|
SRC\pdgebd2.f |
|
| #lines: 444 size: 17 Kb creation: 18/01/2006 23:36:04 last modification: 08/05/2008 18:37:51 attribute: ARCH Find Reload | |
1: 2: 3: 4: 5: 6: 7: 8: 9: 10: 11: 12: 13: 14: 15: 16: 17: 18: 19: 20: 21: 22: 23: 24: 25: 26: 27: 28: 29: 30: 31: 32: 33: 34: 35: 36: 37: 38: 39: 40: 41: 42: 43: 44: 45: 46: 47: 48: 49: 50: 51: 52: 53: 54: 55: 56: 57: 58: 59: 60: 61: 62: 63: 64: 65: 66: 67: 68: 69: 70: 71: 72: 73: 74: 75: 76: 77: 78: 79: 80: 81: 82: 83: 84: 85: 86: 87: 88: 89: 90: 91: 92: 93: 94: 95: 96: 97: 98: 99: 100: 101: 102: 103: 104: 105: 106: 107: 108: 109: 110: 111: 112: 113: 114: 115: 116: 117: 118: 119: 120: 121: 122: 123: 124: 125: 126: 127: 128: 129: 130: 131: 132: 133: 134: 135: 136: 137: 138: 139: 140: 141: 142: 143: 144: 145: 146: 147: 148: 149: 150: 151: 152: 153: 154: 155: 156: 157: 158: 159: 160: 161: 162: 163: 164: 165: 166: 167: 168: 169: 170: 171: 172: 173: 174: 175: 176: 177: 178: 179: 180: 181: 182: 183: 184: 185: 186: 187: 188: 189: 190: 191: 192: 193: 194: 195: 196: 197: 198: 199: 200: 201: 202: 203: 204: 205: 206: 207: 208: 209: 210: 211: 212: 213: 214: 215: 216: 217: 218: 219: 220: 221: 222: 223: 224: 225: 226: 227: 228: 229: 230: 231: 232: 233: 234: 235: 236: 237: 238: 239: 240: 241: 242: 243: 244: 245: 246: 247: 248: 249: 250: 251: 252: 253: 254: 255: 256: 257: 258: 259: 260: 261: 262: 263: 264: 265: 266: 267: 268: 269: 270: 271: 272: 273: 274: 275: 276: 277: 278: 279: 280: 281: 282: 283: 284: 285: 286: 287: 288: 289: 290: 291: 292: 293: 294: 295: 296: 297: 298: 299: 300: 301: 302: 303: 304: 305: 306: 307: 308: 309: 310: 311: 312: 313: 314: 315: 316: 317: 318: 319: 320: 321: 322: 323: 324: 325: 326: 327: 328: 329: 330: 331: 332: 333: 334: 335: 336: 337: 338: 339: 340: 341: 342: 343: 344: 345: 346: 347: 348: 349: 350: 351: 352: 353: 354: 355: 356: 357: 358: 359: 360: 361: 362: 363: 364: 365: 366: 367: 368: 369: 370: 371: 372: 373: 374: 375: 376: 377: 378: 379: 380: 381: 382: 383: 384: 385: 386: 387: 388: 389: 390: 391: 392: 393: 394: 395: 396: 397: 398: 399: 400: 401: 402: 403: 404: 405: 406: 407: 408: 409: 410: 411: 412: 413: 414: 415: 416: 417: 418: 419: 420: 421: 422: 423: 424: 425: 426: 427: 428: 429: 430: 431: 432: 433: 434: 435: 436: 437: 438: 439: 440: 441: 442: 443: 444: |
SUBROUTINE PDGEBD2( M, N, A, IA, JA, DESCA, D, E, TAUQ, TAUP,
$ WORK, LWORK, INFO )
*
* -- ScaLAPACK auxiliary routine (version 1.7) --
* University of Tennessee, Knoxville, Oak Ridge National Laboratory,
* and University of California, Berkeley.
* May 1, 1997
*
* .. Scalar Arguments ..
INTEGER IA, INFO, JA, LWORK, M, N
* ..
* .. Array Arguments ..
INTEGER DESCA( * )
DOUBLE PRECISION A( * ), D( * ), E( * ), TAUP( * ), TAUQ( * ),
$ WORK( * )
* ..
*
* Purpose
* =======
*
* PDGEBD2 reduces a real general M-by-N distributed matrix
* sub( A ) = A(IA:IA+M-1,JA:JA+N-1) to upper or lower bidiagonal
* form B by an orthogonal transformation: Q' * sub( A ) * P = B.
*
* If M >= N, B is upper bidiagonal; if M < N, B is lower bidiagonal.
*
* 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 sub( A ). 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( A ). N >= 0.
*
* A (local input/local output) DOUBLE PRECISION 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
* general distributed matrix sub( A ). On exit, if M >= N,
* the diagonal and the first superdiagonal of sub( A ) are
* overwritten with the upper bidiagonal matrix B; the elements
* below the diagonal, with the array TAUQ, represent the
* orthogonal matrix Q as a product of elementary reflectors,
* and the elements above the first superdiagonal, with the
* array TAUP, represent the orthogonal matrix P as a product
* of elementary reflectors. If M < N, the diagonal and the
* first subdiagonal are overwritten with the lower bidiagonal
* matrix B; the elements below the first subdiagonal, with the
* array TAUQ, represent the orthogonal matrix Q as a product of
* elementary reflectors, and the elements above the diagonal,
* with the array TAUP, represent the orthogonal matrix P 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) DOUBLE PRECISION array, dimension
* LOCc(JA+MIN(M,N)-1) if M >= N; LOCr(IA+MIN(M,N)-1) otherwise.
* The distributed diagonal elements of the bidiagonal matrix
* B: D(i) = A(i,i). D is tied to the distributed matrix A.
*
* E (local output) DOUBLE PRECISION array, dimension
* LOCr(IA+MIN(M,N)-1) if M >= N; LOCc(JA+MIN(M,N)-2) otherwise.
* The distributed off-diagonal elements of the bidiagonal
* distributed matrix B:
* if m >= n, E(i) = A(i,i+1) for i = 1,2,...,n-1;
* if m < n, E(i) = A(i+1,i) for i = 1,2,...,m-1.
* E is tied to the distributed matrix A.
*
* TAUQ (local output) DOUBLE PRECISION array dimension
* LOCc(JA+MIN(M,N)-1). The scalar factors of the elementary
* reflectors which represent the orthogonal matrix Q. TAUQ
* is tied to the distributed matrix A. See Further Details.
*
* TAUP (local output) DOUBLE PRECISION array, dimension
* LOCr(IA+MIN(M,N)-1). The scalar factors of the elementary
* reflectors which represent the orthogonal matrix P. TAUP
* is tied to the distributed matrix A. See Further Details.
*
* 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
* LWORK >= MAX( MpA0, NqA0 )
*
* where NB = MB_A = NB_A, IROFFA = MOD( IA-1, NB )
* IAROW = INDXG2P( IA, NB, MYROW, RSRC_A, NPROW ),
* IACOL = INDXG2P( JA, NB, MYCOL, CSRC_A, NPCOL ),
* MpA0 = NUMROC( M+IROFFA, NB, MYROW, IAROW, NPROW ),
* NqA0 = NUMROC( N+IROFFA, NB, 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 (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.
*
* Further Details
* ===============
*
* The matrices Q and P are represented as products of elementary
* reflectors:
*
* If m >= n,
*
* Q = H(1) H(2) . . . H(n) and P = G(1) G(2) . . . G(n-1)
*
* Each H(i) and G(i) has the form:
*
* H(i) = I - tauq * v * v' and G(i) = I - taup * u * u'
*
* where tauq and taup are real scalars, and v and u are real vectors;
* v(1:i-1) = 0, v(i) = 1, and v(i+1:m) is stored on exit in
* A(ia+i:ia+m-1,ja+i-1);
* u(1:i) = 0, u(i+1) = 1, and u(i+2:n) is stored on exit in
* A(ia+i-1,ja+i+1:ja+n-1);
* tauq is stored in TAUQ(ja+i-1) and taup in TAUP(ia+i-1).
*
* If m < n,
*
* Q = H(1) H(2) . . . H(m-1) and P = G(1) G(2) . . . G(m)
*
* Each H(i) and G(i) has the form:
*
* H(i) = I - tauq * v * v' and G(i) = I - taup * u * u'
*
* where tauq and taup are real scalars, and v and u are real vectors;
* v(1:i) = 0, v(i+1) = 1, and v(i+2:m) is stored on exit in
* A(ia+i+1:ia+m-1,ja+i-1);
* u(1:i-1) = 0, u(i) = 1, and u(i+1:n) is stored on exit in
* A(ia+i-1,ja+i:ja+n-1);
* tauq is stored in TAUQ(ja+i-1) and taup in TAUP(ia+i-1).
*
* The contents of sub( A ) on exit are illustrated by the following
* examples:
*
* m = 6 and n = 5 (m > n): m = 5 and n = 6 (m < n):
*
* ( d e u1 u1 u1 ) ( d u1 u1 u1 u1 u1 )
* ( v1 d e u2 u2 ) ( e d u2 u2 u2 u2 )
* ( v1 v2 d e u3 ) ( v1 e d u3 u3 u3 )
* ( v1 v2 v3 d e ) ( v1 v2 e d u4 u4 )
* ( v1 v2 v3 v4 d ) ( v1 v2 v3 e d u5 )
* ( v1 v2 v3 v4 v5 )
*
* where d and e denote diagonal and off-diagonal elements of B, vi
* denotes an element of the vector defining H(i), and ui an element of
* the vector defining G(i).
*
* Alignment requirements
* ======================
*
* The distributed submatrix sub( A ) must verify some alignment proper-
* ties, namely the following expressions should be true:
* ( MB_A.EQ.NB_A .AND. IROFFA.EQ.ICOFFA )
*
* =====================================================================
*
* .. 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 )
DOUBLE PRECISION ONE, ZERO
PARAMETER ( ONE = 1.0D+0, ZERO = 0.0D+0 )
* ..
* .. Local Scalars ..
LOGICAL LQUERY
INTEGER I, IACOL, IAROW, ICOFFA, ICTXT, II, IROFFA, J,
$ JJ, K, LWMIN, MPA0, MYCOL, MYROW, NPCOL, NPROW,
$ NQA0
DOUBLE PRECISION ALPHA
* ..
* .. Local Arrays ..
INTEGER DESCD( DLEN_ ), DESCE( DLEN_ )
* ..
* .. External Subroutines ..
EXTERNAL BLACS_ABORT, BLACS_GRIDINFO, CHK1MAT, DESCSET,
$ DGEBR2D, DGEBS2D, DLARFG, INFOG2L,
$ PDLARF, PDLARFG, PDELSET, PXERBLA
* ..
* .. External Functions ..
INTEGER INDXG2P, NUMROC
EXTERNAL INDXG2P, NUMROC
* ..
* .. Intrinsic Functions ..
INTRINSIC DBLE, MAX, MIN, MOD
* ..
* .. Executable Statements ..
*
* Test the input 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( M, 1, N, 2, IA, JA, DESCA, 6, INFO )
IF( INFO.EQ.0 ) THEN
IROFFA = MOD( IA-1, DESCA( MB_ ) )
ICOFFA = MOD( JA-1, DESCA( NB_ ) )
IAROW = INDXG2P( IA, DESCA( MB_ ), MYROW, DESCA( RSRC_ ),
$ NPROW )
IACOL = INDXG2P( JA, DESCA( NB_ ), MYCOL, DESCA( CSRC_ ),
$ NPCOL )
MPA0 = NUMROC( M+IROFFA, DESCA( MB_ ), MYROW, IAROW, NPROW )
NQA0 = NUMROC( N+ICOFFA, DESCA( NB_ ), MYCOL, IACOL, NPCOL )
LWMIN = MAX( MPA0, NQA0 )
*
WORK( 1 ) = DBLE( LWMIN )
LQUERY = ( LWORK.EQ.-1 )
IF( IROFFA.NE.ICOFFA ) THEN
INFO = -5
ELSE IF( DESCA( MB_ ).NE.DESCA( NB_ ) ) THEN
INFO = -(600+NB_)
ELSE IF( LWORK.LT.LWMIN .AND. .NOT.LQUERY ) THEN
INFO = -12
END IF
END IF
END IF
*
IF( INFO.LT.0 ) THEN
CALL PXERBLA( ICTXT, 'PDGEBD2', -INFO )
CALL BLACS_ABORT( ICTXT, 1 )
RETURN
ELSE IF( LQUERY ) THEN
RETURN
END IF
*
CALL INFOG2L( IA, JA, DESCA, NPROW, NPCOL, MYROW, MYCOL, II, JJ,
$ IAROW, IACOL )
*
IF( M.EQ.1 .AND. N.EQ.1 ) THEN
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
I = II+(JJ-1)*DESCA( LLD_ )
CALL DLARFG( 1, A( I ), A( I ), 1, TAUQ( JJ ) )
D( JJ ) = A( I )
CALL DGEBS2D( ICTXT, 'Columnwise', ' ', 1, 1, D( JJ ),
$ 1 )
CALL DGEBS2D( ICTXT, 'Columnwise', ' ', 1, 1, TAUQ( JJ ),
$ 1 )
ELSE
CALL DGEBR2D( ICTXT, 'Columnwise', ' ', 1, 1, D( JJ ),
$ 1, IAROW, IACOL )
CALL DGEBR2D( ICTXT, 'Columnwise', ' ', 1, 1, TAUQ( JJ ),
$ 1, IAROW, IACOL )
END IF
END IF
IF( MYROW.EQ.IAROW )
$ TAUP( II ) = ZERO
RETURN
END IF
*
ALPHA = ZERO
*
IF( M.GE.N ) THEN
*
* Reduce to upper bidiagonal form
*
CALL DESCSET( DESCD, 1, JA+MIN(M,N)-1, 1, DESCA( NB_ ), MYROW,
$ DESCA( CSRC_ ), DESCA( CTXT_ ), 1 )
CALL DESCSET( DESCE, IA+MIN(M,N)-1, 1, DESCA( MB_ ), 1,
$ DESCA( RSRC_ ), MYCOL, DESCA( CTXT_ ),
$ DESCA( LLD_ ) )
DO 10 K = 1, N
I = IA + K - 1
J = JA + K - 1
*
* Generate elementary reflector H(j) to annihilate
* A(ia+i:ia+m-1,j)
*
CALL PDLARFG( M-K+1, ALPHA, I, J, A, MIN( I+1, M+IA-1 ),
$ J, DESCA, 1, TAUQ )
CALL PDELSET( D, 1, J, DESCD, ALPHA )
CALL PDELSET( A, I, J, DESCA, ONE )
*
* Apply H(i) to A(i:ia+m-1,i+1:ja+n-1) from the left
*
CALL PDLARF( 'Left', M-K+1, N-K, A, I, J, DESCA, 1, TAUQ, A,
$ I, J+1, DESCA, WORK )
CALL PDELSET( A, I, J, DESCA, ALPHA )
*
IF( K.LT.N ) THEN
*
* Generate elementary reflector G(i) to annihilate
* A(i,ja+j+1:ja+n-1)
*
CALL PDLARFG( N-K, ALPHA, I, J+1, A, I,
$ MIN( J+2, JA+N-1 ), DESCA, DESCA( M_ ),
$ TAUP )
CALL PDELSET( E, I, 1, DESCE, ALPHA )
CALL PDELSET( A, I, J+1, DESCA, ONE )
*
* Apply G(i) to A(i+1:ia+m-1,i+1:ja+n-1) from the right
*
CALL PDLARF( 'Right', M-K, N-K, A, I, J+1, DESCA,
$ DESCA( M_ ), TAUP, A, I+1, J+1, DESCA,
$ WORK )
CALL PDELSET( A, I, J+1, DESCA, ALPHA )
ELSE
CALL PDELSET( TAUP, I, 1, DESCE, ZERO )
END IF
10 CONTINUE
*
ELSE
*
* Reduce to lower bidiagonal form
*
CALL DESCSET( DESCD, IA+MIN(M,N)-1, 1, DESCA( MB_ ), 1,
$ DESCA( RSRC_ ), MYCOL, DESCA( CTXT_ ),
$ DESCA( LLD_ ) )
CALL DESCSET( DESCE, 1, JA+MIN(M,N)-1, 1, DESCA( NB_ ), MYROW,
$ DESCA( CSRC_ ), DESCA( CTXT_ ), 1 )
DO 20 K = 1, M
I = IA + K - 1
J = JA + K - 1
*
* Generate elementary reflector G(i) to annihilate
* A(i,ja+j:ja+n-1)
*
CALL PDLARFG( N-K+1, ALPHA, I, J, A, I,
$ MIN( J+1, JA+N-1 ), DESCA, DESCA( M_ ), TAUP )
CALL PDELSET( D, I, 1, DESCD, ALPHA )
CALL PDELSET( A, I, J, DESCA, ONE )
*
* Apply G(i) to A(i:ia+m-1,j:ja+n-1) from the right
*
CALL PDLARF( 'Right', M-K, N-K+1, A, I, J, DESCA,
$ DESCA( M_ ), TAUP, A, MIN( I+1, IA+M-1 ), J,
$ DESCA, WORK )
CALL PDELSET( A, I, J, DESCA, ALPHA )
*
IF( K.LT.M ) THEN
*
* Generate elementary reflector H(i) to annihilate
* A(i+2:ia+m-1,j)
*
CALL PDLARFG( M-K, ALPHA, I+1, J, A,
$ MIN( I+2, IA+M-1 ), J, DESCA, 1, TAUQ )
CALL PDELSET( E, 1, J, DESCE, ALPHA )
CALL PDELSET( A, I+1, J, DESCA, ONE )
*
* Apply H(i) to A(i+1:ia+m-1,j+1:ja+n-1) from the left
*
CALL PDLARF( 'Left', M-K, N-K, A, I+1, J, DESCA, 1, TAUQ,
$ A, I+1, J+1, DESCA, WORK )
CALL PDELSET( A, I+1, J, DESCA, ALPHA )
ELSE
CALL PDELSET( TAUQ, 1, J, DESCE, ZERO )
END IF
20 CONTINUE
END IF
*
WORK( 1 ) = DBLE( LWMIN )
*
RETURN
*
* End of PDGEBD2
*
END
|