Intel® oneAPI Math Kernel Library
Ask questions and share information with other developers who use Intel® Math Kernel Library.

mkl and real*16

frostie
Beginner
771 Views
hi,
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 ?
thanks
frostie
0 Kudos
3 Replies
jonnin
Beginner
771 Views
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
0 Kudos
Intel_C_Intel
Employee
771 Views
 
0 Kudos
Intel_C_Intel
Employee
771 Views
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. Bruce
0 Kudos
Reply