On Mon, 5 Sep 2022 13:41:31 GMT, Martin Doerr <mdo...@openjdk.org> wrote:
>> Please consider, only implemented on x64/aarch64 linux/windows. >> >> On my box calling clock_gettime via JNI goes from 35ns to 28ns when enabled. >> >> Passes t1-7 with option forced on, also passes t1-4 as is in this PR. > > Nice to see usage of this OS feature. I like it more than the serialization > page we have in 11u (with `-XX:-UseMembar`) and Critical JNI Natives (which > still have some advantage). I have observed the same speedup for a trivial > JNI call on my x86_64 machine. Thanks for having a look Martin(@TheRealMDoerr), I'll see what I can do regarding the define! ------------- PR: https://git.openjdk.org/jdk/pull/10123
