mkl and real*16

mkl and real*16

i am new in this forum and also not very familiar with the mkl library.
i would like to use the mkl library with a 128 bit precision. is it possible and does intel offer this kind ?

4 posts / 0 new
Last post
For more complete information about compiler optimizations, see our Optimization Notice.

As far as I can tell, it supports only

floats, doubles, and complex and double complex.

which is (c sizes can vary) .net c++ for real * 4 and real * 8

MKL supports the same precision as the underlying reference code. Since the BLAS and LAPACK (and ScaLAPACK) support single and double precision only, those are also the precisions we support.


Leave a Comment

Please sign in to add a comment. Not a member? Join today