Using the
/Qmkl Compiler Option
/Q
mkl Compiler Option The Intel®
compiler option:
Parallel Studio XE Composer Edition
compiler supports the following variants of the
/Q
mkl- /Qmkl
- to link with a certainthreading layer depending on the threading option provided:Intel® oneAPI Math Kernel Library
- For-qopenmpthe OpenMP threading layer for Intel compilers
- For-tbbthe Intel® Threading Building Blocks (Intel® TBB) threading layer
- /Qmkl:parallel
- to link with a certainthreading layer depending on the threading option provided:Intel® oneAPI Math Kernel Library
- For-qopenmpthe OpenMP threading layer for Intel compilers
- For-tbbthe Intel® Threading Building Blocks (Intel® TBB) threading layer
- /Qmkl:sequential
- to link with sequential version of.Intel® oneAPI Math Kernel Library
- /Qmkl:cluster
- to link withcluster components (sequential) that use Intel MPI.Intel® oneAPI Math Kernel Library
The
threading layer for linking.
-qopenmp
option has higher priority than
-tbb
in choosing the
Intel® oneAPI Math Kernel Library
For more information on the
compiler option, see the Intel Compiler User and Reference Guides.
/Q
mklFor each variant of the
/Qmkl
option, the compiler links your application using the following conventions:
- cdecl for the IA-32 architecture
- LP64 for the Intel® 64 architecture
If you specify any variant of the
compiler option, the compiler automatically includes the
libraries. In cases not covered by the option, use the Link-line Advisor or see
Linking in Detail.
/Q
mklIntel® oneAPI Math Kernel Library