when I offload a parallel region, my OpenMP tasks are not executed, is this intended?
The example below gives no output as it is, it seems the tasks are created but not executed. If I omit the offload or the task pragma, I get the expected result. Any idea what I am doing wrong?
#pragma offload target(mic)
#pragma omp parallel
#pragma omp task
I confirmed this defect is fixed in the Intel Fortran Composer XE 2013 Update 2 (2013.1.146 - Linux) now available for download from the Intel Registration Center (https://registrationcenter.intel.com)