HP MLIB User's Guide Vol. 2 7th Ed.

Chapter 7 Miscellaneous Routines 609
Control extent of parallelism MLIB_SETNUMTHREADS
If a parallel VECLIB subprogram is called from a
parallelized loop or region, VECLIB will automatically
avoid over-subscription of the CPUs. The number of
threads spawned by each call to a parallelized VECLIB
subroutine on a nested parallel region is limited by
MLIB_NUMBER_OF_THREADS, by the number of
threads still available in the system, and will never be
larger than four. Specifically:
MIN (MLIB_NUMBER_OF_THREADS, threads
still available, 4)
Notes nthreads becomes internal state for MLIB_GETNUMTHREADS. Only one
value of nthread is saved within a UNIX process; subsequent calls to
MLIB_SETNUMTHREADS overwrite the previous value.