RFR: 8334396: RISC-V: verify perf of ReverseBytesI/L

[Hamlin Li]

On Tue, 18 Jun 2024 06:50:04 GMT, Fei Yang <fyang at openjdk.org> wrote:

> Good catch! Did you check the friends ReverseBytesS/ReverseBytesUS? It's very likely that they bear a similar peformance issue.

I think so too, but not yet check ReverseBytesS/ReverseBytesUS, I don't find the existing micro test for them, so I plan to put them in other pr's. And I created an umbrella bug at: https://bugs.openjdk.org/browse/JDK-8334395, am planning to go through (verify and fix) the intrinsics which might lead to potential performance regression gradually.

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

PR Comment: https://git.openjdk.org/jdk/pull/19750#issuecomment-2176113673