P4
Starting with SS12.2, our compilers will support compiler intrinsics for barriers
implemented now in OrderAccess. In some cases, we may be able to simplify our
implementations, make them more portable and perhaps more performant by simply using
the compiler-provided intrinsics
implemented now in OrderAccess. In some cases, we may be able to simplify our
implementations, make them more portable and perhaps more performant by simply using
the compiler-provided intrinsics
- relates to
-
JDK-6973570 OrderAccess::storestore() scales poorly on multi-socket x64 and sparc: cache-line ping-ponging
-
- Closed
-
-
-
- Resolved
-