pcgetrs.f

Go to the documentation of this file.

      SUBROUTINE pcgetrs( TRANS, N, NRHS, A, IA, JA, DESCA, IPIV, B,
     $                    IB, JB, DESCB, INFO )
*
*  -- ScaLAPACK routine (version 1.7) --
*     University of Tennessee, Knoxville, Oak Ridge National Laboratory,
*     and University of California, Berkeley.
*     May 1, 1997
*
*     .. Scalar Arguments ..
      CHARACTER          TRANS
      INTEGER            IA, IB, INFO, JA, JB, N, NRHS
*     ..
*     .. Array Arguments ..
      INTEGER            DESCA( * ), DESCB( * ), IPIV( * )
      COMPLEX            A( * ), B( * )
*     ..
*
*  Purpose
*  =======
*
*  PCGETRS solves a system of distributed linear equations
*
*                   op( sub( A ) ) * X = sub( B )
*
*  with a general N-by-N distributed matrix sub( A ) using the LU
*  factorization computed by PCGETRF.
*  sub( A ) denotes A(IA:IA+N-1,JA:JA+N-1), op( A ) = A, A**T or A**H
*  and sub( B ) denotes B(IB:IB+N-1,JB:JB+NRHS-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
*
*  This routine requires square block data decomposition ( MB_A=NB_A ).
*
*  Arguments
*  =========
*
*  TRANS   (global input) CHARACTER
*          Specifies the form of the system of equations:
*          = 'N':  sub( A )    * X = sub( B )  (No transpose)
*          = 'T':  sub( A )**T * X = sub( B )  (Transpose)
*          = 'C':  sub( A )**H * X = sub( B )  (Conjugate transpose)
*
*  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.
*
*  NRHS    (global input) INTEGER
*          The number of right hand sides, i.e., the number of columns
*          of the distributed submatrix sub( B ). NRHS >= 0.
*
*  A       (local input) COMPLEX 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 factors
*          L and U from the factorization sub( A ) = P*L*U; the unit
*          diagonal elements of L are not stored.
*
*  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.
*
*  IPIV    (local input) INTEGER array, dimension ( LOCr(M_A)+MB_A )
*          This array contains the pivoting information.
*          IPIV(i) -> The global row local row i was swapped with.
*          This array is tied to the distributed matrix A.
*
*  B       (local input/local output) COMPLEX pointer into the
*          local memory to an array of dimension
*          (LLD_B,LOCc(JB+NRHS-1)).  On entry, the right hand sides
*          sub( B ). On exit, sub( B ) is overwritten by the solution
*          distributed matrix X.
*
*  IB      (global input) INTEGER
*          The row index in the global array B indicating the first
*          row of sub( B ).
*
*  JB      (global input) INTEGER
*          The column index in the global array B indicating the
*          first column of sub( B ).
*
*  DESCB   (global and local input) INTEGER array of dimension DLEN_.
*          The array descriptor for the distributed matrix B.
*
*  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            ONE
      parameter( one = 1.0e+0 )
*     ..
*     .. Local Scalars ..
      LOGICAL            NOTRAN
      INTEGER            IAROW, IBROW, ICOFFA, ICTXT, IROFFA, IROFFB,
     $                   mycol, myrow, npcol, nprow
*     ..
*     .. Local Arrays ..
      INTEGER            DESCIP( DLEN_ ), IDUM1( 1 ), IDUM2( 1 )
*     ..
*     .. External Subroutines ..
      EXTERNAL           blacs_gridinfo, chk1mat, descset, pchk2mat,
     $                   pclapiv, pctrsm, pxerbla
*     ..
*     .. External Functions ..
      LOGICAL            LSAME
      INTEGER            INDXG2P, NUMROC
      EXTERNAL           indxg2p, lsame, numroc
*     ..
*     .. Intrinsic Functions ..
      INTRINSIC          ichar, mod
*     ..
*     .. 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
         notran = lsame( trans, 'N' )
         CALL chk1mat( n, 2, n, 2, ia, ja, desca, 7, info )
         CALL chk1mat( n, 2, nrhs, 3, ib, jb, descb, 12, info )
         IF( info.EQ.0 ) THEN
            iarow = indxg2p( ia, desca( mb_ ), myrow, desca( rsrc_ ),
     $                       nprow )
            ibrow = indxg2p( ib, descb( mb_ ), myrow, descb( rsrc_ ),
     $                       nprow )
            iroffa = mod( ia-1, desca( mb_ ) )
            icoffa = mod( ja-1, desca( nb_ ) )
            iroffb = mod( ib-1, descb( mb_ ) )
            IF( .NOT.notran .AND. .NOT.lsame( trans, 'T' ) .AND. .NOT.
     $         lsame( trans, 'C' ) ) THEN
               info = -1
            ELSE IF( iroffa.NE.0 ) THEN
               info = -5
            ELSE IF( icoffa.NE.0 ) THEN
               info = -6
            ELSE IF( desca( mb_ ).NE.desca( nb_ ) ) THEN
               info = -(700+nb_)
            ELSE IF( iroffb.NE.0 .OR. ibrow.NE.iarow ) THEN
               info = -10
            ELSE IF( descb( mb_ ).NE.desca( nb_ ) ) THEN
               info = -(1200+nb_)
            ELSE IF( ictxt.NE.descb( ctxt_ ) ) THEN
               info = -(1200+ctxt_)
            END IF
         END IF
         IF( notran ) THEN
            idum1( 1 ) = ichar( 'N' )
         ELSE IF( lsame( trans, 'T' ) ) THEN
            idum1( 1 ) = ichar( 'T' )
         ELSE
            idum1( 1 ) = ichar( 'C' )
         END IF
         idum2( 1 ) = 1
         CALL pchk2mat( n, 2, n, 2, ia, ja, desca, 7, n, 2, nrhs, 3,
     $                  ib, jb, descb, 12, 1, idum1, idum2, info )
      END IF
*
      IF( info.NE.0 ) THEN
         CALL pxerbla( ictxt, 'PCGETRS', -info )
         RETURN
      END IF
*
*     Quick return if possible
*
      IF( n.EQ.0 .OR. nrhs.EQ.0 )
     $   RETURN
*
      CALL descset( descip, desca( m_ ) + desca( mb_ )*nprow, 1,
     $              desca( mb_ ), 1, desca( rsrc_ ), mycol, ictxt,
     $              desca( mb_ ) + numroc( desca( m_ ), desca( mb_ ),
     $              myrow, desca( rsrc_ ), nprow ) )
*
      IF( notran ) THEN
*
*        Solve sub( A ) * X = sub( B ).
*
*        Apply row interchanges to the right hand sides.
*
         CALL pclapiv( 'Forward', 'Row', 'Col', n, nrhs, b, ib, jb,
     $                 descb, ipiv, ia, 1, descip, idum1 )
*
*        Solve L*X = sub( B ), overwriting sub( B ) with X.
*
         CALL pctrsm( 'Left', 'Lower', 'no transpose', 'unit', N, NRHS,
     $                ONE, A, IA, JA, DESCA, B, IB, JB, DESCB )
*
*        Solve U*X = sub( B ), overwriting sub( B ) with X.
*
         CALL PCTRSM( 'left', 'upper', 'no transpose', 'non-unit', N,
     $                NRHS, ONE, A, IA, JA, DESCA, B, IB, JB, DESCB )
      ELSE
*
*        Solve sub( A )' * X = sub( B ).
*
*        Solve U'*X = sub( B ), overwriting sub( B ) with X.
*
         CALL PCTRSM( 'left', 'upper', TRANS, 'non-unit', N, NRHS,
     $                ONE, A, IA, JA, DESCA, B, IB, JB, DESCB )
*
*        Solve L'*X = sub( B ), overwriting sub( B ) with X.
*
         CALL PCTRSM( 'left', 'lower', TRANS, 'unit', N, NRHS, ONE,
     $                A, IA, JA, DESCA, B, IB, JB, DESCB )
*
*        Apply row interchanges to the solution vectors.
*
         CALL PCLAPIV( 'backward', 'row', 'col', N, NRHS, B, IB, JB,
     $                 DESCB, IPIV, IA, 1, DESCIP, IDUM1 )
*
      END IF
*
      RETURN
*
*     End of PCGETRS
*
      END