RFR: 8187033: [PPC] Imporve performance of ObjectStreamClass.getClassDataLayout()
peter.levart at gmail.com
Wed Sep 20 13:53:41 UTC 2017
On 09/20/2017 12:12 PM, Kazunori Ogata wrote:
> By the way, I'm running the benchmark on POWER8 machine. Removing
> volatile won't change the performance on x86.
I would like to compare different variants of optimization using final
fields. I won't compare it with current code that uses volatile. I think
that overhead that is caused by fences imposed on POWER8 by final fields
(does POWER8 use any memory ordering instructions on the read side for
final fields?) can be offset with better overall algorithm.
More information about the core-libs-dev