HP MLIB for Itanium Linux Version 9.6 Release Note

What’s in This Version

HP MLIB for Itanium Linux Version 9.6 Release Note 11

• Sparse symmetric ordinary and generalized eigensystems solutions.

• Full METIS functionality

This implementation provides the METIS Version 4.0.1 library. It is based on the

public-domain METIS, which was developed at the University of Minnesota, Department

of Computer Science, and the Army HPC Research Center. The library contains a set of

subroutines for graph partitioning, mesh partitioning, and sparse matrix reordering, as

well as auxiliary routines. HP MLIB contains the full METIS functionality as that in the

public domain METIS, however, the routine names are different. HP MLIB METIS

routine names have been prepended with mlib_ to avoid name conflict on applications

and libraries that contain their own local version of METIS.

For more information about METIS, please refer to:

http://www-users.cs.umn.edu/~karypis/metis/metis/index.html

VMATH

VMATH is a library of vector math routines corresponding to many of the widely used scalar

math routines available with C, C++, and Fortran90.

VMATH is intended for computationally intensive mathematical applications amenable to a

vector programming style.

VMATH provides two libraries: VMATH, whose interface uses 4-byte integers; and VMATH8,

whose interface uses 8-byte integers and is otherwise equivalent to VMATH. VMATH

routines come with both Fortran and C interfaces.

For more detailed information on VMATH as well as subprogram specifications, please refer

to the HP MLIB User’s Guide. Or refer to the man pages installed in the directory

/opt/mlib/share/man. VMATH man pages provide a man page for each subprogram.

SMP Parallelism

Parallel processing is available on multi-processor HP platforms. These systems can divide a

single computational process into smaller streams of execution. The result is that you can

have more than one processor executing on behalf of the same process.

Some BLAS-2, BLAS-3, LAPACK, Sparse Solvers, convolution, and FFT SMP parallelism is

implemented using OpenMP—a portable, scalable programming model that gives

shared-memory parallel programmers a simple and flexible interface for developing parallel

applications.

For usage information, see “SMP Parallelism Usage” on page 22.