Next:
Preface
Up:
ScaLAPACK Users' Guide
Previous:
List of Figures
List of Tables
Matrix types in the ScaLAPACK naming scheme
Driver routines for linear equations
Driver routines for linear least squares problems
Driver routines for standard eigenvalue and singular value problems
Driver routine for the generalized symmetric definite eigenvalue problems
Computational routines for linear equations
Computational routines for orthogonal factorizations
Computational routines for the symmetric eigenproblem
Computational routines for the nonsymmetric eigenproblem
Computational routines for the singular value decomposition
Reduction of generalized symmetric definite eigenproblems to standard problems
Computational routines for the generalized symmetric definite eigenproblem
Scopes provided by a two-dimensional process grid
Valid values of DESC_(DTYPE_)
One-dimensional block mapping example for
P
=2 and
N
=16
One-dimensional cyclic mapping example for
P
=2 and
N
=16
One-dimensional block-cyclic mapping example for
P
=2,
NB
=3 and
N
=16
One-dimensional block-cyclic mapping example for
P
=2,
SRC
=1,
NB
=3 and
N
=16
Content of the array descriptor for in-core dense matrices
Sizes of the local arrays
One-dimensional block-column mapping example for
P
=2 and
N
=16
One-dimensional block-column mapping for
P
=2,
SRC
=1,
N
=16 and
NB
=8
Content of the array descriptor for in-core narrow band and tridiagonal coefficient matrices
Content of the array descriptor for right-hand-side dense matrices for narrow band and tridiagonal solvers
Content of the array descriptor for out-of-core dense matrices
Variable definitions
Characteristics of the Cray T3E and IBM SP2 computers timed
Characteristics of the Intel computers timed
Characteristics of the networks of workstations timed
BLACS and Level 3 BLAS performance indicators
Speed in Mflop/s for the PBLAS matrix-vector multiply routine PSGEMV/PDGEMV
Speed in Mflop/s for the PBLAS matrix-matrix multiply routine PSGEMM/PDGEMM
``Standard'' floating-point operation (
) and communication costs (
,
) for selected ScaLAPACK drivers
Speed in Mflop/s of PSGESV/PDGESV for square matrices of order
N
Speed in Mflop/s of PSPOSV/PDPOSV for matrices of order
N
with UPLO=`U'
Speed in Mflop/s of PSGELS/PDGELS for square matrices of order
N
Execution time in seconds of PSSYEVX/PDSYEVX for square matrices of order
N
Execution time in seconds of PSSYEV/PDSYEV for square matrices of order
N
Execution time in seconds of PSGESVD/PDGESVD for square matrices of order
N
Execution time in seconds of PDLAHQR for square matrices of order
N
Estimated (Est) versus obtained (Obt) Mflop/s rates of PDGESV and PDPOSV on
P
nodes of the IBM SP2 computer for matrices of order
N
and a block size (
NB
) equal to 50
Process grid suggestions for some ScaLAPACK drivers
Values of machine parameters in IEEE floating-point arithmetic
Vector and matrix norms
Bounding one vector norm in terms of another
Bounding one matrix norm in terms of another
Susan Blackford
Tue May 13 09:21:01 EDT 1997
) and communication
costs (
, 
) for selected ScaLAPACK drivers