[Numpy-discussion] Linking Numpy with parallel OpenBLAS
davidmenhur at gmail.com
Thu Oct 29 16:50:34 EDT 2015
On 29 October 2015 at 20:25, Julian Taylor <jtaylor.debian at googlemail.com>
> should be possible by putting this into: ~/.numpy-site.cfg
> libraries = openblasp
> LD_PRELOAD the file should also work.
I did some timings on a dot product of a square matrix of size 10000 with
LD_PRELOADing the different versions. I checked that all the cores were
crunching when an other than plain libopenblas/64 was selected. Here are
the timings in seconds:
Both computers have the same software and OS. So, it seems that openblas
doesn't get a significant advantage from going parallel in the older i5;
the i7 using all its cores (4 + 4 hyperthread) gains a 3x speed up, and
there is no big different between OpenMP and pthreads.
I am particullary puzzled by the i5 results, shouldn't threads get a
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the NumPy-Discussion