HP MLIB User's Guide Vol. 1 7th Ed.

Chapter 1 Introduction to VECLIB 19

Parallel processing

For Korn shell:

export MLIB_NUMBER_OF_THREADS=8

MLIB_NUMBER_OF_THREADS is examined on the ﬁrst call to a

parallelized VECLIB subprogram to establish the default parallel action

within VECLIB.

Use the subroutine MLIB_SETNUMTHREADS to restore VECLIB parallel

processing to its run-time default that was speciﬁed by

MLIB_NUMBER_OF_THREADS. Refer to the mlib_setnumthreads(3m)

man page for usage information.

• Use the subroutine MLIB_SETNUMTHREADS.

You can call this subroutine at any time to set the maximum number of

parallel threads used in subsequent VECLIB or LAPACK calls. The

speciﬁed value overrides the absence of the

MLIB_NUMBER_OF_THREADS environment variable or any value

assigned to it.

• To modify the effect of the MLIB_NUMBER_OF_THREADS and

MLIB_SETNUMTHREADS, you can also use

MP_NUMBER_OF_THREADS at runtime. When

MP_NUMBER_OF_THREADS is set to a value smaller than

MLIB_NUMBER_OF_THREADS and MLIB_SETNUMTHREADS, the

value of MP_NUMBER_OF_THREADS takes precedence and limits the

amount of parallelism to MP_NUMBER_OF_THREADS.

These controls set the maximum amount of SMP parallelism that your program

can use, and the VECLIB-speciﬁc mechanisms offer ﬁner control within that

maximum. Refer to “Performance beneﬁts” below for more information.

Performance beneﬁts

If VECLIB parallelism is enabled, each parallelized VECLIB subprogram

determines at runtime if multiple processors are available. If multiple

processors are available, VECLIB detects whether the program is already using

multiple threads. If the application calling VECLIB is not running multiple

threads, VECLIB will attempt to use all available threads (limited by

MLIB_NUMBER_THREADS). If the application calling VECLIB is already

running multiple threads, VECLIB will attempt to use the remaining threads

without over-subscribing. This is a form of nested parallelism.

If you are using an HP server with multiple processors, you can realize the

performance beneﬁts of parallel processing in three ways:

• Call any parallelized VECLIB subprogram. Let it use parallelism internally

if it determines that it is appropriate to do so based on such factors as

problem size, system conﬁguration, and user environment.