Back to the full list of teaching materials
ScaLAPACK Home Page
What is ScaLAPACK?
The ScaLAPACK (or Scalable LAPACK) library includes a subset of
LAPACK routines redesigned for distributed memory MIMD parallel
computers. It is currently written in a Single-Program-Multiple-Data style
using explicit message passing for interprocessor communication. It assumes
matrices are laid out in a two-dimensional block cyclic decomposition.
Software Design
Like LAPACK, the ScaLAPACK routines are based on block-partitioned
algorithms in order to minimize the frequency of data movement between
different levels of the memory hierarchy. (For such machines, the memory
hierarchy includes the off-processor memory of other processors, in addition
to the hierarchy of registers, cache, and local memory on each processor.)
The fundamental building blocks of the ScaLAPACK library are distributed
memory versions (PBLAS)
of the Level
1, 2 and 3 BLAS, and a set of Basic Linear Algebra Communication
Subprograms (BLACS)
for communication tasks that arise frequently in parallel linear algebra
computations. In the ScaLAPACK routines, all interprocessor communication
occurs within the PBLAS and the BLACS. One of the design
goals of ScaLAPACK was to have the ScaLAPACK routines resemble their
LAPACK
equivalents as much as possible.
Supported Architectures
ScaLAPACK is portable on any computer that supports PVM or MPI.
Clusters of computers that have PVM and MPI can use the ScaLAPACK
software.
How can I learn about ScaLAPACK
Support for ScaLAPACK
ScaLAPACK has been thoroughly tested on heterogeneous clusters of workstations
using pvm3.4BETA and mpich version 1.1.0, and on the IBM SP-2, Intel Paragon,
and SGI Power Challenge Array and Origin 2000. The workstations used were
ALPHA, AIX46K, HPPA, SUN4, SUN4SOL2, SGI64, and LINUX. If you do encounter
difficulties, however, we invite you to contact the developers at scalapack@cs.utk.edu
We also highly recommend that the user consult the errata.scalapack
file for information on any machine-specific testing abnormalities.
scalapack@cs.utk.edu
Back to the full list of teaching materials