NAG
Overview
The Intel® Math Kernel Library provides developers of scientific and engineering software with a set of linear algebra, fast Fourier transforms and vector math functions optimized for the latest Intel® Pentium® 4 and Intel® Itanium processors. MKL contains LAPACK, the basic linear algebra subprograms (BLAS), and the extended BLAS (sparse). In addition, there is a set of fast Fourier transforms in single- and double-precision, real and complex data types with both Fortran and C interfaces. MKL also includes a set of vectorized transcendental functions in the Vector Math Library (VML), offering both high performance and excellent accuracy compared to the libm functions for most of the processors.
Setup
Use of MKL does not require any special setup.
Usage - Fortran Library
To include the MKL library in your Fortran code you must link in the
appropriate libraries.
MKL may be used with the Intel compilers only.
When using the Intel Fortran compiler you need to include the
proper library using the following string
-L/usr/global/intel/mkl801/lib/ARCH -lmkl -Wl,-R/usr/global/intel/mkl801/lib/ARCH
where ARCH is one of the following:
- em64t - AMD Opteron and Intel em64t machines (lionxo, hammer, etc.)
- 32- 32-bit Intel machines (e.g. lionxm)
- 64- ia64 architecture (e.g. Unisys)
When using the lapack library you must also include the proper library using the following string
-L/usr/global/intel/mkl801/lib/ARCH -lmkl -lmkl_lapackNN -Wl,-R/usr/global/intel/mkl801/lib/ARCH
where ARCH is defined as above and NN is 32 or 64, depending on machine architecture.
Usage - C Library
This section is under construction
Examples
The MKL libraries can be rather complex to use.
Library documentation can be found in /usr/global/intel/mkl801/doc.
Example codes may be found in directory /usr/global/intel/mkl801/examples/
Documentation
Library documentation can be found in /usr/global/intel/mkl801/doc/mklman.pdf
Please send questions or suggestions about this web page to beatnic@aset.psu.edu
ASET | ITS | Penn State
|
