|
| 1 | +--- |
| 2 | +layout: default |
| 3 | +title: AMICA-Compilation-instructions |
| 4 | +long_title: AMICA-Compilation-instructions |
| 5 | +parent: amica |
| 6 | +grand_parent: Plugins |
| 7 | +--- |
| 8 | +# How to compile with Intel Fortran on Windows |
| 9 | + |
| 10 | +1. Install Intel OneAPI Base Toolkit for Windows. |
| 11 | +2. Install Intel OneAPI HPC Toolkit for Windows. |
| 12 | +3. Open Intel OneAPI command window (in Start menu, 32 or 64 bit as appropriate). Change to directory with Amica code, and compile Amica with the command (/F sets the stack size): |
| 13 | + |
| 14 | + > mpif90 /Qopenmp /Qmkl /F2147483648 /DMKL /fpp /O3 /exe:amica15mkl.exe funmod2.f90 amica15.f90 |
| 15 | + |
| 16 | +4. Test: |
| 17 | + |
| 18 | + > .\amica15mkl.exe .\amicadefs.param |
| 19 | + |
| 20 | +5. The files impi.dll and libfabric.dll should be copied to executable folder when running outside OneAPI command window. Search OneAPI mpi directory for locations. |
| 21 | + |
| 22 | + |
| 23 | +# THow to compile with Intel Fortran on Mac |
| 24 | + |
| 25 | +0. These are old instructions. Try using Intel OneAPI modifiying the commands similar to the instructions for Windows above. |
| 26 | +1. Install Intel Fortran compiler for Mac/Linux (free demo). |
| 27 | + See https://software.intel.com/en-us/intel-parallel-studio-xe |
| 28 | + |
| 29 | +2. Compile MPICH2 setting environmental vars CC, CXX, FC, and F77 to icc and ifort. Set $FBIN to Intel Fortran bin directory. |
| 30 | + |
| 31 | + i) Download the mpich-3.2 code from: http://www.mpich.org/static/downloads/3.2/mpich-3.2.tar.gz |
| 32 | + |
| 33 | + ii) Compile mpich-3.2: |
| 34 | + |
| 35 | + $ cp /Users/$USER/downloads/mpich-3.2.tar.gz . |
| 36 | + $ setenv CC $FBIN/icc |
| 37 | + $ setenv CXX $FBIN/icc |
| 38 | + $ setenv F77 $FBIN/ifort |
| 39 | + $ setenv FC $FBIN/ifort |
| 40 | + $ tar xvf mpich-3.2.tar.gz |
| 41 | + $ cd mpich-3.2 |
| 42 | + $ ./configure --prefix=/Users/$USER/mpich-3.2-install |
| 43 | + $ make |
| 44 | + $ make install |
| 45 | + |
| 46 | +3. Compile Amica with the command: |
| 47 | + |
| 48 | + $ ~/mpich-3.2-install/bin/mpif90 -L/Users/$USER/mpich-3.2-install/lib/ -I/Users/$USER/mpich-3.2-install/include/ -qopenmp -mkl -static-intel -O3 -fpp -DMKL amica15.f90 funmod2.f90 -o amica15mac |
| 49 | + |
| 50 | +4. Test: |
| 51 | + |
| 52 | + i) Download Sample EEG Data (Memorize.fdt and amicadefs.param) from: https://sccn.ucsd.edu/~jason/amica_web.html |
| 53 | + |
| 54 | + ii) Test binary: |
| 55 | + |
| 56 | + $ ./amica15mac ./amicadefs.param |
| 57 | + |
| 58 | + |
| 59 | +# How to compile with Intel Fortran on Ubuntu |
| 60 | + |
| 61 | +0. These are old instructions. Try using Intel OneAPI modifiying the commands similar to the instructions for Windows above. |
| 62 | +1. Install Intel Fortran compiler for Linux. |
| 63 | +2. Compile MPICH2 setting environmental vars CC, CXX, FC, and F77 to icc and ifort. |
| 64 | +3. Compile Amica with the command: |
| 65 | + |
| 66 | + $ /home/jason/mpich2-3.2-install/bin/mpif90 -I/opt/intel/mkl/include/ -fpp -qopenmp -O3 -mkl -static -static-intel -DMKL funmod2.f90 amica15.f90 -o amica15ub |
| 67 | + |
| 68 | +4. Test: |
| 69 | + |
| 70 | + $ ./amica15ub ./amicadefs.param |
| 71 | + |
| 72 | + |
| 73 | +# How to compile with Intel Fortran on Expanse HPC |
| 74 | + |
| 75 | +1. load appropriate modules: |
| 76 | + |
| 77 | +``` |
| 78 | + module purge |
| 79 | + module load cpu/0.15.4 intel intel-mkl mvapich2 |
| 80 | +``` |
| 81 | + |
| 82 | +2. Compile Amica with the command: |
| 83 | + |
| 84 | +``` |
| 85 | + mpif90 -static-intel -fpp -O3 -march=core-avx2 -heap-arrays \ |
| 86 | + -qopenmp -mkl -DMKL -o amica15ex funmod2.f90 amica17.f90 |
| 87 | +``` |
| 88 | + |
| 89 | +3. Test: |
| 90 | +``` |
| 91 | + $ ./amica17nsg ./amicadefs.param |
| 92 | +``` |
| 93 | + |
| 94 | +4. Run on compute partition: |
| 95 | + |
| 96 | +``` |
| 97 | + <Edit amicadefs.param file line to: maxthreads 4> |
| 98 | + $ module load cpu/0.15.4 slurm intel intel-mkl mvapich2 |
| 99 | + $ export OMP_NUM_THREADS=4 ; export SRUN_CPUS_PER_TASK=4 ; export MV2_ENABLE_AFFINITY=0 |
| 100 | + $ srun --partition=compute --nodes=<NUM_NODES> --tasks-per-node=32 --cpus-per-task=4 \ |
| 101 | + --mem=249208M --account=<ACCOUNT> --export=ALL -t 04:00:00 ./amica17nsg ./amicadefs.param |
| 102 | + <If job fails, reduce block_size in amicadefs.param. Increase block_size to speed up.> |
| 103 | +``` |
0 commit comments