From f86bb89d39e6611806c3b31719509e661120f3a1 Mon Sep 17 00:00:00 2001 From: Gael Guennebaud Date: Thu, 9 Nov 2017 11:07:45 +0100 Subject: Add EIGEN_MKL_NO_DIRECT_CALL option --- doc/UsingIntelMKL.dox | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'doc/UsingIntelMKL.dox') diff --git a/doc/UsingIntelMKL.dox b/doc/UsingIntelMKL.dox index 6de14afad..fc35c3cf0 100644 --- a/doc/UsingIntelMKL.dox +++ b/doc/UsingIntelMKL.dox @@ -63,7 +63,11 @@ In addition you can choose which parts will be substituted by defining one or mu \c EIGEN_USE_MKL_ALL Defines \c EIGEN_USE_BLAS, \c EIGEN_USE_LAPACKE, and \c EIGEN_USE_MKL_VML -The options can be combined with \b MKL_DIRECT_CALL to enable MKL direct call feature. 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. To make it work properly, the macro \c EIGEN_USE_MKL must also be defined in the case none of the other \c EIGEN_USE_MKL_* macros has been defined. +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. -- cgit v1.2.3