https://community.intel.com/t5/Intel-Fortran-Compiler/illegal-instruction-with-ifort-and-mkl-10-1-012-under-openmp/m-p/747446#M4988 I don't have any experience with 32-bit Core Duo, but it doesn't have a reputation for effective OpenMP support. I can't find -march=prescott in the documentation (-xP would be the usual equivalent). -march=pentium4 should be OK.<BR /> Mon, 07 Apr 2008 12:45:27 GMT TimP 2008-04-07T12:45:27Z https://community.intel.com/t5/Intel-Fortran-Compiler/illegal-instruction-with-ifort-and-mkl-10-1-012-under-openmp/m-p/747444#M4986 Greetings -- I'm compiling the same Fortran code with or without OpenMP on my Mac OSX Core Duo MacBook with 32-bit prescott CPU. Works fine without -openmp. When I try to exploit OpenMP, which the application allows, here's what happens:<BR /><BR />zsh: illegal hardware instruction ./example.DARWIN_ICC_IA32.x &lt; netflix-double-rra.in<BR /><BR />-- now I make sure I use ifort as<BR /><BR />IFORT=/opt/intel/fc/10.1.012/bin/ifort<BR /><BR />and other options are <BR /><BR /># Compiler flags<BR />OPENMP = -openmp<BR />OPTIMIZE = -O3 -ipo $(CPUOPT)<BR />FFLAGS = -w95 -cm -assume buffered_io -vec_report0 $(OPTIMIZE) $(OPENMP)<BR /><BR />-- where CPUOPT is not specified for ifort, I use -march-prescott for gfortran. (Which architecture could I use for the 32-bit Core Duo with ifort?)<BR /><BR />My MKL is used as follows:<BR /><BR />BLAS = -L/Library/Frameworks/Intel_MKL.framework/Libraries/32 -lmkl_intel -lmkl_intel_thread -lmkl_lapack -lmkl_core<BR /><BR />-- as you can see, I get 32-bit throughout. What's up with the illegal instruction?<BR /> Mon, 07 Apr 2008 08:21:50 GMT https://community.intel.com/t5/Intel-Fortran-Compiler/illegal-instruction-with-ifort-and-mkl-10-1-012-under-openmp/m-p/747444#M4986 braver 2008-04-07T08:21:50Z https://community.intel.com/t5/Intel-Fortran-Compiler/illegal-instruction-with-ifort-and-mkl-10-1-012-under-openmp/m-p/747445#M4987 Same result occurs if I link with Veclib or Goto BLAS -- when OpenMP is enabled. Without OpenMP, ifort_mkl works fine. I process a very large matrix which takes up 1.1 GB. Same code compiled with OpenMP works fine with a small matrix. I increase ulimit -x unlimited for all x's reported by ulimit -a.<BR /> Mon, 07 Apr 2008 08:54:04 GMT https://community.intel.com/t5/Intel-Fortran-Compiler/illegal-instruction-with-ifort-and-mkl-10-1-012-under-openmp/m-p/747445#M4987 braver 2008-04-07T08:54:04Z https://community.intel.com/t5/Intel-Fortran-Compiler/illegal-instruction-with-ifort-and-mkl-10-1-012-under-openmp/m-p/747446#M4988 I don't have any experience with 32-bit Core Duo, but it doesn't have a reputation for effective OpenMP support. I can't find -march=prescott in the documentation (-xP would be the usual equivalent). -march=pentium4 should be OK.<BR /> Mon, 07 Apr 2008 12:45:27 GMT https://community.intel.com/t5/Intel-Fortran-Compiler/illegal-instruction-with-ifort-and-mkl-10-1-012-under-openmp/m-p/747446#M4988 TimP 2008-04-07T12:45:27Z https://community.intel.com/t5/Intel-Fortran-Compiler/illegal-instruction-with-ifort-and-mkl-10-1-012-under-openmp/m-p/747447#M4989 You most certainly do NOT have any kind of "Prescott" in a Mac. That was the first 90nm Pentium 4 desktop processor. Core Duo in a MacBook would be Dothan. But for the purpose of generated code selection, Prescott is compatible. 32-bit ifort will default to that so there's nothing to specify.<BR /><BR />It would be helpful to know where in the application this illegal instruction fault is happening.<BR /> Mon, 07 Apr 2008 15:21:26 GMT https://community.intel.com/t5/Intel-Fortran-Compiler/illegal-instruction-with-ifort-and-mkl-10-1-012-under-openmp/m-p/747447#M4989 Steven_L_Intel1 2008-04-07T15:21:26Z