Joshua Chamas wrote:
> The Hello World 2000 benchmark is complete, and my results are below
Kind of harsh results for Template Toolkit, but it makes sense given the
nature of the test. Variable interpolation in TT provides extra
functionality to give transparent access to method calls, coderefs,
etc. The other systems are just going direct to Perl data structures.
In practice, I wouldn't do all this variable assignment stuff in the
template; I'd do it in a handler before running the template. That
wouldn't make sense for the Embperl/ASP/Mason style systems though.
By the way, it would be cool if the test ran a few times, dropped the
high and low for each system, and took an average of the remaining
times. That would smooth out some of the inaccuracies that are
unavoidable with this kind of benchmarking.
Nice work.
- Perrin
