On Jan 13, 10:07 am, cliffc <cli...@acm.org> wrote:
-snip-
> 5- The debianshootoutresults generally badly mis-represent Java.
> Most of them have runtimes that are too small (<10sec) to show off the
> JIT, and generally don't use any of the features which commonly appear
> in large Java programs (heavy use of virtuals, deep class hierarchies,
> etc) for which the JIT does a lot of optimization.  I give a public
> talk on the dangers of microbenchmarks and all the harnesses I've
> looked at in theshootoutfail basic sanity checks.  Example: the
> fannkuch benchmark runs 5 secs in Java, somewhat faster in C++.  Why
> does anybody care about a program which runs 5sec?


I guess they wonder if "somewhat faster" might become 25 minutes as
the workload increases ;-)

         usr+sys :: elapsed
N=10
Java   0.756s :: 0.643s
C++   0.332s :: 0.099s

N=11
Java   5.944s :: 1.859s
C++   3.540s :: 1.063s

N=12
Java   74.689s :: 20.460s
C++   51.895s :: 14.167s

N=13
Java   1083.592s :: 271.876s
C++    796.506s :: 199.856s

N=14
Java   18015.666s :: 5296.275s
C++   12392.987s :: 3791.224s
--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups 
"Clojure" group.
To post to this group, send email to clojure@googlegroups.com
To unsubscribe from this group, send email to 
clojure+unsubscr...@googlegroups.com
For more options, visit this group at 
http://groups.google.com/group/clojure?hl=en
-~----------~----~----~----~------~----~------~--~---

Reply via email to