RFR: 8135157: DMB elimination in AArch64 C2 synchronization implementation

Andrew Haley aph at redhat.com
Mon Sep 7 16:17:53 UTC 2015


Most of this patch is by Wei Tang of Linaro, and the explanation is in
the bug report.  I have been over it fairly thoroughly because this is
a very delicate and critical part of the compiler, and I think that
Wei Tang's reasoning is correct.

I took the opportunity to cut out some dead wood because otherwise we
would have had four almost-identical versions of cmpxchg.

OK?

Andrew.


More information about the hotspot-compiler-dev mailing list