Technical Solutions

Solution:

MATLAB uses the Basic Linear Algebra Subroutines (BLAS) libraries to speed up matrix multiplication and LAPACK-based functions like EIG, SVD, and \ (MLDIVIDE). At start-up, MATLAB selects the BLAS library to use.

In MATLAB 7.0.1 (R14SP1) on computers that use Intel processors, the default BLAS library is the Math Kernel Library (MKL) BLAS provided by Intel. For R14 and prior versions, MATLAB still uses the ATLAS BLAS libraries.

If you are using MATLAB 7.0 (R14) and want to take advantage of the potential performance enhancements provided by the MKL BLAS, you can switch to the MKL BLAS by setting the value of the environment variable BLAS_VERSION to the name of the MKL library, mkl.dll. MATLAB uses the BLAS specified by this environment variable, if it exists.

To set the BLAS_VERSION environment variable, follow this procedure:

1. Click the Start button, go to the Settings menu, and select Control Panel.
2. On the Control Panel menu, select System.
3. In the System Properties dialog box, click the "Advanced" tab.
4. On the Advanced panel, click the Environment Variables button.
5. In the Environment Variables dialog box, click the "New" button in the User variables section.
6. In the New User Variable dialog box, enter the name of the variable as BLAS_VERSION and set the value of the variable to the name of the MKL library: mkl.dll.

For information on how to override the default BLAS library for operating systems other than Windows, review the documentation for that specific operating system.

A list of some BLAS vendors:
-------------------------------
Intel MKL: http://www.intel.com/software/products/mkl/

AMD ACML: http://www.amd.com/us-en/Processors/DevelopWithAMD/0,,30_2252_2282,00.html

The AMD ACML BLAS is not supported on MATLAB 7.3 (R2006b) and on previous releases of MATLAB on the Windows platform.

HP MLIB: http://h21007.www2.hp.com/dspp/tech/tech_TechSoftwareDetailPage_IDX/1,,1204,00.html

Sun Performance Library: http://wwws.sun.com/software/sundev/news/features/sunperf.html

Apple Mac: http://developer.apple.com/releasenotes/MacOSX/index.html