P vs P speed (was RE: Newbie question: files..)

[Cameron Laird]

In article <87puykiham.fsf at pc-hrvoje.srce.hr>,
Hrvoje Niksic  <hniksic at srce.hr> wrote:
>"Tim Peters" <tim_one at email.msn.com> writes:
			.
			.
			.
>> On my home platform (P5-166, 32Mb RAM, Win95), it takes about 20
>> seconds in Perl and about 14 in Python.  Which, applying the usual
>> benchmarking chicanery, means "Python is 43% faster than Perl".
>
>FWIW, here it takes 16.5 seconds of CPU time, while Perl takes 12.8.
>Does that make Perl 37% faster?  :-)
>
>Benchmarks truly suck.

I think benchmarks are truly wonderful.  They
fill me with wonder.

I've seen enough cases where *identical* source
produces dramatically different results on
apparently randomly chosen machines that I'm
ready to begin investigating material causes
(holding in reserve the speculation that the
boxes know the preferences of their owners).  Is
there some plausible mechanism for supposing
that Tim's tired old silicon (I can write that;
I've still got machines from last decade that I
prefer to the thought of spending any cash) is
relatively more efficient on Python processes,
presumably because its DLLs and such are in bet-
ter places?
-- 

Cameron Laird           http://starbase.neosoft.com/~claird/home.html
claird at NeoSoft.com      +1 281 996 8546 FAX