sposvx.f

Go to the documentation of this file.

      SUBROUTINE sposvx( FACT, UPLO, N, NRHS, A, LDA, AF, LDAF, EQUED,
     $                   s, b, ldb, x, ldx, rcond, ferr, berr, work,
     $                   iwork, info )
*
      include 'plasmaf.h'
*
*  -- LAPACK driver routine (version 3.2) --
*     Univ. of Tennessee, Univ. of California Berkeley and NAG Ltd..
*     November 2006
*
*     .. Scalar Arguments ..
      CHARACTER          equed, fact, uplo
      INTEGER            info, lda, ldaf, ldb, ldx, n, nrhs
      INTEGER            plasma_uplo
      REAL               rcond
*     ..
*     .. Array Arguments ..
      INTEGER            iwork( * )
      REAL               a( lda, * ), af( ldaf, * ), b( ldb, * ),
     $                   berr( * ), ferr( * ), s( * ), work( * ),
     $                   x( ldx, * )
*     ..
*
*  Purpose
*  =======
*
*  SPOSVX uses the Cholesky factorization A = U**T*U or A = L*L**T to
*  compute the solution to a real system of linear equations
*     A * X = B,
*  where A is an N-by-N symmetric positive definite matrix and X and B
*  are N-by-NRHS matrices.
*
*  Error bounds on the solution and a condition estimate are also
*  provided.
*
*  Description
*  ===========
*
*  The following steps are performed:
*
*  1. If FACT = 'E', real scaling factors are computed to equilibrate
*     the system:
*        diag(S) * A * diag(S) * inv(diag(S)) * X = diag(S) * B
*     Whether or not the system will be equilibrated depends on the
*     scaling of the matrix A, but if equilibration is used, A is
*     overwritten by diag(S)*A*diag(S) and B by diag(S)*B.
*
*  2. If FACT = 'N' or 'E', the Cholesky decomposition is used to
*     factor the matrix A (after equilibration if FACT = 'E') as
*        A = U**T* U,  if UPLO = 'U', or
*        A = L * L**T,  if UPLO = 'L',
*     where U is an upper triangular matrix and L is a lower triangular
*     matrix.
*
*  3. If the leading i-by-i principal minor is not positive definite,
*     then the routine returns with INFO = i. Otherwise, the factored
*     form of A is used to estimate the condition number of the matrix
*     A.  If the reciprocal of the condition number is less than machine
*     precision, INFO = N+1 is returned as a warning, but the routine
*     still goes on to solve for X and compute error bounds as
*     described below.
*
*  4. The system of equations is solved for X using the factored form
*     of A.
*
*  5. Iterative refinement is applied to improve the computed solution
*     matrix and calculate error bounds and backward error estimates
*     for it.
*
*  6. If equilibration was used, the matrix X is premultiplied by
*     diag(S) so that it solves the original system before
*     equilibration.
*
*  Arguments
*  =========
*
*  FACT    (input) CHARACTER*1
*          Specifies whether or not the factored form of the matrix A is
*          supplied on entry, and if not, whether the matrix A should be
*          equilibrated before it is factored.
*          = 'F':  On entry, AF contains the factored form of A.
*                  If EQUED = 'Y', the matrix A has been equilibrated
*                  with scaling factors given by S.  A and AF will not
*                  be modified.
*          = 'N':  The matrix A will be copied to AF and factored.
*          = 'E':  The matrix A will be equilibrated if necessary, then
*                  copied to AF and factored.
*
*  UPLO    (input) CHARACTER*1
*          = 'U':  Upper triangle of A is stored;
*          = 'L':  Lower triangle of A is stored.
*
*  N       (input) INTEGER
*          The number of linear equations, i.e., the order of the
*          matrix A.  N >= 0.
*
*  NRHS    (input) INTEGER
*          The number of right hand sides, i.e., the number of columns
*          of the matrices B and X.  NRHS >= 0.
*
*  A       (input/output) REAL array, dimension (LDA,N)
*          On entry, the symmetric matrix A, except if FACT = 'F' and
*          EQUED = 'Y', then A must contain the equilibrated matrix
*          diag(S)*A*diag(S).  If UPLO = 'U', the leading
*          N-by-N upper triangular part of A contains the upper
*          triangular part of the matrix A, and the strictly lower
*          triangular part of A is not referenced.  If UPLO = 'L', the
*          leading N-by-N lower triangular part of A contains the lower
*          triangular part of the matrix A, and the strictly upper
*          triangular part of A is not referenced.  A is not modified if
*          FACT = 'F' or 'N', or if FACT = 'E' and EQUED = 'N' on exit.
*
*          On exit, if FACT = 'E' and EQUED = 'Y', A is overwritten by
*          diag(S)*A*diag(S).
*
*  LDA     (input) INTEGER
*          The leading dimension of the array A.  LDA >= max(1,N).
*
*  AF      (input or output) REAL array, dimension (LDAF,N)
*          If FACT = 'F', then AF is an input argument and on entry
*          contains the triangular factor U or L from the Cholesky
*          factorization A = U**T*U or A = L*L**T, in the same storage
*          format as A.  If EQUED .ne. 'N', then AF is the factored form
*          of the equilibrated matrix diag(S)*A*diag(S).
*
*          If FACT = 'N', then AF is an output argument and on exit
*          returns the triangular factor U or L from the Cholesky
*          factorization A = U**T*U or A = L*L**T of the original
*          matrix A.
*
*          If FACT = 'E', then AF is an output argument and on exit
*          returns the triangular factor U or L from the Cholesky
*          factorization A = U**T*U or A = L*L**T of the equilibrated
*          matrix A (see the description of A for the form of the
*          equilibrated matrix).
*
*  LDAF    (input) INTEGER
*          The leading dimension of the array AF.  LDAF >= max(1,N).
*
*  EQUED   (input or output) CHARACTER*1
*          Specifies the form of equilibration that was done.
*          = 'N':  No equilibration (always true if FACT = 'N').
*          = 'Y':  Equilibration was done, i.e., A has been replaced by
*                  diag(S) * A * diag(S).
*          EQUED is an input argument if FACT = 'F'; otherwise, it is an
*          output argument.
*
*  S       (input or output) REAL array, dimension (N)
*          The scale factors for A; not accessed if EQUED = 'N'.  S is
*          an input argument if FACT = 'F'; otherwise, S is an output
*          argument.  If FACT = 'F' and EQUED = 'Y', each element of S
*          must be positive.
*
*  B       (input/output) REAL array, dimension (LDB,NRHS)
*          On entry, the N-by-NRHS right hand side matrix B.
*          On exit, if EQUED = 'N', B is not modified; if EQUED = 'Y',
*          B is overwritten by diag(S) * B.
*
*  LDB     (input) INTEGER
*          The leading dimension of the array B.  LDB >= max(1,N).
*
*  X       (output) REAL array, dimension (LDX,NRHS)
*          If INFO = 0 or INFO = N+1, the N-by-NRHS solution matrix X to
*          the original system of equations.  Note that if EQUED = 'Y',
*          A and B are modified on exit, and the solution to the
*          equilibrated system is inv(diag(S))*X.
*
*  LDX     (input) INTEGER
*          The leading dimension of the array X.  LDX >= max(1,N).
*
*  RCOND   (output) REAL
*          The estimate of the reciprocal condition number of the matrix
*          A after equilibration (if done).  If RCOND is less than the
*          machine precision (in particular, if RCOND = 0), the matrix
*          is singular to working precision.  This condition is
*          indicated by a return code of INFO > 0.
*
*  FERR    (output) REAL array, dimension (NRHS)
*          The estimated forward error bound for each solution vector
*          X(j) (the j-th column of the solution matrix X).
*          If XTRUE is the true solution corresponding to X(j), FERR(j)
*          is an estimated upper bound for the magnitude of the largest
*          element in (X(j) - XTRUE) divided by the magnitude of the
*          largest element in X(j).  The estimate is as reliable as
*          the estimate for RCOND, and is almost always a slight
*          overestimate of the true error.
*
*  BERR    (output) REAL array, dimension (NRHS)
*          The componentwise relative backward error of each solution
*          vector X(j) (i.e., the smallest relative change in
*          any element of A or B that makes X(j) an exact solution).
*
*  WORK    (workspace) REAL array, dimension (3*N)
*
*  IWORK   (workspace) INTEGER array, dimension (N)
*
*  INFO    (output) INTEGER
*          = 0: successful exit
*          < 0: if INFO = -i, the i-th argument had an illegal value
*          > 0: if INFO = i, and i is
*                <= N:  the leading minor of order i of A is
*                       not positive definite, so the factorization
*                       could not be completed, and the solution has not
*                       been computed. RCOND = 0 is returned.
*                = N+1: U is nonsingular, but RCOND is less than machine
*                       precision, meaning that the matrix is singular
*                       to working precision.  Nevertheless, the
*                       solution and error bounds are computed because
*                       there are a number of situations where the
*                       computed solution can be more accurate than the
*                       value of RCOND would suggest.
*
*  =====================================================================
*
*     .. Parameters ..
      REAL               zero, one
      parameter( zero = 0.0e+0, one = 1.0e+0 )
*     ..
*     .. Local Scalars ..
      LOGICAL            equil, nofact, rcequ
      INTEGER            i, infequ, j
      REAL               amax, anorm, bignum, scond, smax, smin, smlnum
*     ..
*     .. External Functions ..
      LOGICAL            lsame
      REAL               slamch, slansy
      EXTERNAL           lsame, slamch, slansy
*     ..
*     .. External Subroutines ..
      EXTERNAL           slacpy, slaqsy, spocon, spoequ, sporfs, spotrf,
     $                   spotrs, xerbla
*     ..
*     .. Intrinsic Functions ..
      INTRINSIC          max, min
*     ..
*     .. Executable Statements ..
*
      info = 0
      nofact = lsame( fact, 'N' )
      equil = lsame( fact, 'E' )
      IF( nofact .OR. equil ) THEN
         equed = 'N'
         rcequ = .false.
      ELSE
         rcequ = lsame( equed, 'Y' )
         smlnum = slamch( 'Safe minimum' )
         bignum = one / smlnum
      END IF
*
*     Test the input parameters.
*
      IF( .NOT.nofact .AND. .NOT.equil .AND. .NOT.lsame( fact, 'F' ) )
     $     THEN
         info = -1
      ELSE IF( .NOT.lsame( uplo, 'U' ) .AND. .NOT.lsame( uplo, 'L' ) )
     $          THEN
         info = -2
      ELSE IF( n.LT.0 ) THEN
         info = -3
      ELSE IF( nrhs.LT.0 ) THEN
         info = -4
      ELSE IF( lda.LT.max( 1, n ) ) THEN
         info = -6
      ELSE IF( ldaf.LT.max( 1, n ) ) THEN
         info = -8
      ELSE IF( lsame( fact, 'F' ) .AND. .NOT.
     $         ( rcequ .OR. lsame( equed, 'N' ) ) ) THEN
         info = -9
      ELSE
         IF( rcequ ) THEN
            smin = bignum
            smax = zero
            DO 10 j = 1, n
               smin = min( smin, s( j ) )
               smax = max( smax, s( j ) )
   10       continue
            IF( smin.LE.zero ) THEN
               info = -10
            ELSE IF( n.GT.0 ) THEN
               scond = max( smin, smlnum ) / min( smax, bignum )
            ELSE
               scond = one
            END IF
         END IF
         IF( info.EQ.0 ) THEN
            IF( ldb.LT.max( 1, n ) ) THEN
               info = -12
            ELSE IF( ldx.LT.max( 1, n ) ) THEN
               info = -14
            END IF
         END IF
      END IF
*
      IF( info.NE.0 ) THEN
         CALL xerbla( 'SPOSVX', -info )
         return
      END IF
*
      IF( lsame( uplo, 'U' ) ) THEN
         plasma_uplo = plasmaupper     
      ELSE
         plasma_uplo = plasmalower     
      ENDIF
*
      IF( equil ) THEN
*
*        Compute row and column scalings to equilibrate the matrix A.
*
         CALL spoequ( n, a, lda, s, scond, amax, infequ )
         IF( infequ.EQ.0 ) THEN
*
*           Equilibrate the matrix.
*
            CALL slaqsy( uplo, n, a, lda, s, scond, amax, equed )
            rcequ = lsame( equed, 'Y' )
         END IF
      END IF
*
*     Scale the right hand side.
*
      IF( rcequ ) THEN
         DO 30 j = 1, nrhs
            DO 20 i = 1, n
               b( i, j ) = s( i )*b( i, j )
   20       continue
   30    continue
      END IF
*
      IF( nofact .OR. equil ) THEN
*
*        Compute the Cholesky factorization A = U'*U or A = L*L'.
*
         CALL slacpy( uplo, n, n, a, lda, af, ldaf )
         CALL plasma_spotrf( plasma_uplo, n, af, ldaf, info )
*
*        Return if INFO is non-zero.
*
         IF( info.GT.0 )THEN
            rcond = zero
            return
         END IF
      END IF
*
*     Compute the norm of the matrix A.
*
      anorm = slansy( '1', uplo, n, a, lda, work )
*
*     Compute the reciprocal of the condition number of A.
*
      CALL spocon( uplo, n, af, ldaf, anorm, rcond, work, iwork, info )
*
*     Compute the solution matrix X.
*
      CALL slacpy( 'Full', n, nrhs, b, ldb, x, ldx )
      CALL plasma_spotrs( plasma_uplo, n, nrhs, af, ldaf, x, ldx, info )
*
*     Use iterative refinement to improve the computed solution and
*     compute error bounds and backward error estimates for it.
*
      CALL sporfs( uplo, n, nrhs, a, lda, af, ldaf, b, ldb, x, ldx,
     $             ferr, berr, work, iwork, info )
*
*     Transform the solution matrix X to a solution of the original
*     system.
*
      IF( rcequ ) THEN
         DO 50 j = 1, nrhs
            DO 40 i = 1, n
               x( i, j ) = s( i )*x( i, j )
   40       continue
   50    continue
         DO 60 j = 1, nrhs
            ferr( j ) = ferr( j ) / scond
   60    continue
      END IF
*
*     Set INFO = N+1 if the matrix is singular to working precision.
*
      IF( rcond.LT.slamch( 'Epsilon' ) )
     $   info = n + 1
*
      return
*
*     End of SPOSVX
*
      END