Hongli's merge sort benchmark runs 2x faster in JRuby/Ruby 1.9


#1

I wrapped Hongli’s simple merge sort benchmark described here:

http://izumi.plan99.net/blog/index.php/2008/01/17/ruby-vs-php-performance

in Ruby’s Benchmark library and did a more detailed comparison of
1.8.6, 1.9 trunk, and JRuby running on Java 1.5, 1.6, and 1.7.

http://blog.concord.org/archives/24-Comparison-of-Ruby-1.8.6-1.9-and-JRuby-running-on-Java-1.5-1.6-and-1.7.html

The fastest “safe” result shows that JRuby running on Java 1.6 on
MacOS X* is a little more than twice as fast as Ruby 1.9.

I also have measurements using the “-fast” option with JRuby that
show a performance almost 2.5 times that of Ruby 1.9 – but the use
of this option is still experimental.

  • Apple’s Java 1.6 is 64-bit and always runs in server mode

To unsubscribe from this list, please visit:

http://xircles.codehaus.org/manage_email

#2

Stephen B. wrote:

The fastest “safe” result shows that JRuby running on Java 1.6 on MacOS
X* is a little more than twice as fast as Ruby 1.9.

I also have measurements using the “-fast” option with JRuby that show a
performance almost 2.5 times that of Ruby 1.9 – but the use of this
option is still experimental.

  • Apple’s Java 1.6 is 64-bit and always runs in server mode

Very nice results, Stephen, thank you. I think we’ll want to get more of
these kinds of posts out as we approach 1.2 release.


To unsubscribe from this list, please visit:

http://xircles.codehaus.org/manage_email

#3

Stephen B. wrote:

I wrapped Hongli’s simple merge sort benchmark described here:

http://izumi.plan99.net/blog/index.php/2008/01/17/ruby-vs-php-performance

in Ruby’s Benchmark library and did a more detailed comparison of
1.8.6, 1.9 trunk, and JRuby running on Java 1.5, 1.6, and 1.7.

Cool. I added that test to the ruby benchmark suite, for fun.
http://github.com/acangiano/ruby-benchmark-suite/tree/master
Enjoy.
-=r