[Numpy-discussion] Fast threading solution thoughts

Brian Granger ellisonbg.net@gmail....
Thu Feb 12 13:43:31 CST 2009


> Recent Matlab versions use Intels Math Kernel Library, which performs
> automatic multi-threading - also for mathematical functions like sin
> etc, but not for  addition, multiplication etc. It seems to me Matlab
> itself does not take care of multi-threading. On
> http://www.intel.com/software/products/mkl/data/vml/functions/_listfunc.html
> you can have a look at the performance data of the MKL vectorized math
> functions. Around a vector length between 100-1000, depending on which
> function, precision, cpu architecture, they switch to multi-threading.

Fantastic, thanks for this pointer!

Brian


More information about the Numpy-discussion mailing list