1 Apr
2015
1 Apr
'15
4:12 p.m.
"Klemm, Michael" michael.klemm@intel.com wrote:
I have found that the numpy.linalg.svd algorithm creates the resulting U, sigma, and V matrixes with Fortran storage. Is there any way to force these kind of algorithms to not change the storage order? That would make passing the matrixes to the native dgemm operation much easier.
NumPy's dot function will call cblas_dgemm in the most efficient way regardless of storage. It knows what to do with C and Fortran arrays.
Sturla