SuperLU_DIST  4.0
superlu_dist on CPU and GPU clusters
 All Classes Files Functions Variables Typedefs Enumerations Enumerator Macros Pages
Functions
dsp_blas2.c File Reference

Sparse BLAS 2, using some dense BLAS 2 operations. More...

#include "superlu_ddefs.h"

Functions

void dusolve (int, int, double *, double *)
 
void dlsolve (int, int, double *, double *)
 
void dmatvec (int, int, int, double *, double *, double *)
 
int sp_dtrsv_dist (char *uplo, char *trans, char *diag, SuperMatrix *L, SuperMatrix *U, double *x, int *info)
 
int sp_dgemv_dist (char *trans, double alpha, SuperMatrix *A, double *x, int incx, double beta, double *y, int incy)
 

Detailed Description

Sparse BLAS 2, using some dense BLAS 2 operations.

– Distributed SuperLU routine (version 1.0) –
Lawrence Berkeley National Lab, Univ. of California Berkeley.
September 1, 1999

Function Documentation

void dlsolve ( int  ldm,
int  ncol,
double *  M,
double *  rhs 
)
Solves a dense UNIT lower triangular system. The unit lower 
triangular matrix is stored in a 2D array M(1:nrow,1:ncol). 
The solution will be returned in the rhs vector.
void dmatvec ( int  ldm,
int  nrow,
int  ncol,
double *  M,
double *  vec,
double *  Mxvec 
)
Performs a dense matrix-vector multiply: Mxvec = Mxvec + M * vec.
The input matrix is M(1:nrow,1:ncol); The product is returned in Mxvec[].
void dusolve ( int  ldm,
int  ncol,
double *  M,
double *  rhs 
)
Solves a dense upper triangular system. The upper triangular matrix is
stored in a 2-dim array M(1:ldm,1:ncol). The solution will be returned
in the rhs vector.
int sp_dgemv_dist ( char *  trans,
double  alpha,
SuperMatrix A,
double *  x,
int  incx,
double  beta,
double *  y,
int  incy 
)

Purpose

    sp_dgemv_dist()  performs one of the matrix-vector operations   
       y := alpha*A*x + beta*y,   or   y := alpha*A'*x + beta*y,   
    where alpha and beta are scalars, x and y are vectors and A is a
    sparse A->nrow by A->ncol matrix.

Parameters

    TRANS  - (input) char*
             On entry, TRANS specifies the operation to be performed as   
             follows:   
                TRANS = 'N' or 'n'   y := alpha*A*x + beta*y.   
                TRANS = 'T' or 't'   y := alpha*A'*x + beta*y.   
                TRANS = 'C' or 'c'   y := alpha*A'*x + beta*y.
    ALPHA  - (input) double
             On entry, ALPHA specifies the scalar alpha.
    A      - (input) SuperMatrix*
             Matrix A with a sparse format, of dimension (A->nrow, A->ncol).
             Currently, the type of A can be:
                 Stype = SLU_NC or SLU_NCP; Dtype = SLU_D; Mtype = SLU_GE. 
             In the future, more general A can be handled.
    X      - (input) double*, array of DIMENSION at least   
             ( 1 + ( n - 1 )*abs( INCX ) ) when TRANS = 'N' or 'n'   
             and at least   
             ( 1 + ( m - 1 )*abs( INCX ) ) otherwise.   
             Before entry, the incremented array X must contain the   
             vector x.
    INCX   - (input) int
             On entry, INCX specifies the increment for the elements of   
             X. INCX must not be zero.
    BETA   - (input) double
             On entry, BETA specifies the scalar beta. When BETA is   
             supplied as zero then Y need not be set on input.
    Y      - (output) double*,  array of DIMENSION at least   
             ( 1 + ( m - 1 )*abs( INCY ) ) when TRANS = 'N' or 'n'   
             and at least   
             ( 1 + ( n - 1 )*abs( INCY ) ) otherwise.   
             Before entry with BETA non-zero, the incremented array Y   
             must contain the vector y. On exit, Y is overwritten by the 
             updated vector y.
    INCY   - (input) int
             On entry, INCY specifies the increment for the elements of   
             Y. INCY must not be zero.
    ==== Sparse Level 2 Blas routine.   
int sp_dtrsv_dist ( char *  uplo,
char *  trans,
char *  diag,
SuperMatrix L,
SuperMatrix U,
double *  x,
int *  info 
)

Purpose

  sp_dtrsv_dist() solves one of the systems of equations   
      A*x = b,   or   A'*x = b,
  where b and x are n element vectors and A is a sparse unit , or   
  non-unit, upper or lower triangular matrix.   
  No test for singularity or near-singularity is included in this   
  routine. Such tests must be performed before calling this routine.

Parameters

  uplo   - (input) char*
           On entry, uplo specifies whether the matrix is an upper or   
            lower triangular matrix as follows:   
               uplo = 'U' or 'u'   A is an upper triangular matrix.   
               uplo = 'L' or 'l'   A is a lower triangular matrix.
  trans  - (input) char*
            On entry, trans specifies the equations to be solved as   
            follows:   
               trans = 'N' or 'n'   A*x = b.   
               trans = 'T' or 't'   A'*x = b.   
               trans = 'C' or 'c'   A'*x = b.
  diag   - (input) char*
            On entry, diag specifies whether or not A is unit   
            triangular as follows:   
               diag = 'U' or 'u'   A is assumed to be unit triangular.   
               diag = 'N' or 'n'   A is not assumed to be unit   
                                   triangular.
  L       - (input) SuperMatrix*
        The factor L from the factorization Pr*A*Pc=L*U. Use
            compressed row subscripts storage for supernodes, i.e.,
            L has types: Stype = SLU_SC, Dtype = SLU_D, Mtype = SLU_TRLU.
  U       - (input) SuperMatrix*
         The factor U from the factorization Pr*A*Pc=L*U.
         U has types: Stype = SLU_NC, Dtype = SLU_D, Mtype = SLU_TRU.
  x       - (input/output) double*
            Before entry, the incremented array X must contain the n   
            element right-hand side vector b. On exit, X is overwritten 
            with the solution vector x.
  info    - (output) int*
            If *info = -i, the i-th argument had an illegal value.