Code review request for 6908131 Pure Java implementations of StrictMath.floor(double) &StrictMath.ceil(double)

[Martin Buchholz]

I think it's reasonable to have small microbenchmarks of
JDK functionality in the openjdk code base.
I've done that occasionally myself in the jdk/test directory.

More serious implementation-independent benchmarking efforts
should probably have their own project, as with e.g. DaCapo.
Maybe there's already a Java community benchmarking project
that would be interested in math-related things?

Martin

On Sun, Jan 24, 2010 at 22:04, Dmitry Nadezhin <Dmitry.Nadezhin at sun.com> wrote:
> Joe,
>
> I'm interested in micro-benchmarking of math in OpenJDK .
> This includes a choice of proper framework, a choice of representative
> patterns (or testsuites).
>
> Will math micro-benchmarking be ever hosted by OpenJDK ?
> Or I should develop them elsewhere ?