STXR_PREFETCH is usually done unconditionally in non-JVM code. Does it ever hurt performance? If not, let's get rid of STXR_PREFETCH and do prefetching unconditionally.
Refs: https://github.com/openjdk/jdk/pull/8258
Refs: https://github.com/openjdk/jdk/pull/8258
- relates to
-
JDK-8157841 aarch64: prefetch ignores cache line size
- Resolved