pcungqr.f

Go to the documentation of this file.

      SUBROUTINE pcungqr( M, N, K, A, IA, JA, DESCA, 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 ..
      INTEGER            IA, INFO, JA, K, LWORK, M, N
*     ..
*     .. Array Arguments ..
      INTEGER            DESCA( * )
      COMPLEX            A( * ), TAU( * ), WORK( * )
*     ..
*
*  Purpose
*  =======
*
*  PCUNGQR generates an M-by-N complex distributed matrix Q denoting
*  A(IA:IA+M-1,JA:JA+N-1) with orthonormal columns, which is defined as
*  the first N columns of a product of K elementary reflectors of order
*  M
*
*        Q  =  H(1) H(2) . . . H(k)
*
*  as returned by PCGEQRF.
*
*  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
*  =========
*
*  M       (global input) INTEGER
*          The number of rows to be operated on i.e the number of rows
*          of the distributed submatrix Q. M >= 0.
*
*  N       (global input) INTEGER
*          The number of columns to be operated on i.e the number of
*          columns of the distributed submatrix Q. M >= N >= 0.
*
*  K       (global input) INTEGER
*          The number of elementary reflectors whose product defines the
*          matrix Q. N >= K >= 0.
*
*  A       (local input/local output) COMPLEX pointer into the
*          local memory to an array of dimension (LLD_A,LOCc(JA+N-1)).
*          On entry, the j-th column must contain the vector which
*          defines the elementary reflector H(j), JA <= j <= JA+K-1, as
*          returned by PCGEQRF in the K columns of its distributed
*          matrix argument A(IA:*,JA:JA+K-1). On exit, this array
*          contains the local pieces of the M-by-N distributed matrix Q.
*
*  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.
*
*  TAU     (local input) COMPLEX, array, dimension LOCc(JA+K-1)
*          This array contains the scalar factors TAU(j) of the
*          elementary reflectors H(j) as returned by PCGEQRF.
*          TAU is tied to the distributed matrix A.
*
*  WORK    (local workspace/local output) COMPLEX 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 >= NB_A * ( NqA0 + MpA0 + NB_A ), where
*
*          IROFFA = MOD( IA-1, MB_A ), ICOFFA = MOD( JA-1, NB_A ),
*          IAROW = INDXG2P( IA, MB_A, MYROW, RSRC_A, NPROW ),
*          IACOL = INDXG2P( JA, NB_A, MYCOL, CSRC_A, NPCOL ),
*          MpA0 = NUMROC( M+IROFFA, MB_A, MYROW, IAROW, NPROW ),
*          NqA0 = NUMROC( N+ICOFFA, NB_A, MYCOL, IACOL, NPCOL ),
*
*          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.
*
*  =====================================================================
*
*     .. 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 )
      COMPLEX            ZERO
      parameter( zero = ( 0.0e+0, 0.0e+0 ) )
*     ..
*     .. Local Scalars ..
      LOGICAL            LQUERY
      CHARACTER          COLBTOP, ROWBTOP
      INTEGER            I, IACOL, IAROW, ICTXT, IINFO, IPW, J, JB, JL,
     $                   jn, lwmin, mpa0, mycol, myrow, npcol, nprow,
     $                   nqa0
*     ..
*     .. Local Arrays ..
      INTEGER            IDUM1( 2 ), IDUM2( 2 )
*     ..
*     .. External Subroutines ..
      EXTERNAL           blacs_gridinfo, chk1mat, pchk1mat, pclarfb,
     $                   pclarft, pclaset, pcung2r, pb_topget,
     $                   pb_topset, pxerbla
*     ..
*     .. External Functions ..
      INTEGER            ICEIL, INDXG2P, NUMROC
      EXTERNAL           iceil, indxg2p, numroc
*     ..
*     .. Intrinsic Functions ..
      INTRINSIC          cmplx, 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 = -(700+ctxt_)
      ELSE
         CALL chk1mat( m, 1, n, 2, ia, ja, desca, 7, info )
         IF( info.EQ.0 ) THEN
            iarow = indxg2p( ia, desca( mb_ ), myrow, desca( rsrc_ ),
     $                       nprow )
            iacol = indxg2p( ja, desca( nb_ ), mycol, desca( csrc_ ),
     $                       npcol )
            mpa0 = numroc( m+mod( ia-1, desca( mb_ ) ), desca( mb_ ),
     $                     myrow, iarow, nprow )
            nqa0 = numroc( n+mod( ja-1, desca( nb_ ) ), desca( nb_ ),
     $                     mycol, iacol, npcol )
            lwmin = desca( nb_ ) * ( mpa0 + nqa0 + desca( nb_ ) )
*
            work( 1 ) = cmplx( real( lwmin ) )
            lquery = ( lwork.EQ.-1 )
            IF( n.GT.m ) THEN
               info = -2
            ELSE IF( k.LT.0 .OR. k.GT.n ) THEN
               info = -3
            ELSE IF( lwork.LT.lwmin .AND. .NOT.lquery ) THEN
               info = -10
            END IF
         END IF
         idum1( 1 ) = k
         idum2( 1 ) = 3
         IF( lwork.EQ.-1 ) THEN
            idum1( 2 ) = -1
         ELSE
            idum1( 2 ) = 1
         END IF
         idum2( 2 ) = 10
         CALL pchk1mat( m, 1, n, 2, ia, ja, desca, 7, 2, idum1, idum2,
     $                  info )
      END IF
*
      IF( info.NE.0 ) THEN
         CALL pxerbla( ictxt, 'PCUNGQR', -info )
         RETURN
      ELSE IF( lquery ) THEN
         RETURN
      END IF
*
*     Quick return if possible
*
      IF( n.LE.0 )
     $   RETURN
*
      ipw = desca( nb_ )*desca( nb_ ) + 1
      jn = min( iceil( ja, desca( nb_ ) ) * desca( nb_ ), ja+k-1 )
      jl = max( ( (ja+k-2) / desca( nb_ ) ) * desca( nb_ ) + 1, ja )
      CALL pb_topget( ictxt, 'Broadcast', 'Rowwise', rowbtop )
      CALL pb_topget( ictxt, 'Broadcast', 'Columnwise', colbtop )
      CALL pb_topset( ictxt, 'Broadcast', 'Rowwise', 'd-ring' )
      CALL PB_TOPSET( ICTXT, 'broadcast', 'columnwise', ' ' )
*
      CALL PCLASET( 'all', JL-JA, JA+N-JL, ZERO, ZERO, A, IA, JL,
     $              DESCA )
*
*     Use unblocked code for the last or only block.
*
      CALL PCUNG2R( M-JL+JA, JA+N-JL, JA+K-JL, A, IA+JL-JA, JL, DESCA,
     $              TAU, WORK, LWORK, IINFO )
*
*     Is there at least one block of columns to loop over ?
*
.GT.      IF( JLJN+1 ) THEN
*
*        Use blocked code
*
         DO 10 J = JL-DESCA( NB_ ), JN+1, -DESCA( NB_ )
            JB = MIN( DESCA( NB_ ), JA+N-J )
            I = IA + J - JA
*
.LE.            IF( J+JBJA+N-1 ) THEN
*
*              Form the triangular factor of the block reflector
*              H = H(j) H(j+1) . . . H(j+jb-1)
*
               CALL PCLARFT( 'forward', 'columnwise', M-I+IA, JB, A, I,
     $                       J, DESCA, TAU, WORK, WORK( IPW ) )
*
*              Apply H to A(i:ia+m-1,j+jb:ja+n-1) from the left
*
               CALL PCLARFB( 'left', 'no transpose', 'forward',
     $                       'Columnwise', m-i+ia, n-j-jb+ja, jb, a, i,
     $                       j, desca, work, a, i, j+jb, desca,
     $                       work( ipw ) )
            END IF
*
*           Apply H to rows i:ia+m-1 of current block
*
            CALL pcung2r( m-i+ia, jb, jb, a, i, j, desca, tau, work,
     $                    lwork, iinfo )
*
*           Set rows ia:i-1 of current block to zero
*
            CALL pclaset( 'All', i-ia, jb, zero, zero, a, ia, j, desca )
*
   10    CONTINUE
*
      END IF
*
*     Handle first block separately
*
      IF( jl.GT.ja ) THEN
*
         jb = jn - ja + 1
*
*        Form the triangular factor of the block reflector
*        H = H(j) H(j+1) . . . H(j+jb-1)
*
         CALL pclarft( 'Forward', 'Columnwise', m, jb, a, ia, ja, desca,
     $                 tau, work, work( ipw ) )
*
*        Apply H to A(ia:ia+m-1,ja+jb:ja+n-1) from the left
*
         CALL pclarfb( 'Left', 'No transpose', 'Forward', 'Columnwise',
     $                 m, n-jb, jb, a, ia, ja, desca, work, a, ia,
     $                 ja+jb, desca, work( ipw ) )
*
*        Apply H to rows ia:ia+m-1 of current block
*
         CALL pcung2r( m, jb, jb, a, ia, ja, desca, tau, work, lwork,
     $                 iinfo )
*
      END IF
*
      CALL pb_topget( ictxt, 'Broadcast', 'Rowwise', rowbtop )
      CALL pb_topget( ictxt, 'Broadcast', 'Columnwise', colbtop )
*
      work( 1 ) = cmplx( real( lwmin ) )
*
      RETURN
*
*     End of PCUNGQR
*
      END