diff options
Diffstat (limited to 'doc/UsingIntelMKL.dox')
| -rw-r--r-- | doc/UsingIntelMKL.dox | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/doc/UsingIntelMKL.dox b/doc/UsingIntelMKL.dox index a1a3a18f2..fc35c3cf0 100644 --- a/doc/UsingIntelMKL.dox +++ b/doc/UsingIntelMKL.dox @@ -63,6 +63,12 @@ In addition you can choose which parts will be substituted by defining one or mu <tr><td>\c EIGEN_USE_MKL_ALL </td><td>Defines \c EIGEN_USE_BLAS, \c EIGEN_USE_LAPACKE, and \c EIGEN_USE_MKL_VML </td></tr> </table> +The \c EIGEN_USE_BLAS and \c EIGEN_USE_LAPACKE* macros can be combined with \c EIGEN_USE_MKL to explicitly tell Eigen that the underlying BLAS/Lapack implementation is Intel MKL. +The main effect is to enable MKL direct call feature (\c MKL_DIRECT_CALL). +This may help to increase performance of some MKL BLAS (?GEMM, ?GEMV, ?TRSM, ?AXPY and ?DOT) and LAPACK (LU, Cholesky and QR) routines for very small matrices. +MKL direct call can be disabled by defining \c EIGEN_MKL_NO_DIRECT_CALL. + + Note that the BLAS and LAPACKE backends can be enabled for any F77 compatible BLAS and LAPACK libraries. See this \link TopicUsingBlasLapack page \endlink for the details. Finally, the PARDISO sparse solver shipped with Intel MKL can be used through the \ref PardisoLU, \ref PardisoLLT and \ref PardisoLDLT classes of the \ref PardisoSupport_Module. |