Skip to content

SIRF, Gadgetron and MKL

Edoardo Pasca edited this page May 8, 2019 · 3 revisions

Gadgetron can make use of the Intel Math Kernel Library. This will speed up some calculations and might give you some extra functionality. However, this is currently not needed for SIRF.

If you want to use MKL with Gadgetron:

  1. Install Intel MKL following the instructions at their website. For debian based linux follow this link. The latter will install MKL in opt/intel
  2. Gadgetron's FindMKL.cmake will try to look for MKL libraries in /opt/intel on Unix/Apple and in C:/Program Files (x86)/Intel/Composer XE in Windows. Make sure that this is the location of the library or pass the variable MKLROOT_PATH (Unix/Apple) or set the environment variable MKLROOT_PATH on Windows.
  3. Configure the SuperBuild to pass Gadgetron_USE_MKL=ON. To disable/enable after you've run cmake use -UGadgetron_USE_MKL -DGadgetron_USE_MKL=ON or OFF accordingly.

If the version of MKL you have is not sufficient for Gadgetron, the configuration will fail and you'll have to disable MKL as in 3.

Notice that other packages may look for a blas implementation issuing CMake's find_package(BLAS). This will look for MKL taking hint directories from the environment variable LD_LIBRARY_PATH, DYLD_LIBRARY_PATH and LIB, on Unix, Apple and Windows respectively.

See also Readme