HP MLIB for Itanium Linux Version 9.6 Release Note

Compatibility Information

HP MLIB for Itanium Linux Version 9.6 Release Note22

NOTE HP-MPI 2.2 scripts mpif77 and mpif90 default to Intel compiler ifort in your

path, and scripts mpicc and mpiCC default to Intel compiler icc in your path. If

you don’t want to use the Intel compilers set in your path, you need to set the

environment variables MPI_F77, MPI_F90, MPI_CC, and MPI_CXX, respectively,

to use the desired Intel compilers. For example, to use the Intel V9.1 compiler:

For Bourne-like shells:

% export MPI_F77=/opt/intel/fc/9.1/bin/ifort

% export MPI_F90=/opt/intel/fc/9.1/bin/ifort

% export MPI_CC=/opt/intel/cc/9.1/bin/icc

% export MPI_CXX=/opt/intel/cc/9.1/bin/icc

For C-like shells:

% setenv MPI_F77 /opt/intel/fc/9.1/bin/ifort

% setenv MPI_F90 /opt/intel/fc/9.1/bin/ifort

% setenv MPI_CC /opt/intel/cc/9.1/bin/icc

% setenv MPI_CXX /opt/intel/cc/9.1/bin/icc

MPI_F77 must be set even if Fortran 77 is not in use as the variable is used in

the mpif90 shell script.

SMP Parallelism Usage

You can enable or disable SMP parallel processing at runtime. A program does not use

parallelism in MLIB unless parallel processing is enabled at runtime. Some BLAS-2, BLAS-3,

LAPACK, sparse solvers, convolution, and FFT routines have been optimized for parallelism.

Controlling MLIB SMP parallelism at runtime

Two methods are available at runtime to specify the extent of SMP parallel processing in

MLIB.

1. Use MLIB_NUMBER_OF_THREADS, a shell environment variable that allows you to enable

SMP parallelism within MLIB subprograms and to specify the maximum number of

threads that can be used in parallel regions.

Not setting MLIB_NUMBER_OF_THREADS has the same result as setting it to 1; parallel

processing is disabled within MLIB subroutines. Setting MLIB_NUMBER_OF_THREADS to the

number of CPUs in the system (or greater) allows parallelized MLIB subprograms to use

as many CPUs as are available to the application.