[Numpy-discussion] Profiling numpy ? (parts written in C)

[David Cournapeau]

Francesc Altet wrote:
>
>
>
> So, cProfile is only showing where the time is spent at the
> first-level calls in extension level. If we want more introspection on
> the C stack, and you are running un Linux, oprofile
> (http://oprofile.sourceforge.net) is a very nice profiler. Here are
> the outputs for the above routines on my machine.
>
> For clip1:
>
> Profiling through timer interrupt
> samples  %        image name               symbol name
> 643      54.6769  libc-2.3.6.so            memmove
> 151      12.8401  multiarray.so            PyArray_Choose
> 35        2.9762  umath.so                 BYTE_multiply
> 34        2.8912  umath.so                 DOUBLE_greater
> 32        2.7211  mtrand.so                rk_random
> 32        2.7211  umath.so                 DOUBLE_less
> 30        2.5510  libc-2.3.6.so            memcpy
>
>
> For clip2:
>
> Profiling through timer interrupt
> samples  %        image name               symbol name
> 188      24.5111  libc-2.3.6.so            memmove
> 143      18.6441  multiarray.so            _nonzero_indices
> 126      16.4276  multiarray.so            PyArray_MapIterNext
> 37        4.8240  umath.so                 DOUBLE_greater
> 36        4.6936  mtrand.so                rk_gauss
> 33        4.3025  umath.so                 DOUBLE_less
> 24        3.1291  libc-2.3.6.so            memcpy
Could you detail a bit how you did the profiling with oprofile ? I don't 
manage to get the same results than you (that is on per application 
basis when the application is a python script and not a 'binary' program)

Thank you,

David