php-developer-list | 2001122
Date: 12/31/01
- Next message: Sebastian Bergmann: "Re: [PHP-DEV] Re: MOPS Benchmark"
- Previous message: sterling <email protected>: "[PHP-DEV] Bug #14683 Updated: RETURNTRANSFER causes core dump"
- In reply to: Sebastian Bergmann: "[PHP-DEV] MOPS Benchmark"
- Next in thread: Sebastian Bergmann: "Re: [PHP-DEV] Re: MOPS Benchmark"
- Reply: Sebastian Bergmann: "Re: [PHP-DEV] Re: MOPS Benchmark"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Mmmm,
since this is -dev I'm just going to
#include usual extensive benchmark disclaimers
case in point, the php and perl version are not written "same way" aka same
logic and data structures. Rewriting the perl version with a while contruct
actually speeds it up (and re-inforces the fact that these are sensitive to
small things among other issues).
My results are very close to Andrew Sitnikov's.
2x1Ghz 2.4.7-10smp
Iterations: 100000000
Estimated ops: 200000000
perl 5.6.0 w/ while
Elapsed time: 53
M op/s: 3.77
perl 5.6.0 default
Elapsed time: 69
M op/s: 2.89
php 4.1.0 (and 4.0.6)
Elapsed time: 215
M op/s: 0.93
python 1.5.2
Elapsed time: 92
M op/s: 2.15
python -OO 1.5.2
Elapsed time: 81
M op/s: 2.45
Would be interesting to profile these and see where the time goes.
- August
-- PHP Development Mailing List <http://www.php.net/> To unsubscribe, e-mail: php-dev-unsubscribe <email protected> For additional commands, e-mail: php-dev-help <email protected> To contact the list administrators, e-mail: php-list-admin <email protected>
- Next message: Sebastian Bergmann: "Re: [PHP-DEV] Re: MOPS Benchmark"
- Previous message: sterling <email protected>: "[PHP-DEV] Bug #14683 Updated: RETURNTRANSFER causes core dump"
- In reply to: Sebastian Bergmann: "[PHP-DEV] MOPS Benchmark"
- Next in thread: Sebastian Bergmann: "Re: [PHP-DEV] Re: MOPS Benchmark"
- Reply: Sebastian Bergmann: "Re: [PHP-DEV] Re: MOPS Benchmark"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

