https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Anamolous-behavior-of-Intel-MKL/m-p/913592#M12342 I am using Intel MKL routine zgemm() to multiply two complex matrices on a 2-core processor machine with a clock speed of 2.79 GHz<BR /> <BR /> When I run the program with no OMP_NUM_THREADS and KMP_AFFINITY not set, I am getting approximately 2700 MLFOPS. When I set OMP_NUM_THREADS=2 and set KMP_AFFINITY= (null), my program's FLOPS go down to 1390 MFLOPS. When unset KMP_AFFINITY FLOP rate goes down even further to 1000 MFLOPS.<BR /> <BR /> Why is the single thread code running better than when I specify two threads?<BR /> <BR /> TIA<BR /> <BR /> Wed, 08 Aug 2007 18:09:17 GMT Intel_C_Intel 2007-08-08T18:09:17Z https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Anamolous-behavior-of-Intel-MKL/m-p/913592#M12342 I am using Intel MKL routine zgemm() to multiply two complex matrices on a 2-core processor machine with a clock speed of 2.79 GHz<BR /> <BR /> When I run the program with no OMP_NUM_THREADS and KMP_AFFINITY not set, I am getting approximately 2700 MLFOPS. When I set OMP_NUM_THREADS=2 and set KMP_AFFINITY= (null), my program's FLOPS go down to 1390 MFLOPS. When unset KMP_AFFINITY FLOP rate goes down even further to 1000 MFLOPS.<BR /> <BR /> Why is the single thread code running better than when I specify two threads?<BR /> <BR /> TIA<BR /> <BR /> Wed, 08 Aug 2007 18:09:17 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Anamolous-behavior-of-Intel-MKL/m-p/913592#M12342 Intel_C_Intel 2007-08-08T18:09:17Z