This PR proposes to fix a performance regression (on x64 platforms) for quad-string words introduced by [JDK-8345120](https://bugs.openjdk.org/browse/JDK-8345120).
The PR also fixes a performance regression in the benchmarks caused by using the wrong type for `MemorySegment`. Regrettably, this PR uses different code paths for various architectures. This gives optimum performance for all platforms at the expense of slightly more code complexity. ------------- Commit messages: - Fix regression on x64 - Go back to use MemorySegment types - Merge branch 'master' into strlen-bench-update - Use aliases for legacy code. Changes: https://git.openjdk.org/jdk/pull/22539/files Webrev: https://webrevs.openjdk.org/?repo=jdk&pr=22539&range=00 Issue: https://bugs.openjdk.org/browse/JDK-8345465 Stats: 25 lines in 2 files changed: 5 ins; 2 del; 18 mod Patch: https://git.openjdk.org/jdk/pull/22539.diff Fetch: git fetch https://git.openjdk.org/jdk.git pull/22539/head:pull/22539 PR: https://git.openjdk.org/jdk/pull/22539
