of a larger test suite execution?

It was run as part of `test/hotspot/jtreg/:hotspot_vector_2`, but the failing test seems to be

 * @run main/othervm/timeout=600 -Xbatch -DcheckOutput=true -Dmode=ECB
 *      -XX:+UnlockDiagnosticVMOptions -XX:+WhiteBoxAPI -Xbootclasspath/a:.
 *      compiler.codegen.aes.TestAESMain

so, because of `main/othervm`, it gets a fresh VM, right?

Another thing is that it was run on a Windows Server 2022, in case the OS can play a role. Run in fastdebug mode. I don't see much more relevant info, sorry.

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

PR Comment: https://git.openjdk.org/jdk/pull/29385#issuecomment-3966998768