In very large, complex functions, loops preceded by OpenMP directives may not be threaded. Compiler may emit the warning remark: "An internal threshold was exceeded: loops may not be vectorized or parallelized. Try to reduce routine size."
This page lists fixes that have been made in Intel Professional Edition Compilers 11.1.
The newest versions of the Intel® C++ and Fortran compilers now support OpenMP* environment variable OMP_PROC_BIND on compatible non-Intel processors for Linux* and Windows* platfo