Routine: PDORMR3()  File: SRC\pdormr3.f

 
 
# lines: 390
  # code: 390
  # comment: 0
  # blank:0
# Variables:59
# Callers:1
# Callings:1
# Words:192
# Keywords:130
 

 

..
     .. Array Arguments ..
     ..
  Purpose
  =======
  PDORMR3 overwrites the general real M-by-N distributed matrix
  sub( C ) = C(IC:IC+M-1,JC:JC+N-1) with
                       SIDE = 'L'          SIDE = 'R'
  TRANS = 'N':      Q * sub( C )         sub(  C ) * Q
  TRANS = 'T':      Q**T * sub( C )      sub( C ) * Q**T
  where Q is a real orthogonal distributed matrix defined as the
  product of K elementary reflectors
        Q = H(1) H(2) . . . H(k)
  as returned by PDTZRZF. Q is of order M if SIDE = 'L' and of order N
  if SIDE = 'R'.
  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
  =========
  SIDE    (global input) CHARACTER
          = 'L': apply Q or Q**T from the Left;
          = 'R': apply Q or Q**T from the Right.
  TRANS   (global input) CHARACTER
          = 'N':  No transpose, apply Q;
          = 'T':  Transpose, apply Q**T.
  M       (global input) INTEGER
          The number of rows to be operated on i.e the number of rows
          of the distributed submatrix sub( C ). M >= 0.
  N       (global input) INTEGER
          The number of columns to be operated on i.e the number of
          columns of the distributed submatrix sub( C ). N >= 0.
  K       (global input) INTEGER
          The number of elementary reflectors whose product defines the
          matrix Q.  If SIDE = 'L', M >= K >= 0, if SIDE = 'R',
          N >= K >= 0.
  L       (global input) INTEGER
          The columns of the distributed submatrix sub( A ) containing
          the meaningful part of the Householder reflectors.
          If SIDE = 'L', M >= L >= 0, if SIDE = 'R', N >= L >= 0.
  A       (local input) DOUBLE PRECISION pointer into the local memory
          to an array of dimension (LLD_A,LOCc(JA+M-1)) if SIDE='L',
          and (LLD_A,LOCc(JA+N-1)) if SIDE='R', where
          LLD_A >= MAX(1,LOCr(IA+K-1)); On entry, the i-th row must
          contain the vector which defines the elementary reflector
          H(i), IA <= i <= IA+K-1, as returned by PDTZRZF in the
          K rows of its distributed matrix argument A(IA:IA+K-1,JA:*).
          A(IA:IA+K-1,JA:*) is modified by the routine but restored on
          exit.
  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) DOUBLE PRECISION array, dimension LOCc(IA+K-1).
          This array contains the scalar factors TAU(i) of the
          elementary reflectors H(i) as returned by PDTZRZF.
          TAU is tied to the distributed matrix A.
  C       (local input/local output) DOUBLE PRECISION pointer into the
          local memory to an array of dimension (LLD_C,LOCc(JC+N-1)).
          On entry, the local pieces of the distributed matrix sub(C).
          On exit, sub( C ) is overwritten by Q*sub( C ) or Q'*sub( C )
          or sub( C )*Q' or sub( C )*Q.
  IC      (global input) INTEGER
          The row index in the global array C indicating the first
          row of sub( C ).
  JC      (global input) INTEGER
          The column index in the global array C indicating the
          first column of sub( C ).
  DESCC   (global and local input) INTEGER array of dimension DLEN_.
          The array descriptor for the distributed matrix C.
  WORK    (local workspace/local output) DOUBLE PRECISION 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
          If SIDE = 'L', LWORK >= MpC0 + MAX( MAX( 1, NqC0 ), NUMROC(
                  NUMROC( M+IROFFC,MB_A,0,0,NPROW ),MB_A,0,0,LCMP ) );
          if SIDE = 'R', LWORK >= NqC0 + MAX( 1, MpC0 );
          where LCMP = LCM / NPROW with LCM = ICLM( NPROW, NPCOL ),
          IROFFC = MOD( IC-1, MB_C ), ICOFFC = MOD( JC-1, NB_C ),
          ICROW = INDXG2P( IC, MB_C, MYROW, RSRC_C, NPROW ),
          ICCOL = INDXG2P( JC, NB_C, MYCOL, CSRC_C, NPCOL ),
          MpC0 = NUMROC( M+IROFFC, MB_C, MYROW, ICROW, NPROW ),
          NqC0 = NUMROC( N+ICOFFC, NB_C, MYCOL, ICCOL, NPCOL ),
          ILCM, 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    (local 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.
  Alignment requirements
  ======================
  The distributed submatrices A(IA:*, JA:*) and C(IC:IC+M-1,JC:JC+N-1)
  must verify some alignment properties, namely the following
  expressions should be true:
  If SIDE = 'L',
    ( NB_A.EQ.MB_C .AND. ICOFFA.EQ.IROFFC )
  If SIDE = 'R',
    ( NB_A.EQ.NB_C .AND. ICOFFA.EQ.ICOFFC .AND. IACOL.EQ.ICCOL )
  =====================================================================
     .. Parameters ..

 
Display dynamic version Find AutoScroll Reload FontSize: - + Hide Comments Hide Blanks Frame FullScreen MailPrint

 
001        SUBROUTINE PDORMR3( SIDE , TRANS , M , N , K , L , A , IA , JA , DESCA ,
002       $TAU , C , IC , JC , DESCC , WORK , LWORK , INFO )
003  
004  *     -- ScaLAPACK routine(version 1.7) --
005  *     University of Tennessee , Knoxville , Oak Ridge National Laboratory ,
006  *     and University of California , Berkeley.
007  *     May 25 , 2001
008  
009  *     .. Scalar Arguments ..
010        CHARACTER SIDE , TRANS
011        INTEGER IA , IC , INFO , JA , JC , K , L , LWORK , M , N
012        INTEGER BLOCK_CYCLIC_2D , CSRC_ , CTXT_ , DLEN_ , DTYPE_ ,
013       $LLD_ , MB_ , M_ , NB_ , N_ , RSRC_
014        PARAMETER( BLOCK_CYCLIC_2D = 1 , DLEN_ = 9 , DTYPE_ = 1 ,
015       $CTXT_ = 2 , M_ = 3 , N_ = 4 , MB_ = 5 , NB_ = 6 ,
016       $RSRC_ = 7 , CSRC_ = 8 , LLD_ = 9 )
017  *     ..
018  *     .. Local Scalars ..
019        LOGICAL LEFT , LQUERY , NOTRAN
020        CHARACTER COLBTOP , ROWBTOP
021        INTEGER I , I1 , I2 , I3 , IACOL , ICC , ICCOL , ICOFFA ,
022       $ICOFFC , ICROW , ICTXT , IROFFC , JAA , JCC , LCM ,
023       $LCMP , LWMIN , MI , MPC0 , MYCOL , MYROW , NI , NPCOL ,
024       $NPROW , NQ , NQC0
025  *     ..
026  *     .. External Subroutines ..
027        EXTERNAL BLACS_ABORT , BLACS_GRIDINFO , CHK1MAT , PDLARZ ,
028       $PB_TOPGET , PB_TOPSET , PXERBLA
029  *     ..
030  *     .. External Functions ..
031        LOGICAL LSAME
032        INTEGER ILCM , INDXG2P , NUMROC
033        EXTERNAL ILCM , INDXG2P , LSAME , NUMROC
034  *     ..
035  *     .. Intrinsic Functions ..
036        INTRINSIC DBLE , MAX , MOD
037  *     ..
038  *     .. Executable Statements ..
039  
040  *     Get grid parameters
041  
042        ICTXT = DESCA( CTXT_ )
043        CALL BLACS_GRIDINFO( ICTXT , NPROW , NPCOL , MYROW , MYCOL )
044  
045  *     Test the input parameters
046  
047        INFO = 0
048        IF( NPROW.EQ. - 1 ) THEN
049            INFO = - (900 + CTXT_)
050        ELSE
051            LEFT = LSAME( SIDE , 'L' )
052            NOTRAN = LSAME( TRANS , 'N' )
053  
054  *         NQ is the order of Q
055  
056            IF( LEFT ) THEN
057                NQ = M
058                CALL CHK1MAT( K , 5 , M , 3 , IA , JA , DESCA , 10 , INFO )
059            ELSE
060                NQ = N
061                CALL CHK1MAT( K , 5 , N , 4 , IA , JA , DESCA , 10 , INFO )
062            END IF
063            CALL CHK1MAT( M , 3 , N , 4 , IC , JC , DESCC , 15 , INFO )
064            IF( INFO.EQ.0 ) THEN
065                ICOFFA = MOD( JA - 1 , DESCA( NB_ ) )
066                IROFFC = MOD( IC - 1 , DESCC( MB_ ) )
067                ICOFFC = MOD( JC - 1 , DESCC( NB_ ) )
068                IACOL = INDXG2P( JA , DESCA( NB_ ) , MYCOL , DESCA( CSRC_ ) ,
069       $        NPCOL )
070                ICROW = INDXG2P( IC , DESCC( MB_ ) , MYROW , DESCC( RSRC_ ) ,
071       $        NPROW )
072                ICCOL = INDXG2P( JC , DESCC( NB_ ) , MYCOL , DESCC( CSRC_ ) ,
073       $        NPCOL )
074                MPC0 = NUMROC( M + IROFFC , DESCC( MB_ ) , MYROW , ICROW , NPROW )
075                NQC0 = NUMROC( N + ICOFFC , DESCC( NB_ ) , MYCOL , ICCOL , NPCOL )
076  
077                IF( LEFT ) THEN
078                    LCM = ILCM( NPROW , NPCOL )
079                    LCMP = LCM / NPROW
080                    LWMIN = MPC0 + MAX( MAX( 1 , NQC0 ) , NUMROC( NUMROC(
081       $            M + IROFFC , DESCA( MB_ ) , 0 , 0 , NPROW ) ,
082       $            DESCA( MB_ ) , 0 , 0 , LCMP ) )
083                ELSE
084                    LWMIN = NQC0 + MAX( 1 , MPC0 )
085                END IF
086  
087                WORK( 1 ) = DBLE( LWMIN )
088                LQUERY =( LWORK.EQ. - 1 )
089                IF( .NOT.LEFT .AND. .NOT.LSAME( SIDE , 'R' ) ) THEN
090                    INFO = - 1
091                ELSE IF( .NOT.NOTRAN .AND. .NOT.LSAME( TRANS , 'T' ) ) THEN
092                    INFO = - 2
093                ELSE IF( K.LT.0 .OR. K.GT.NQ ) THEN
094                    INFO = - 5
095                ELSE IF( L.LT.0 .OR. L.GT.NQ ) THEN
096                    INFO = - 6
097                ELSE IF( LEFT .AND. DESCA( NB_ ).NE.DESCC( MB_ ) ) THEN
098                    INFO = - (1000 + NB_)
099                ELSE IF( LEFT .AND. ICOFFA.NE.IROFFC ) THEN
100                    INFO = - 13
101                ELSE IF( .NOT.LEFT .AND. ICOFFA.NE.ICOFFC ) THEN
102                    INFO = - 14
103                ELSE IF( .NOT.LEFT .AND. IACOL.NE.ICCOL ) THEN
104                    INFO = - 14
105                ELSE IF( .NOT.LEFT .AND. DESCA( NB_ ).NE.DESCC( NB_ ) ) THEN
106                    INFO = - (1500 + NB_)
107                ELSE IF( ICTXT.NE.DESCC( CTXT_ ) ) THEN
108                    INFO = - (1500 + CTXT_)
109                ELSE IF( LWORK.LT.LWMIN .AND. .NOT.LQUERY ) THEN
110                    INFO = - 17
111                END IF
112            END IF
113        END IF
114  
115        IF( INFO.NE.0 ) THEN
116            CALL PXERBLA( ICTXT , 'PDORMR3' , - INFO )
117            CALL BLACS_ABORT( ICTXT , 1 )
118            RETURN
119        ELSE IF( LQUERY ) THEN
120            RETURN
121        END IF
122  
123  *     Quick return if possible
124  
125        IF( M.EQ.0 .OR. N.EQ.0 .OR. K.EQ.0 )
126       $    RETURN
127  
128            CALL PB_TOPGET( ICTXT , 'Broadcast' , 'Rowwise' , ROWBTOP )
129            CALL PB_TOPGET( ICTXT , 'Broadcast' , 'Columnwise' , COLBTOP )
130  
131            IF(( LEFT .AND. .NOT.NOTRAN .OR. .NOT.LEFT .AND. NOTRAN ) ) THEN
132                I1 = IA
133                I2 = IA + K - 1
134                I3 = 1
135            ELSE
136                I1 = IA + K - 1
137                I2 = IA
138                I3 = - 1
139            END IF
140  
141            IF( LEFT ) THEN
142                NI = N
143                JCC = JC
144                JAA = JA + M - L
145            ELSE
146                MI = M
147                ICC = IC
148                JAA = JA + N - L
149                CALL PB_TOPSET( ICTXT , 'Broadcast' , 'Rowwise' , ' ' )
150                IF( NOTRAN ) THEN
151                    CALL PB_TOPSET( ICTXT , 'Broadcast' , 'Columnwise' , 'I - ring' )
152                ELSE
153                    CALL PB_TOPSET( ICTXT , 'Broadcast' , 'Columnwise' , 'D - ring' )
154                END IF
155            END IF
156  
157            DO 10 I = I1 , I2 , I3
158                IF( LEFT ) THEN
159  
160  *                 H(i) or H(i)' is applied to C(ic + i - ia : icc + m - 1 , jc : jc + n - 1)
161  
162                    MI = M - I + IA
163                    ICC = IC + I - IA
164                ELSE
165  
166  *                 H(i) or H(i)' is applied to C(ic : ic + m - 1 , jc + i - ia : jc + n - 1)
167  
168                    NI = N - I + IA
169                    JCC = JC + I - IA
170                END IF
171  
172  *             Apply H(i) or H(i)'
173  
174                CALL PDLARZ ( SIDE , MI , NI , L , A , I , JAA , DESCA , DESCA( M_ ) ,
175       $        TAU , C , ICC , JCC , DESCC , WORK )
176  
177     10     CONTINUE
178  
179            CALL PB_TOPSET( ICTXT , 'Broadcast' , 'Rowwise' , ROWBTOP )
180            CALL PB_TOPSET( ICTXT , 'Broadcast' , 'Columnwise' , COLBTOP )
181  
182            WORK( 1 ) = DBLE( LWMIN )
183  
184            RETURN
185  
186  *         End of PDORMR3
187  
188        END