A while ago I committed an optimization to HashMap [1] that showed good
improvements to SPEC benchmarks on the IBM VME, but it turned out caused
problems to the OPT JIT [2], so we rolled it back.
The JIT has been improved so I'm going to go ahead an re-apply the
optimizations for Integer keys. It would be good to hear that people
see the same improvements now on DRLVM benchmarks too.
[1] http://svn.apache.org/viewvc?rev=575658&view=rev
[2] http://issues.apache.org/jira/browse/HARMONY-5014
Regards,
Tim
