Christian Catchpole wrote:
These performance tests are dodgy at the best of times, simply because
the way you approach problems are different in different languages.
Let me be a bit harsh: 90% of the (micro)benchmarks that are published
around are written by people who doesn't have the skill to write them.
Not to say worse:
"it took the C code about 1/1000th of a millisecond to perform about
10,000,000 arithmetic operations!"
If I read correctly that would mean 10^7*10^3 = 10^10 arithmetic
operations per millisecond, that is 10^13 operations per second. 10.000
GFLops! Whoa!
There's a comment about that, but it seems the commenter missed that is
1/1000th of a millisecond, not of a second, so got to the less absurd 10
GFlops figure.
Not to count that, as usual, he didn't "warm up" the JIT and he can't
reliably measure such short times as 1 microsecond to get some
statistics, he should rather run with a higher count and get longer times.
--
Fabrizio Giudici - Java Architect, Project Manager
Tidalwave s.a.s. - "We make Java work. Everywhere."
weblogs.java.net/blog/fabriziogiudici - www.tidalwave.it/people
[email protected]
--
You received this message because you are subscribed to the Google Groups "The
Java Posse" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to
[email protected].
For more options, visit this group at
http://groups.google.com/group/javaposse?hl=en.
