- Infos im HLRS Wiki sind nicht rechtsverbindlich und ohne Gewähr -
- Information contained in the HLRS Wiki is not legally binding and HLRS is not responsible for any damages that might result from its use -
MKL: Difference between revisions
From HLRS Platforms
Jump to navigationJump to search
No edit summary |
No edit summary |
||
| Line 13: | Line 13: | ||
Load the necessary module. For example: | Load the necessary module. For example: | ||
<pre> | |||
module load compiler/intel | module load compiler/intel | ||
module load numlib/intel/mkl # set up MKL environment | module load numlib/intel/mkl # set up MKL environment | ||
module load mpi/impi # if MPI needed | module load mpi/impi # if MPI needed | ||
</pre> | |||
=== Example === | === Example === | ||
| Line 50: | Line 50: | ||
=== Compilation example === | === Compilation example === | ||
<pre> | |||
ifort -c example_blas.f90 -o example_blas.o | ifort -c example_blas.f90 -o example_blas.o | ||
ifort -L$MKLROOT/lib/intel64 -lmkl_intel_lp64 -lmkl_intel_thread -lmkl_core -openmp5 -lpthread example_blas.o | ifort -L$MKLROOT/lib/intel64 -lmkl_intel_lp64 -lmkl_intel_thread -lmkl_core -openmp5 -lpthread example_blas.o | ||
</pre> | |||
To see what libraries are recommended for a particular use case, visit: | To see what libraries are recommended for a particular use case, visit: | ||
Revision as of 10:51, 17 October 2014
| Intel® Math Kernel Library (MKL) is a library of optimized math routines for science, engineering, and financial applications. Core math functions include BLAS, LAPACK, ScaLAPACK, Sparse Solvers, Fast Fourier Transforms and Vector Math. |
| ||||||||||||
Using MKL on Nehalem cluster
This example shows the basic steps when using MKL.
Load the necessary module. For example:
module load compiler/intel module load numlib/intel/mkl # set up MKL environment module load mpi/impi # if MPI needed
Example
File: example_blas.f90
program example_blas implicit none real, dimension(3) :: a = (/2.,1.,-1./), b = (/5., -2., 1.5/) real :: c, sdot real(kind=8) :: d, dnrm2 ! *** skalar product *** ! sdot: s ... REAL, dot ... skalar product ! 1. Argument ... dimensions of the vectors ! 2. und 4. A. ... the vectors ! 3. und 5. A. ... increment (here 1) c = sdot(3, a, 1, b, 1) write(*,*) c ! Result: 6.500000 ! *** norm of the vectors *** ! dnrm2: d ... DOUBLE PRECISION, nrm2 ... (euklidian) norm ! 1. Argument: dimensions of the vectors ! 2. A.: vektor ! 3. A.: increment (here 1) d = dnrm2(3, dble(a), 1) write(*,*) d ! Result: 2.44948974278318 end program example_blas
Compilation example
ifort -c example_blas.f90 -o example_blas.o ifort -L$MKLROOT/lib/intel64 -lmkl_intel_lp64 -lmkl_intel_thread -lmkl_core -openmp5 -lpthread example_blas.o
To see what libraries are recommended for a particular use case, visit: