pcpocon.f

Go to the documentation of this file.

      SUBROUTINE pcpocon( UPLO, N, A, IA, JA, DESCA, ANORM, RCOND, WORK,
     $                    LWORK, RWORK, LRWORK, 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, LRWORK, LWORK, N
      REAL               ANORM, RCOND
*     ..
*     .. Array Arguments ..
      INTEGER            DESCA( * )
      REAL               RWORK( * )
      COMPLEX            A( * ), WORK( * )
*     ..
*
*  Purpose
*  =======
*
*  PCPOCON estimates the reciprocal of the condition number (in the
*  1-norm) of a complex Hermitian positive definite distributed matrix
*  using the Cholesky factorization A = U**H*U or A = L*L**H computed by
*  PCPOTRF.
*
*  An estimate is obtained for norm(inv(A(IA:IA+N-1,JA:JA+N-1))), and
*  the reciprocal of the condition number is computed as
*             RCOND = 1 / ( norm( A(IA:IA+N-1,JA:JA+N-1)      ) *
*                           norm( inv(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 factor stored in
*          A(IA:IA+N-1,JA:JA+N-1) is upper or lower triangular.
*          = 'U':  Upper triangular
*          = 'L':  Lower triangular
*
*  N       (global input) INTEGER
*          The order of the distributed matrix A(IA:IA+N-1,JA:JA+N-1).
*          N >= 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 or U from
*          the Cholesky factorization A(IA:IA+N-1,JA:JA+N-1) = U'*U or
*          L*L', as computed by PCPOTRF.
*
*  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.
*
*  ANORM   (global input) REAL
*          The 1-norm (or infinity-norm) of the hermitian distributed
*          matrix A(IA:IA+N-1,JA:JA+N-1).
*
*  RCOND   (global output) REAL
*          The reciprocal of the condition number of the distributed
*          matrix A(IA:IA+N-1,JA:JA+N-1), computed as
*             RCOND = 1 / ( norm( A(IA:IA+N-1,JA:JA+N-1)      ) *
*                           norm( inv(A(IA:IA+N-1,JA:JA+N-1)) ) ).
*
*  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 >= 2*LOCr(N+MOD(IA-1,MB_A)) +
*          MAX( 2, MAX(NB_A*MAX(1,CEIL(P-1,Q)),LOCc(N+MOD(JA-1,NB_A)) +
*          NB_A*MAX(1,CEIL(Q-1,P))) ).
*
*          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.
*
*  RWORK   (local workspace/local output) REAL array,
*                                                  dimension (LRWORK)
*          On exit, RWORK(1) returns the minimal and optimal LRWORK.
*
*  LRWORK  (local or global input) INTEGER
*          The dimension of the array RWORK.
*          LRWORK is local input and must be at least
*          LRWORK >= 2*LOCc(N+MOD(JA-1,NB_A)).
*
*          If LRWORK = -1, then LRWORK 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 )
      REAL               ONE, ZERO
      parameter( one = 1.0e+0, zero = 0.0e+0 )
*     ..
*     .. Local Scalars ..
      LOGICAL            LQUERY, UPPER
      CHARACTER          CBTOP, COLCTOP, NORMIN, ROWCTOP
      INTEGER            IACOL, IAROW, ICOFF, ICTXT, IIA, IPNL, IPNU,
     $                   ipv, ipw, ipx, iroff, iv, ix, ixx, jja, jv,
     $                   jx, kase, lrwmin, lwmin, mycol, myrow, np,
     $                   npcol, nprow, npmod, nq, nqmod
      REAL               AINVNM, SCALE, SL, SU, SMLNUM
      COMPLEX            WMAX, ZDUM
*     ..
*     .. Local Arrays ..
      INTEGER            DESCV( DLEN_ ), DESCX( DLEN_ ), IDUM1( 3 ),
     $                   idum2( 3 )
*     ..
*     .. External Subroutines ..
      EXTERNAL           blacs_gridinfo, cgebr2d, cgebs2d, chk1mat,
     $                   descset, infog2l, pcamax, pchk1mat, pclatrs,
     $                   pclacon, pcsrscl, pb_topget, pb_topset,
     $                   pxerbla
*     ..
*     .. External Functions ..
      LOGICAL            LSAME
      INTEGER            ICEIL, INDXG2P, NUMROC
      REAL               PSLAMCH
      EXTERNAL           iceil, indxg2p, lsame, numroc, pslamch
*     ..
*     .. Intrinsic Functions ..
      INTRINSIC          abs, aimag, ichar, max, mod, real
*     ..
*     .. Statement Functions ..
      REAL               CABS1
*     ..
*     .. Statement Function definitions ..
      cabs1( zdum ) = abs( real( zdum ) ) + abs( aimag( zdum ) )
*     ..
*     .. 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 )
         IF( info.EQ.0 ) THEN
            upper = lsame( uplo, 'U' )
            iarow = indxg2p( ia, desca( mb_ ), myrow, desca( rsrc_ ),
     $                       nprow )
            iacol = indxg2p( ja, desca( nb_ ), mycol, desca( csrc_ ),
     $                       npcol )
            npmod = numroc( n + mod( ia-1, desca( mb_ ) ), desca( mb_ ),
     $                      myrow, iarow, nprow )
            nqmod = numroc( n + mod( ja-1, desca( nb_ ) ), desca( nb_ ),
     $                      mycol, iacol, npcol )
            lwmin = 2*npmod +
     $              max( 2, max( desca( nb_ )*
     $                   max( 1, iceil( nprow-1, npcol ) ), nqmod +
     $                   desca( nb_ )*
     $                   max( 1, iceil( npcol-1, nprow ) ) ) )
            work( 1 ) = real( lwmin )
            lrwmin = 2*nqmod
            rwork( 1 ) = real( lrwmin )
            lquery = ( lwork.EQ.-1 .OR. lrwork.EQ.-1 )
*
            IF( .NOT.upper .AND. .NOT.lsame( uplo, 'l' ) ) THEN
               INFO = -1
.LT.            ELSE IF( ANORMZERO ) THEN
               INFO = -7
.LT..AND..NOT.            ELSE IF( LWORKLWMIN  LQUERY ) THEN
               INFO = -10
.LT..AND..NOT.            ELSE IF( LRWORKLRWMIN  LQUERY ) THEN
               INFO = -12
            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 ) = 10
.EQ.         IF( LRWORK-1 ) THEN
            IDUM1( 3 ) = -1
         ELSE
            IDUM1( 3 ) = 1
         END IF
         IDUM2( 3 ) = 12
         CALL PCHK1MAT( N, 2, N, 2, IA, JA, DESCA, 6, 3, IDUM1, IDUM2,
     $                  INFO )
      END IF
*
.NE.      IF( INFO0 ) THEN
         CALL PXERBLA( ICTXT, 'pcpocon', -INFO )
         RETURN
      ELSE IF( LQUERY ) THEN
         RETURN
      END IF
*
*     Quick return if possible
*
      RCOND = ZERO
.EQ.      IF( N0 ) THEN
         RCOND = ONE
         RETURN
.EQ.      ELSE IF( ANORMZERO ) THEN
         RETURN
.EQ.      ELSE IF( N1 ) THEN
         RCOND = ONE
         RETURN
      END IF
*
      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' )
*
      SMLNUM = PSLAMCH( ICTXT, 'safe minimum' )
      IROFF = MOD( IA-1, DESCA( MB_ ) )
      ICOFF = MOD( JA-1, DESCA( NB_ ) )
      CALL INFOG2L( IA, JA, DESCA, NPROW, NPCOL, MYROW, MYCOL, IIA, JJA,
     $              IAROW, IACOL )
      NP = NUMROC( N+IROFF, DESCA( MB_ ), MYROW, IAROW, NPROW )
      NQ = NUMROC( N+ICOFF, DESCA( NB_ ), MYCOL, IACOL, NPCOL )
      IV = IROFF + 1
      IX = IV
      JV = ICOFF + 1
      JX = JV
*
      IPX = 1
      IPV = IPX + NP
      IPW = IPV + NP
      IPNL = 1
      IPNU = IPNL + NQ
*
      CALL DESCSET( DESCV, N+IROFF, 1, DESCA( MB_ ), 1, IAROW, MYCOL,
     $              ICTXT, MAX( 1, NP ) )
      CALL DESCSET( DESCX, N+IROFF, 1, DESCA( MB_ ), 1, IAROW, MYCOL,
     $              ICTXT, MAX( 1, NP ) )
*
*     Estimate the 1-norm (or I-norm) of inv(A).
*
      AINVNM = ZERO
      KASE   = 0
      NORMIN = 'n'
*
   10 CONTINUE
      CALL PCLACON( N, WORK( IPV ), IV, JV, DESCV, WORK( IPX ), IX, JX,
     $              DESCX, AINVNM, KASE )
.NE.      IF( KASE0 ) THEN
         IF( UPPER ) THEN
*
*           Multiply by inv(U').
*
            DESCX( CSRC_ ) = IACOL
            CALL PCLATRS( 'upper', 'conjugate transpose', 'non-unit',
     $                    NORMIN, N, A, IA, JA, DESCA, WORK( IPX ),
     $                    IX, JX, DESCX, SL, RWORK( IPNL ),
     $                    WORK( IPW ) )
            DESCX( CSRC_ ) = MYCOL
            NORMIN = 'y'
*
*           Multiply by inv(U).
*
            DESCX( CSRC_ ) = IACOL
            CALL PCLATRS( 'upper', 'no transpose', 'non-unit', NORMIN,
     $                    N, A, IA, JA, DESCA, WORK( IPX ), IX, JX,
     $                    DESCX, SU, RWORK( IPNU ), WORK( IPW ) )
            DESCX( CSRC_ ) = MYCOL
         ELSE
*
*           Multiply by inv(L).
*
            DESCX( CSRC_ ) = IACOL
            CALL PCLATRS( 'lower', 'no transpose', 'non-unit', NORMIN,
     $                    N, A, IA, JA, DESCA, WORK( IPX ), IX, JX,
     $                    DESCX, SL, RWORK( IPNL ), WORK( IPW ) )
            DESCX( CSRC_ ) = MYCOL
            NORMIN = 'y'
*
*           Multiply by inv(L').
*
            DESCX( CSRC_ ) = IACOL
            CALL PCLATRS( 'lower', 'conjugate transpose', 'non-unit',
     $                    NORMIN, N, A, IA, JA, DESCA, WORK( IPX ),
     $                    IX, JX, DESCX, SU, RWORK( IPNU ),
     $                    WORK( IPW ) )
            DESCX( CSRC_ ) = MYCOL
         END IF
*
*        Multiply by 1/SCALE if doing so will not cause overflow.
*
         SCALE = SL*SU
.NE.         IF( SCALEONE ) THEN
            CALL PCAMAX( N, WMAX, IXX, WORK( IPX ), IX, JX, DESCX, 1 )
.EQ..AND..EQ.            IF( DESCX( M_ )1  N1 ) THEN
               CALL PB_TOPGET( ICTXT, 'broadcast', 'columnwise', CBTOP )
.EQ.               IF( MYROWIAROW ) THEN
                  CALL CGEBS2D( ICTXT, 'column', CBTOP, 1, 1, WMAX, 1 )
               ELSE
                  CALL CGEBR2D( ICTXT, 'column', CBTOP, 1, 1, WMAX, 1,
     $                          IAROW, MYCOL )
               END IF
            END IF
.LT..OR..EQ.            IF( SCALECABS1( WMAX )*SMLNUM  SCALEZERO )
     $         GO TO 20
            CALL PCSRSCL( N, SCALE, WORK( IPX ), IX, JX, DESCX, 1 )
         END IF
         GO TO 10
      END IF
*
*     Compute the estimate of the reciprocal condition number.
*
.NE.      IF( AINVNMZERO )
     $   RCOND = ( ONE / AINVNM ) / ANORM
*
   20 CONTINUE
*
      CALL PB_TOPSET( ICTXT, 'combine', 'columnwise', COLCTOP )
      CALL PB_TOPSET( ICTXT, 'combine', 'Rowwise',    rowctop )
*
      RETURN
*
*     End of PCPOCON
*
      END