News for hackers. Stuff that matters.
Re:Pillow-SIMD: improving the performance of image processing by wiredfool on Friday May 13, 2016 @02:50PM (#11692413)
I'm curious how scpiy and numpy manage it. I'm pretty sure that they have solved some of this before.
Re:Pillow-SIMD: improving the performance of image processing by tavert on Friday May 13, 2016 @03:39PM (#11692733)
Entirely handled by the underlying BLAS library, OpenBLAS and MKL have this feature but few if any other libraries do. I believe FFTW has something similar, but scipy doesn't use FFTW.
Re:Pillow-SIMD: improving the performance of image processing by dalke on Friday May 13, 2016 @03:14PM (#11692580)
In my short search, I didn't see evidence that either package has run-time dispatch based on the processor type.

I don't see "cpuid" used in the scipy code base, and the only intrinsic I found is specifically in a MS Windows #ifdef.

Numpy doesn't use cpuid. It does have compile-time options for intrinsics, but not run-time.