Running the Software

To obtain results for the pre-determined sample problem sizes on a given system, type one of the following, as appropriate:

./runme_xeon32

./runme_xeon64

./runme_xeon64_ao

./runme_mic

To run the software for other problem sizes, see the extended help included with the program. Extended help can be viewed by running the program executable with the -e option:

./xlinpack_xeon32 -e

./xlinpack_xeon64 -e

./xlinpack_mic -e

The pre-defined data input files lininput_xeon32, lininput_xeon64, lininput_xeon64_ao, and lininput_mic are examples. Different systems have different numbers of processors or amounts of memory and therefore require new input files. The extended help can give insight into proper ways to change the sample input files.

Each input file requires at least the following amount of memory:

lininput_xeon32             2 GB

lininput_xeon64            16 GB

lininput_xeon64_ao          8 GB

lininput_mic                8 GB

If the system has less memory than the above sample data input requires, you may need to edit or create your own data input files, as explained in the extended help.

The Intel Optimized LINPACK Benchmark determines the optimal number of OpenMP threads to use. To run a different number, you can set the OMP_NUM_THREADS or MKL_NUM_THREADS environment variable inside a sample script. If you run the Intel Optimized LINPACK Benchmark without setting the number of threads, it defaults to the number of physical cores.