[Numpy-discussion] numpy blas running slow: how to check that it is properly linked

David Cournapeau cournape@gmail....
Tue Sep 20 14:48:47 CDT 2011


On Tue, Sep 20, 2011 at 1:18 PM, David Cournapeau <cournape@gmail.com> wrote:
> On Tue, Sep 20, 2011 at 9:56 AM, David Cottrell
> <david.cottrell@gmail.com> wrote:
>> Thanks, just getting back to this. I just checked again, and after
>> setting my LD_LIBRARY_PATH properly, ldd shows _dotblas.so pointing
>> and the sunmath and sunperf libraries. However the test_03.py still
>> runs at about 8-9 seconds ... far too slow.
>>
>> ~/local/lib/python3.1/site-packages/numpy/core $ ldd _dotblas.so | sed
>> -e 's/$me/$USERNAME/g'
>>        libsunperf.so.8 =>
>> /home/$USERNAME/local/archive/SolarisStudio12.2-solaris-sparc-tar-ML/solstudio12.2/lib//libsunperf.so.8
>>        libsunmath.so.1 =>
>> /home/$USERNAME/local/archive/SolarisStudio12.2-solaris-sparc-tar-ML/solstudio12.2/lib//libsunmath.so.1
>>        libgcc_s.so.1 =>         /usr/sfw/lib/libgcc_s.so.1
>>        libfsu.so.1 =>
>> /home/$USERNAME/local/archive/SolarisStudio12.2-solaris-sparc-tar-ML/solstudio12.2/lib//libfsu.so.1
>>        libfui.so.2 =>
>> /home/$USERNAME/local/archive/SolarisStudio12.2-solaris-sparc-tar-ML/solstudio12.2/lib//libfui.so.2
>>        libpicl.so.1 =>  /usr/lib/libpicl.so.1
>>        libmtsk.so.1 =>  /lib/libmtsk.so.1
>>        libm.so.2 =>     /lib/libm.so.2
>>        libc.so.1 =>     /lib/libc.so.1
>>        libm.so.1 =>     /lib/libm.so.1
>>        libdl.so.1 =>    /lib/libdl.so.1
>>        libdoor.so.1 =>  /lib/libdoor.so.1
>>        libthread.so.1 =>        /lib/libthread.so.1
>>        libkstat.so.1 =>         /lib/libkstat.so.1
>>        libpthread.so.1 =>       /lib/libpthread.so.1
>>        librt.so.1 =>    /lib/librt.so.1
>>        libaio.so.1 =>   /lib/libaio.so.1
>>        libmd.so.1 =>    /lib/libmd.so.1
>>        /platform/SUNW,Sun-Fire-V490/lib/libc_psr.so.1
>>        /platform/SUNW,Sun-Fire-V490/lib/libmd_psr.so.1

If this refers to the model of your solaris machine (SunFire V490,
meaning UltraSparc IV), then the numbers are actually not hard to
believe. Those are almost a decade-old CPU (from 2003-2004), and SPARC
are not speed deamons in the first place. Having them 10 times slower
than a recent core i7 (which are very performant for floating points)
seems "reasonable".

cheers,

David


More information about the NumPy-Discussion mailing list