The OMP standard gives an algorithm for determining the number of threads in a parallel region (page 36, algorithm 2.1 here: http://www.openmp.org/mp-documents/OpenMP3.1.pdf). The last two lines of the algorithm are reproduced here:
else if (dyn-var = false) and (ThreadsRequested > ThreadsAvailable)
then behavior is implementation defined;
Do we know what the Intel implementation is for the last line ?