pssytrd.f

Go to the documentation of this file.

      SUBROUTINE pssytrd( UPLO, N, A, IA, JA, DESCA, D, E, TAU, WORK,
     $                    LWORK, INFO )
*
*  -- ScaLAPACK routine (version 1.7) --
*     University of Tennessee, Knoxville, Oak Ridge National Laboratory,
*     and University of California, Berkeley.
*     May 25, 2001
*
*     .. Scalar Arguments ..
      CHARACTER          UPLO
      INTEGER            IA, INFO, JA, LWORK, N
*     ..
*     .. Array Arguments ..
      INTEGER            DESCA( * )
      REAL               A( * ), D( * ), E( * ), TAU( * ), WORK( * )
*     ..
*
*  Purpose
*  =======
*
*  PSSYTRD reduces a real symmetric matrix sub( A ) to symmetric
*  tridiagonal form T by an orthogonal similarity transformation:
*  Q' * sub( A ) * Q = T, where sub( A ) = A(IA:IA+N-1,JA:JA+N-1).
*
*  Notes
*  =====
*
*  Each global data object is described by an associated description
*  vector.  This vector stores the information required to establish
*  the mapping between an object element and its corresponding process
*  and memory location.
*
*  Let A be a generic term for any 2D block cyclicly distributed array.
*  Such a global array has an associated description vector DESCA.
*  In the following comments, the character _ should be read as
*  "of the global array".
*
*  NOTATION        STORED IN      EXPLANATION
*  --------------- -------------- --------------------------------------
*  DTYPE_A(global) DESCA( DTYPE_ )The descriptor type.  In this case,
*                                 DTYPE_A = 1.
*  CTXT_A (global) DESCA( CTXT_ ) The BLACS context handle, indicating
*                                 the BLACS process grid A is distribu-
*                                 ted over. The context itself is glo-
*                                 bal, but the handle (the integer
*                                 value) may vary.
*  M_A    (global) DESCA( M_ )    The number of rows in the global
*                                 array A.
*  N_A    (global) DESCA( N_ )    The number of columns in the global
*                                 array A.
*  MB_A   (global) DESCA( MB_ )   The blocking factor used to distribute
*                                 the rows of the array.
*  NB_A   (global) DESCA( NB_ )   The blocking factor used to distribute
*                                 the columns of the array.
*  RSRC_A (global) DESCA( RSRC_ ) The process row over which the first
*                                 row of the array A is distributed.
*  CSRC_A (global) DESCA( CSRC_ ) The process column over which the
*                                 first column of the array A is
*                                 distributed.
*  LLD_A  (local)  DESCA( LLD_ )  The leading dimension of the local
*                                 array.  LLD_A >= MAX(1,LOCr(M_A)).
*
*  Let K be the number of rows or columns of a distributed matrix,
*  and assume that its process grid has dimension p x q.
*  LOCr( K ) denotes the number of elements of K that a process
*  would receive if K were distributed over the p processes of its
*  process column.
*  Similarly, LOCc( K ) denotes the number of elements of K that a
*  process would receive if K were distributed over the q processes of
*  its process row.
*  The values of LOCr() and LOCc() may be determined via a call to the
*  ScaLAPACK tool function, NUMROC:
*          LOCr( M ) = NUMROC( M, MB_A, MYROW, RSRC_A, NPROW ),
*          LOCc( N ) = NUMROC( N, NB_A, MYCOL, CSRC_A, NPCOL ).
*  An upper bound for these quantities may be computed by:
*          LOCr( M ) <= ceil( ceil(M/MB_A)/NPROW )*MB_A
*          LOCc( N ) <= ceil( ceil(N/NB_A)/NPCOL )*NB_A
*
*  Arguments
*  =========
*
*  UPLO    (global input) CHARACTER
*          Specifies whether the upper or lower triangular part of the
*          symmetric matrix sub( A ) is stored:
*          = 'U':  Upper triangular
*          = 'L':  Lower triangular
*
*  N       (global input) INTEGER
*          The number of rows and columns to be operated on, i.e. the
*          order of the distributed submatrix sub( A ). N >= 0.
*
*  A       (local input/local output) REAL pointer into the
*          local memory to an array of dimension (LLD_A,LOCc(JA+N-1)).
*          On entry, this array contains the local pieces of the
*          symmetric distributed matrix sub( A ).  If UPLO = 'U', the
*          leading N-by-N upper triangular part of sub( A ) contains
*          the upper triangular part of the matrix, and its strictly
*          lower triangular part is not referenced. If UPLO = 'L', the
*          leading N-by-N lower triangular part of sub( A ) contains the
*          lower triangular part of the matrix, and its strictly upper
*          triangular part is not referenced. On exit, if UPLO = 'U',
*          the diagonal and first superdiagonal of sub( A ) are over-
*          written by the corresponding elements of the tridiagonal
*          matrix T, and the elements above the first superdiagonal,
*          with the array TAU, represent the orthogonal matrix Q as a
*          product of elementary reflectors; if UPLO = 'L', the diagonal
*          and first subdiagonal of sub( A ) are overwritten by the
*          corresponding elements of the tridiagonal matrix T, and the
*          elements below the first subdiagonal, with the array TAU,
*          represent the orthogonal matrix Q as a product of elementary
*          reflectors. See Further Details.
*
*  IA      (global input) INTEGER
*          The row index in the global array A indicating the first
*          row of sub( A ).
*
*  JA      (global input) INTEGER
*          The column index in the global array A indicating the
*          first column of sub( A ).
*
*  DESCA   (global and local input) INTEGER array of dimension DLEN_.
*          The array descriptor for the distributed matrix A.
*
*  D       (local output) REAL array, dimension LOCc(JA+N-1)
*          The diagonal elements of the tridiagonal matrix T:
*          D(i) = A(i,i). D is tied to the distributed matrix A.
*
*  E       (local output) REAL array, dimension LOCc(JA+N-1)
*          if UPLO = 'U', LOCc(JA+N-2) otherwise. The off-diagonal
*          elements of the tridiagonal matrix T: E(i) = A(i,i+1) if
*          UPLO = 'U', E(i) = A(i+1,i) if UPLO = 'L'. E is tied to the
*          distributed matrix A.
*
*  TAU     (local output) REAL, array, dimension
*          LOCc(JA+N-1). This array contains the scalar factors TAU of
*          the elementary reflectors. TAU is tied to the distributed
*          matrix A.
*
*  WORK    (local workspace/local output) REAL array,
*                                                  dimension (LWORK)
*          On exit, WORK( 1 ) returns the minimal and optimal LWORK.
*
*  LWORK   (local or global input) INTEGER
*          The dimension of the array WORK.
*          LWORK is local input and must be at least
*          LWORK >= MAX( NB * ( NP +1 ), 3 * NB )
*
*          where NB = MB_A = NB_A,
*          NP = NUMROC( N, NB, MYROW, IAROW, NPROW ),
*          IAROW = INDXG2P( IA, NB, MYROW, RSRC_A, NPROW ).
*
*          INDXG2P and NUMROC are ScaLAPACK tool functions;
*          MYROW, MYCOL, NPROW and NPCOL can be determined by calling
*          the subroutine BLACS_GRIDINFO.
*
*          If LWORK = -1, then LWORK is global input and a workspace
*          query is assumed; the routine only calculates the minimum
*          and optimal size for all work arrays. Each of these
*          values is returned in the first entry of the corresponding
*          work array, and no error message is issued by PXERBLA.
*
*  INFO    (global output) INTEGER
*          = 0:  successful exit
*          < 0:  If the i-th argument is an array and the j-entry had
*                an illegal value, then INFO = -(i*100+j), if the i-th
*                argument is a scalar and had an illegal value, then
*                INFO = -i.
*
*  Further Details
*  ===============
*
*  If UPLO = 'U', the matrix Q is represented as a product of elementary
*  reflectors
*
*     Q = H(n-1) . . . H(2) H(1).
*
*  Each H(i) has the form
*
*     H(i) = I - tau * v * v'
*
*  where tau is a real scalar, and v is a real vector with
*  v(i+1:n) = 0 and v(i) = 1; v(1:i-1) is stored on exit in
*  A(ia:ia+i-2,ja+i), and tau in TAU(ja+i-1).
*
*  If UPLO = 'L', the matrix Q is represented as a product of elementary
*  reflectors
*
*     Q = H(1) H(2) . . . H(n-1).
*
*  Each H(i) has the form
*
*     H(i) = I - tau * v * v'
*
*  where tau is a real scalar, and v is a real vector with
*  v(1:i) = 0 and v(i+1) = 1; v(i+2:n) is stored on exit in
*  A(ia+i+1:ia+n-1,ja+i-1), and tau in TAU(ja+i-1).
*
*  The contents of sub( A ) on exit are illustrated by the following
*  examples with n = 5:
*
*  if UPLO = 'U':                       if UPLO = 'L':
*
*    (  d   e   v2  v3  v4 )              (  d                  )
*    (      d   e   v3  v4 )              (  e   d              )
*    (          d   e   v4 )              (  v1  e   d          )
*    (              d   e  )              (  v1  v2  e   d      )
*    (                  d  )              (  v1  v2  v3  e   d  )
*
*  where d and e denote diagonal and off-diagonal elements of T, and vi
*  denotes an element of the vector defining H(i).
*
*  Alignment requirements
*  ======================
*
*  The distributed submatrix sub( A ) must verify some alignment proper-
*  ties, namely the following expression should be true:
*  ( MB_A.EQ.NB_A .AND. IROFFA.EQ.ICOFFA .AND. IROFFA.EQ.0 ) with
*  IROFFA = MOD( IA-1, MB_A ) and ICOFFA = MOD( JA-1, NB_A ).
*
*  =====================================================================
*
*     .. Parameters ..
      INTEGER            BLOCK_CYCLIC_2D, CSRC_, CTXT_, DLEN_, DTYPE_,
     $                   lld_, mb_, m_, nb_, n_, rsrc_
      parameter( block_cyclic_2d = 1, dlen_ = 9, dtype_ = 1,
     $                     ctxt_ = 2, m_ = 3, n_ = 4, mb_ = 5, nb_ = 6,
     $                     rsrc_ = 7, csrc_ = 8, lld_ = 9 )
      REAL               ONE
      parameter( one = 1.0e+0 )
*     ..
*     .. Local Scalars ..
      LOGICAL            LQUERY, UPPER
      CHARACTER          COLCTOP, ROWCTOP
      INTEGER            I, IACOL, IAROW, ICOFFA, ICTXT, IINFO, IPW,
     $                   iroffa, j, jb, jx, k, kk, lwmin, mycol, myrow,
     $                   nb, np, npcol, nprow, nq
*     ..
*     .. Local Arrays ..
      INTEGER            DESCW( DLEN_ ), IDUM1( 2 ), IDUM2( 2 )
*     ..
*     .. External Subroutines ..
      EXTERNAL           blacs_gridinfo, chk1mat, descset, pchk1mat,
     $                   pslatrd, pssyr2k, pssytd2, pb_topget,
     $                   pb_topset, pxerbla
*     ..
*     .. External Functions ..
      LOGICAL            LSAME
      INTEGER            INDXG2L, INDXG2P, NUMROC
      EXTERNAL           lsame, indxg2l, indxg2p, numroc
*     ..
*     .. Intrinsic Functions ..
      INTRINSIC          ichar, max, min, mod, real
*     ..
*     .. Executable Statements ..
*
*     Get grid parameters
*
      ictxt = desca( ctxt_ )
      CALL blacs_gridinfo( ictxt, nprow, npcol, myrow, mycol )
*
*     Test the input parameters
*
      info = 0
      IF( nprow.EQ.-1 ) THEN
         info = -(600+ctxt_)
      ELSE
         CALL chk1mat( n, 2, n, 2, ia, ja, desca, 6, info )
         upper = lsame( uplo, 'U' )
         IF( info.EQ.0 ) THEN
            nb = desca( nb_ )
            iroffa = mod( ia-1, desca( mb_ ) )
            icoffa = mod( ja-1, desca( nb_ ) )
            iarow = indxg2p( ia, nb, myrow, desca( rsrc_ ), nprow )
            iacol = indxg2p( ja, nb, mycol, desca( csrc_ ), npcol )
            np = numroc( n, nb, myrow, iarow, nprow )
            nq = max( 1, numroc( n+ja-1, nb, mycol, desca( csrc_ ),
     $                npcol ) )
            lwmin = max( (np+1)*nb, 3*nb )
*
            work( 1 ) = real( lwmin )
            lquery = ( lwork.EQ.-1 )
            IF( .NOT.upper .AND. .NOT.lsame( uplo, 'l' ) ) THEN
               INFO = -1
.NE..OR..NE.            ELSE IF( IROFFAICOFFA  ICOFFA0 ) THEN
               INFO = -5
.NE.            ELSE IF( DESCA( MB_ )DESCA( NB_ ) ) THEN
               INFO = -(600+NB_)
.LT..AND..NOT.            ELSE IF( LWORKLWMIN  LQUERY ) THEN
               INFO = -11
            END IF
         END IF
         IF( UPPER ) THEN
            IDUM1( 1 ) = ICHAR( 'u' )
         ELSE
            IDUM1( 1 ) = ICHAR( 'l' )
         END IF
         IDUM2( 1 ) = 1
.EQ.         IF( LWORK-1 ) THEN
            IDUM1( 2 ) = -1
         ELSE
            IDUM1( 2 ) = 1
         END IF
         IDUM2( 2 ) = 11
         CALL PCHK1MAT( N, 2, N, 2, IA, JA, DESCA, 6, 2, IDUM1, IDUM2,
     $                  INFO )
      END IF
*
.NE.      IF( INFO0 ) THEN
         CALL PXERBLA( ICTXT, 'pssytrd', -INFO )
         RETURN
      ELSE IF( LQUERY ) THEN
         RETURN
      END IF
*
*     Quick return if possible
*
.EQ.      IF( N0 )
     $   RETURN
*
      CALL PB_TOPGET( ICTXT, 'combine', 'columnwise', COLCTOP )
      CALL PB_TOPGET( ICTXT, 'combine', 'rowwise',    ROWCTOP )
      CALL PB_TOPSET( ICTXT, 'combine', 'columnwise', '1-tree' )
      CALL PB_TOPSET( ICTXT, 'combine', 'rowwise',    '1-tree' )
*
      IPW = NP * NB + 1
*
      IF( UPPER ) THEN
*
*        Reduce the upper triangle of sub( A ).
*
         KK = MOD( JA+N-1, NB )
.EQ.         IF( KK0 )
     $      KK = NB
         CALL DESCSET( DESCW, N, NB, NB, NB, IAROW, INDXG2P( JA+N-KK,
     $                 NB, MYCOL, DESCA( CSRC_ ), NPCOL ), ICTXT,
     $                 MAX( 1, NP ) )
*
         DO 10 K = N-KK+1, NB+1, -NB
            JB = MIN( N-K+1, NB )
            I = IA + K - 1
            J = JA + K - 1
*
*           Reduce columns I:I+NB-1 to tridiagonal form and form
*           the matrix W which is needed to update the unreduced part of
*           the matrix
*
            CALL PSLATRD( UPLO, K+JB-1, JB, A, IA, JA, DESCA, D, E, TAU,
     $                    WORK, 1, 1, DESCW, WORK( IPW ) )
*
*           Update the unreduced submatrix A(IA:I-1,JA:J-1), using an
*           update of the form:
*           A(IA:I-1,JA:J-1) := A(IA:I-1,JA:J-1) - V*W' - W*V'
*
            CALL PSSYR2K( UPLO, 'no transpose', K-1, JB, -ONE, A, IA, J,
     $                    DESCA, WORK, 1, 1, DESCW, ONE, A, IA, JA,
     $                    DESCA )
*
*           Copy last superdiagonal element back into sub( A )
*
            JX = MIN( INDXG2L( J, NB, 0, IACOL, NPCOL ), NQ )
            CALL PSELSET( A, I-1, J, DESCA, E( JX ) )
*
            DESCW( CSRC_ ) = MOD( DESCW( CSRC_ ) + NPCOL - 1, NPCOL )
*
   10    CONTINUE
*
*        Use unblocked code to reduce the last or only block
*
         CALL PSSYTD2( UPLO, MIN( N, NB ), A, IA, JA, DESCA, D, E,
     $                 TAU, WORK, LWORK, IINFO )
*
      ELSE
*
*        Reduce the lower triangle of sub( A )
*
         KK = MOD( JA+N-1, NB )
.EQ.         IF( KK0 )
     $      KK = NB
         CALL DESCSET( DESCW, N, NB, NB, NB, IAROW, IACOL, ICTXT,
     $                 MAX( 1, NP ) )
*
         DO 20 K = 1, N-NB, NB
            I = IA + K - 1
            J = JA + K - 1
*
*           Reduce columns I:I+NB-1 to tridiagonal form and form
*           the matrix W which is needed to update the unreduced part
*           of the matrix
*
            CALL PSLATRD( UPLO, N-K+1, NB, A, I, J, DESCA, D, E, TAU,
     $                    WORK, K, 1, DESCW, WORK( IPW ) )
*
*           Update the unreduced submatrix A(I+NB:IA+N-1,I+NB:IA+N-1),
*           using an update of the form: A(I+NB:IA+N-1,I+NB:IA+N-1) :=
*           A(I+NB:IA+N-1,I+NB:IA+N-1) - V*W' - W*V'
*
            CALL PSSYR2K( UPLO, 'no transpose', N-K-NB+1, NB, -ONE, A,
     $                    I+NB, J, DESCA, WORK, K+NB, 1, DESCW, ONE, A,
     $                    I+NB, J+NB, DESCA )
*
*           Copy last subdiagonal element back into sub( A )
*
            JX = MIN( INDXG2L( J+NB-1, NB, 0, IACOL, NPCOL ), NQ )
            CALL PSELSET( A, I+NB, J+NB-1, DESCA, E( JX ) )
*
            DESCW( CSRC_ ) = MOD( DESCW( CSRC_ ) + 1, NPCOL )
*
   20    CONTINUE
*
*        Use unblocked code to reduce the last or only block
*
         CALL PSSYTD2( UPLO, KK, A, IA+K-1, JA+K-1, DESCA, D, E,
     $                 TAU, WORK, LWORK, IINFO )
      END IF
*
      CALL PB_TOPSET( ICTXT, 'combine', 'columnwise', COLCTOP )
      CALL PB_TOPSET( ICTXT, 'combine', 'rowwise',    ROWCTOP )
*
      WORK( 1 ) = REAL( LWMIN )
*
      RETURN
*
*     End of PSSYTRD
*
      END