On Feb 16, 2011, at 10:55 AM, Christian Thalinger wrote: > On Feb 15, 2011, at 7:03 PM, Charles Oliver Nutter wrote: >> * Performance >> >> Because JRuby does a pretty good job optimizing, indy only recently >> started to be faster than our normal call protocol logic. I expect to >> see it get better and better as more of the method handle chain >> inlines and optimizes with the rest of the calling method. Seeing a >> recent indy build run 30% faster than our normal protocol was a great >> feeling. > > I'm still a little skeptical about that. What benchmarks did you run?
Btw. when I try indy JRuby I get: $ bin/jruby.sh -J-Djruby.compile.invokedynamic=true -J-XX:+UnlockExperimentalVMOptions -J-XX:+EnableMethodHandles -J-XX:+EnableInvokeDynamic test/test_array.rb VM option '+UnlockExperimentalVMOptions' VM option '+EnableMethodHandles' VM option '+EnableInvokeDynamic' LoadError: load error: builtin/java/org.jruby.ast -- java.lang.RuntimeException: java.lang.IllegalArgumentException: bad reorder array require at org/jruby/RubyKernel.java:1038 (root) at /home/ct232829/mlvm/jruby/lib/ruby/site_ruby/shared/builtin/javasupport.rb:45 process_args at /home/ct232829/mlvm/jruby/lib/ruby/site_ruby/shared/builtin/javasupport.rb:90 run at /home/ct232829/mlvm/jruby/lib/ruby/1.8/test/unit/autorunner.rb:11 (root) at /home/ct232829/mlvm/jruby/lib/ruby/1.8/test/unit.rb:279 call at org/jruby/RubyProc.java:268 call at org/jruby/RubyProc.java:232 _______________________________________________ mlvm-dev mailing list mlvm-dev@openjdk.java.net http://mail.openjdk.java.net/mailman/listinfo/mlvm-dev