Scalapack on the NAVO MSRC IBM Power6
- ContactIs.Organization
PETTT Advanced Computational Environments
- DateOfInformation
- Mon Dec 01 18:40:58 PST 2008
- DeployedOn.Machine
- NAVO MSRC IBM POWER6 - Davinci
- DeploymentDate
- Mon Oct 17 13:49:35 EDT 2005
- IsDeploymentOf.Asset
- Scalapack
- Abstract
- 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-
Mulitple-Data style using explicit message passing for interprocessor communication. It assumes
matrices are laid out in a two-dimensional block cyclic decomposition.
ScaLAPACK is designed for heterogeneous computing and is portable on any computer that supports
MPI or PVM.
Like LAPACK, the ScaLAPACK routines are based on block-partitioned algorithms in order to minimize
the frequency of data movement between different levels of memory hierarchy. (For some 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.
- ContactIs.Organization
- PETTT Advanced Computational Environments
- DateOfInformation
- Tue Dec 04 16:14:32 EST 2007
- Documentation
- http://www.netlib.org/scalapack/slug/index.html
- Domain
- Numerical Programs and Routines
- Linear algebra
- IsComposedOf.Asset
- ATLAS/BLAS
- Abstract
- The ATLAS (Automatically Tuned Linear Algebra Software) project is an ongoing research effort focusing on applying empirical techniques in order to provide portable performance. At present, it provides C and Fortran77 interfaces to a portably efficient BLAS implementation, as well as a few routines from LAPACK.
- ContactIs.Organization
- PETTT Advanced Computational Environments
- DateOfInformation
- Sat Jan 03 10:47:08 PST 2009
- DistributionStatement
- http://math-atlas.sourceforge.net/faq.html#license
- Documentation
- http://math-atlas.sourceforge.net/faq.html#doc
- Domain
- Numerical Programs and Routines
- Linear algebra
- Name
- ATLAS/BLAS
- RecordMaintainedBy.Organization
- PETTT Advanced Computational Environments
- TitleLine
- Automatically Tuned Linear Algebra Software (ATLAS)
- Version
- 3.6.0
- VersionDate
- December 21, 2003
- Webpage
- http://math-atlas.souceforge.net/
- IsMadeOf.Element
- buildMatrix
- ElementType
- Matlab .m file
- Name
- buildMatrix
- Name
- Scalapack
- RecordMaintainedBy.Organization
- PETTT Advanced Computational Environments
- Version
- 1.8.0
- VersionDate
- August 31, 2001
- WasCreatedBy.Organization
- AHPCRC
- Webpage
- http://www.netlib.org/scalapack/scalapack_home.html
- Name
- Scalapack on the NAVO MSRC IBM Power6
- Status
- Installed
- UsageInfo
- The Scalapack library is located in $PET_HOME/MATH/IBM/lib32 (and lib64) for Scalapack built using IBM's compilers. A version of Scalapack built using the GNU compilers is located in $PET_HOME/MATH/GNU/lib32 (and lib64).
- Version
- 1.8.0