|
SRC\pdlantr.f |
|
| #lines: 1030 size: 36 Kb creation: 18/01/2006 23:36:04 last modification: 08/05/2008 18:37:54 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: 445: 446: 447: 448: 449: 450: 451: 452: 453: 454: 455: 456: 457: 458: 459: 460: 461: 462: 463: 464: 465: 466: 467: 468: 469: 470: 471: 472: 473: 474: 475: 476: 477: 478: 479: 480: 481: 482: 483: 484: 485: 486: 487: 488: 489: 490: 491: 492: 493: 494: 495: 496: 497: 498: 499: 500: 501: 502: 503: 504: 505: 506: 507: 508: 509: 510: 511: 512: 513: 514: 515: 516: 517: 518: 519: 520: 521: 522: 523: 524: 525: 526: 527: 528: 529: 530: 531: 532: 533: 534: 535: 536: 537: 538: 539: 540: 541: 542: 543: 544: 545: 546: 547: 548: 549: 550: 551: 552: 553: 554: 555: 556: 557: 558: 559: 560: 561: 562: 563: 564: 565: 566: 567: 568: 569: 570: 571: 572: 573: 574: 575: 576: 577: 578: 579: 580: 581: 582: 583: 584: 585: 586: 587: 588: 589: 590: 591: 592: 593: 594: 595: 596: 597: 598: 599: 600: 601: 602: 603: 604: 605: 606: 607: 608: 609: 610: 611: 612: 613: 614: 615: 616: 617: 618: 619: 620: 621: 622: 623: 624: 625: 626: 627: 628: 629: 630: 631: 632: 633: 634: 635: 636: 637: 638: 639: 640: 641: 642: 643: 644: 645: 646: 647: 648: 649: 650: 651: 652: 653: 654: 655: 656: 657: 658: 659: 660: 661: 662: 663: 664: 665: 666: 667: 668: 669: 670: 671: 672: 673: 674: 675: 676: 677: 678: 679: 680: 681: 682: 683: 684: 685: 686: 687: 688: 689: 690: 691: 692: 693: 694: 695: 696: 697: 698: 699: 700: 701: 702: 703: 704: 705: 706: 707: 708: 709: 710: 711: 712: 713: 714: 715: 716: 717: 718: 719: 720: 721: 722: 723: 724: 725: 726: 727: 728: 729: 730: 731: 732: 733: 734: 735: 736: 737: 738: 739: 740: 741: 742: 743: 744: 745: 746: 747: 748: 749: 750: 751: 752: 753: 754: 755: 756: 757: 758: 759: 760: 761: 762: 763: 764: 765: 766: 767: 768: 769: 770: 771: 772: 773: 774: 775: 776: 777: 778: 779: 780: 781: 782: 783: 784: 785: 786: 787: 788: 789: 790: 791: 792: 793: 794: 795: 796: 797: 798: 799: 800: 801: 802: 803: 804: 805: 806: 807: 808: 809: 810: 811: 812: 813: 814: 815: 816: 817: 818: 819: 820: 821: 822: 823: 824: 825: 826: 827: 828: 829: 830: 831: 832: 833: 834: 835: 836: 837: 838: 839: 840: 841: 842: 843: 844: 845: 846: 847: 848: 849: 850: 851: 852: 853: 854: 855: 856: 857: 858: 859: 860: 861: 862: 863: 864: 865: 866: 867: 868: 869: 870: 871: 872: 873: 874: 875: 876: 877: 878: 879: 880: 881: 882: 883: 884: 885: 886: 887: 888: 889: 890: 891: 892: 893: 894: 895: 896: 897: 898: 899: 900: 901: 902: 903: 904: 905: 906: 907: 908: 909: 910: 911: 912: 913: 914: 915: 916: 917: 918: 919: 920: 921: 922: 923: 924: 925: 926: 927: 928: 929: 930: 931: 932: 933: 934: 935: 936: 937: 938: 939: 940: 941: 942: 943: 944: 945: 946: 947: 948: 949: 950: 951: 952: 953: 954: 955: 956: 957: 958: 959: 960: 961: 962: 963: 964: 965: 966: 967: 968: 969: 970: 971: 972: 973: 974: 975: 976: 977: 978: 979: 980: 981: 982: 983: 984: 985: 986: 987: 988: 989: 990: 991: 992: 993: 994: 995: 996: 997: 998: 999: 1000: 1001: 1002: 1003: 1004: 1005: 1006: 1007: 1008: 1009: 1010: 1011: 1012: 1013: 1014: 1015: 1016: 1017: 1018: 1019: 1020: 1021: 1022: 1023: 1024: 1025: 1026: 1027: 1028: 1029: 1030: |
DOUBLE PRECISION FUNCTION PDLANTR( NORM, UPLO, DIAG, M, N, A,
$ IA, JA, DESCA, WORK )
*
* -- ScaLAPACK auxiliary routine (version 1.7) --
* University of Tennessee, Knoxville, Oak Ridge National Laboratory,
* and University of California, Berkeley.
* May 1, 1997
*
* .. Scalar Arguments ..
CHARACTER DIAG, NORM, UPLO
INTEGER IA, JA, M, N
* ..
* .. Array Arguments ..
INTEGER DESCA( * )
DOUBLE PRECISION A( * ), WORK( * )
* ..
*
* Purpose
* =======
*
* PDLANTR returns the value of the one norm, or the Frobenius norm,
* or the infinity norm, or the element of largest absolute value of a
* trapezoidal or triangular distributed matrix sub( A ) denoting
* A(IA:IA+M-1, JA:JA+N-1).
*
* PDLANTR returns the value
*
* ( max(abs(A(i,j))), NORM = 'M' or 'm' with ia <= i <= ia+m-1,
* ( and ja <= j <= ja+n-1,
* (
* ( norm1( sub( A ) ), NORM = '1', 'O' or 'o'
* (
* ( normI( sub( A ) ), NORM = 'I' or 'i'
* (
* ( normF( sub( A ) ), NORM = 'F', 'f', 'E' or 'e'
*
* where norm1 denotes the one norm of a matrix (maximum column sum),
* normI denotes the infinity norm of a matrix (maximum row sum) and
* normF denotes the Frobenius norm of a matrix (square root of sum of
* squares). Note that max(abs(A(i,j))) is not a matrix norm.
*
* 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
* =========
*
* NORM (global input) CHARACTER
* Specifies the value to be returned in PDLANTR as described
* above.
*
* UPLO (global input) CHARACTER
* Specifies whether the matrix sub( A ) is upper or lower
* trapezoidal.
* = 'U': Upper trapezoidal
* = 'L': Lower trapezoidal
* Note that sub( A ) is triangular instead of trapezoidal
* if M = N.
*
* DIAG (global input) CHARACTER
* Specifies whether or not the distributed matrix sub( A ) has
* unit diagonal.
* = 'N': Non-unit diagonal
* = 'U': Unit diagonal
*
* M (global input) INTEGER
* The number of rows to be operated on i.e the number of rows
* of the distributed submatrix sub( A ). When M = 0, PDLANTR is
* set to zero. 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 ). When N = 0,
* PDLANTR is set to zero. N >= 0.
*
* A (local input) DOUBLE PRECISION pointer into the local memory
* to an array of dimension (LLD_A, LOCc(JA+N-1) ) containing
* the local pieces of sub( A ).
*
* 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.
*
* WORK (local workspace) DOUBLE PRECISION array dimension (LWORK)
* LWORK >= 0 if NORM = 'M' or 'm' (not referenced),
* Nq0 if NORM = '1', 'O' or 'o',
* Mp0 if NORM = 'I' or 'i',
* 0 if NORM = 'F', 'f', 'E' or 'e' (not referenced),
* 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 ),
* Mp0 = NUMROC( M+IROFFA, MB_A, MYROW, IAROW, NPROW ),
* Nq0 = 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.
*
* =====================================================================
*
* .. 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 UDIAG
INTEGER IACOL, IAROW, ICTXT, II, IIA, ICOFF, IOFFA,
$ IROFF, J, JB, JJ, JJA, JN, KK, LDA, LL, MP,
$ MYCOL, MYROW, NP, NPCOL, NPROW, NQ
DOUBLE PRECISION SCALE, SUM, VALUE
* ..
* .. Local Arrays ..
DOUBLE PRECISION RWORK( 2 )
* ..
* .. External Subroutines ..
EXTERNAL BLACS_GRIDINFO, DCOMBSSQ, DGEBR2D,
$ DGEBS2D, DGAMX2D, DGSUM2D, DLASSQ,
$ INFOG2L, PDTREECOMB
* ..
* .. External Functions ..
LOGICAL LSAME
INTEGER ICEIL, IDAMAX, NUMROC
EXTERNAL LSAME, ICEIL, IDAMAX, NUMROC
* ..
* .. Intrinsic Functions ..
INTRINSIC ABS, DBLE, MAX, MIN, MOD, SQRT
* ..
* .. Executable Statements ..
*
* Get grid parameters
*
ICTXT = DESCA( CTXT_ )
CALL BLACS_GRIDINFO( ICTXT, NPROW, NPCOL, MYROW, MYCOL )
*
UDIAG = LSAME( DIAG, 'U' )
CALL INFOG2L( IA, JA, DESCA, NPROW, NPCOL, MYROW, MYCOL, IIA, JJA,
$ IAROW, IACOL )
IROFF = MOD( IA-1, DESCA( MB_ ) )
ICOFF = MOD( JA-1, DESCA( NB_ ) )
MP = NUMROC( M+IROFF, DESCA( MB_ ), MYROW, IAROW, NPROW )
NQ = NUMROC( N+ICOFF, DESCA( NB_ ), MYCOL, IACOL, NPCOL )
IF( MYROW.EQ.IAROW )
$ MP = MP - IROFF
IF( MYCOL.EQ.IACOL )
$ NQ = NQ - ICOFF
LDA = DESCA( LLD_ )
IOFFA = ( JJA - 1 ) * LDA
*
IF( MIN( M, N ).EQ.0 ) THEN
*
VALUE = ZERO
*
ELSE IF( LSAME( NORM, 'M' ) ) THEN
*
* Find max(abs(A(i,j))).
*
IF( UDIAG ) THEN
VALUE = ONE
ELSE
VALUE = ZERO
END IF
*
IF( LSAME( UPLO, 'U' ) ) THEN
*
* Upper triangular matrix
*
II = IIA
JJ = JJA
JN = MIN( ICEIL( JA, DESCA( NB_ ) ) * DESCA( NB_ ), JA+N-1 )
JB = JN-JA+1
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 20 LL = JJ, JJ + JB -1
DO 10 KK = IIA, MIN(II+LL-JJ+1,IIA+MP-1)
VALUE = MAX( VALUE, ABS( A( IOFFA+KK ) ) )
10 CONTINUE
IOFFA = IOFFA + LDA
20 CONTINUE
ELSE
DO 40 LL = JJ, JJ + JB -1
DO 30 KK = IIA, MIN( II+LL-JJ, IIA+MP-1 )
VALUE = MAX( VALUE, ABS( A( IOFFA+KK ) ) )
30 CONTINUE
IOFFA = IOFFA + LDA
40 CONTINUE
END IF
ELSE
DO 60 LL = JJ, JJ + JB -1
DO 50 KK = IIA, MIN( II-1, IIA+MP-1 )
VALUE = MAX( VALUE, ABS( A( IOFFA+KK ) ) )
50 CONTINUE
IOFFA = IOFFA + LDA
60 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
* Loop over remaining block of columns
*
DO 130 J = JN+1, JA+N-1, DESCA( NB_ )
JB = MIN( JA+N-J, DESCA( NB_ ) )
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 80 LL = JJ, JJ + JB -1
DO 70 KK = IIA, MIN( II+LL-JJ+1, IIA+MP-1 )
VALUE = MAX( VALUE, ABS( A( IOFFA+KK ) ) )
70 CONTINUE
IOFFA = IOFFA + LDA
80 CONTINUE
ELSE
DO 100 LL = JJ, JJ + JB -1
DO 90 KK = IIA, MIN( II+LL-JJ, IIA+MP-1 )
VALUE = MAX( VALUE, ABS( A( IOFFA+KK ) ) )
90 CONTINUE
IOFFA = IOFFA + LDA
100 CONTINUE
END IF
ELSE
DO 120 LL = JJ, JJ + JB -1
DO 110 KK = IIA, MIN( II-1, IIA+MP-1 )
VALUE = MAX( VALUE, ABS( A( IOFFA+KK ) ) )
110 CONTINUE
IOFFA = IOFFA + LDA
120 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
130 CONTINUE
*
ELSE
*
* Lower triangular matrix
*
II = IIA
JJ = JJA
JN = MIN( ICEIL( JA, DESCA( NB_ ) ) * DESCA( NB_ ), JA+N-1 )
JB = JN-JA+1
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 150 LL = JJ, JJ + JB -1
DO 140 KK = II+LL-JJ+1, IIA+MP-1
VALUE = MAX( VALUE, ABS( A( IOFFA+KK ) ) )
140 CONTINUE
IOFFA = IOFFA + LDA
150 CONTINUE
ELSE
DO 170 LL = JJ, JJ + JB -1
DO 160 KK = II+LL-JJ, IIA+MP-1
VALUE = MAX( VALUE, ABS( A( IOFFA+KK ) ) )
160 CONTINUE
IOFFA = IOFFA + LDA
170 CONTINUE
END IF
ELSE
DO 190 LL = JJ, JJ + JB -1
DO 180 KK = II, IIA+MP-1
VALUE = MAX( VALUE, ABS( A( IOFFA+KK ) ) )
180 CONTINUE
IOFFA = IOFFA + LDA
190 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
* Loop over remaining block of columns
*
DO 260 J = JN+1, JA+N-1, DESCA( NB_ )
JB = MIN( JA+N-J, DESCA( NB_ ) )
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 210 LL = JJ, JJ + JB -1
DO 200 KK = II+LL-JJ+1, IIA+MP-1
VALUE = MAX( VALUE, ABS( A( IOFFA+KK ) ) )
200 CONTINUE
IOFFA = IOFFA + LDA
210 CONTINUE
ELSE
DO 230 LL = JJ, JJ + JB -1
DO 220 KK = II+LL-JJ, IIA+MP-1
VALUE = MAX( VALUE, ABS( A( IOFFA+KK ) ) )
220 CONTINUE
IOFFA = IOFFA + LDA
230 CONTINUE
END IF
ELSE
DO 250 LL = JJ, JJ + JB -1
DO 240 KK = II, IIA+MP-1
VALUE = MAX( VALUE, ABS( A( IOFFA+KK ) ) )
240 CONTINUE
IOFFA = IOFFA + LDA
250 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
260 CONTINUE
*
END IF
*
* Gather the intermediate results to process (0,0).
*
CALL DGAMX2D( ICTXT, 'All', ' ', 1, 1, VALUE, 1, KK, LL, -1,
$ 0, 0 )
*
ELSE IF( LSAME( NORM, 'O' ) .OR. NORM.EQ.'1' ) THEN
*
VALUE = ZERO
*
IF( LSAME( UPLO, 'U' ) ) THEN
*
* Upper triangular matrix
*
II = IIA
JJ = JJA
JN = MIN( ICEIL( JA, DESCA( NB_ ) ) * DESCA( NB_ ), JA+N-1 )
JB = JN-JA+1
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 280 LL = JJ, JJ + JB -1
SUM = ONE
DO 270 KK = IIA, MIN( II+LL-JJ, IIA+MP-1 )
SUM = SUM + ABS( A( IOFFA+KK ) )
270 CONTINUE
IOFFA = IOFFA + LDA
WORK( LL-JJA+1 ) = SUM
280 CONTINUE
ELSE
DO 300 LL = JJ, JJ + JB -1
SUM = ZERO
DO 290 KK = IIA, MIN( II+LL-JJ+1, IIA+MP-1 )
SUM = SUM + ABS( A( IOFFA+KK ) )
290 CONTINUE
IOFFA = IOFFA + LDA
WORK( LL-JJA+1 ) = SUM
300 CONTINUE
END IF
ELSE
DO 320 LL = JJ, JJ + JB -1
SUM = ZERO
DO 310 KK = IIA, MIN( II-1, IIA+MP-1 )
SUM = SUM + ABS( A( IOFFA+KK ) )
310 CONTINUE
IOFFA = IOFFA + LDA
WORK( LL-JJA+1 ) = SUM
320 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
* Loop over remaining block of columns
*
DO 390 J = JN+1, JA+N-1, DESCA( NB_ )
JB = MIN( JA+N-J, DESCA( NB_ ) )
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 340 LL = JJ, JJ + JB -1
SUM = ONE
DO 330 KK = IIA, MIN( II+LL-JJ+1, IIA+MP-1 )
SUM = SUM + ABS( A( IOFFA+KK ) )
330 CONTINUE
IOFFA = IOFFA + LDA
WORK( LL-JJA+1 ) = SUM
340 CONTINUE
ELSE
DO 360 LL = JJ, JJ + JB -1
SUM = ZERO
DO 350 KK = IIA, MIN( II+LL-JJ, IIA+MP-1 )
SUM = SUM + ABS( A( IOFFA+KK ) )
350 CONTINUE
IOFFA = IOFFA + LDA
WORK( LL-JJA+1 ) = SUM
360 CONTINUE
END IF
ELSE
DO 380 LL = JJ, JJ + JB -1
SUM = ZERO
DO 370 KK = IIA, MIN( II-1, IIA+MP-1 )
SUM = SUM + ABS( A( IOFFA+KK ) )
370 CONTINUE
IOFFA = IOFFA + LDA
WORK( LL-JJA+1 ) = SUM
380 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
390 CONTINUE
*
ELSE
*
* Lower triangular matrix
*
II = IIA
JJ = JJA
JN = MIN( ICEIL( JA, DESCA( NB_ ) ) * DESCA( NB_ ), JA+N-1 )
JB = JN-JA+1
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 410 LL = JJ, JJ + JB -1
SUM = ONE
DO 400 KK = II+LL-JJ+1, IIA+MP-1
SUM = SUM + ABS( A( IOFFA+KK ) )
400 CONTINUE
IOFFA = IOFFA + LDA
WORK( LL-JJA+1 ) = SUM
410 CONTINUE
ELSE
DO 430 LL = JJ, JJ + JB -1
SUM = ZERO
DO 420 KK = II+LL-JJ, IIA+MP-1
SUM = SUM + ABS( A( IOFFA+KK ) )
420 CONTINUE
IOFFA = IOFFA + LDA
WORK( LL-JJA+1 ) = SUM
430 CONTINUE
END IF
ELSE
DO 450 LL = JJ, JJ + JB -1
SUM = ZERO
DO 440 KK = II, IIA+MP-1
SUM = SUM + ABS( A( IOFFA+KK ) )
440 CONTINUE
IOFFA = IOFFA + LDA
WORK( LL-JJA+1 ) = SUM
450 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
* Loop over remaining block of columns
*
DO 520 J = JN+1, JA+N-1, DESCA( NB_ )
JB = MIN( JA+N-J, DESCA( NB_ ) )
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 470 LL = JJ, JJ + JB -1
SUM = ONE
DO 460 KK = II+LL-JJ+1, IIA+MP-1
SUM = SUM + ABS( A( IOFFA+KK ) )
460 CONTINUE
IOFFA = IOFFA + LDA
WORK( LL-JJA+1 ) = SUM
470 CONTINUE
ELSE
DO 490 LL = JJ, JJ + JB -1
SUM = ZERO
DO 480 KK = II+LL-JJ, IIA+MP-1
SUM = SUM + ABS( A( IOFFA+KK ) )
480 CONTINUE
IOFFA = IOFFA + LDA
WORK( LL-JJA+1 ) = SUM
490 CONTINUE
END IF
ELSE
DO 510 LL = JJ, JJ + JB -1
SUM = ZERO
DO 500 KK = II, IIA+MP-1
SUM = SUM + ABS( A( IOFFA+KK ) )
500 CONTINUE
IOFFA = IOFFA + LDA
WORK( LL-JJA+1 ) = SUM
510 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
520 CONTINUE
*
END IF
*
* Find sum of global matrix columns and store on row 0 of
* process grid
*
CALL DGSUM2D( ICTXT, 'Columnwise', ' ', 1, NQ, WORK, 1,
$ 0, MYCOL )
*
* Find maximum sum of columns for 1-norm
*
IF( MYROW.EQ.0 ) THEN
IF( NQ.GT.0 ) THEN
VALUE = WORK( IDAMAX( NQ, WORK, 1 ) )
ELSE
VALUE = ZERO
END IF
CALL DGAMX2D( ICTXT, 'Rowwise', ' ', 1, 1, VALUE, 1, KK, LL,
$ -1, 0, 0 )
END IF
*
ELSE IF( LSAME( NORM, 'I' ) ) THEN
*
IF( LSAME( UPLO, 'U' ) ) THEN
IF( UDIAG ) THEN
DO 530 KK = IIA, IIA+MP-1
WORK( KK ) = ONE
530 CONTINUE
ELSE
DO 540 KK = IIA, IIA+MP-1
WORK( KK ) = ZERO
540 CONTINUE
END IF
ELSE
IF( UDIAG ) THEN
NP = NUMROC( N+IROFF, DESCA( MB_ ), MYROW, IAROW, NPROW )
IF( MYROW.EQ.IAROW )
$ NP = NP - IROFF
DO 550 KK = IIA, IIA+NP-1
WORK( KK ) = ONE
550 CONTINUE
DO 560 KK = IIA+NP, IIA+MP-1
WORK( KK ) = ZERO
560 CONTINUE
ELSE
DO 570 KK = IIA, IIA+MP-1
WORK( KK ) = ZERO
570 CONTINUE
END IF
END IF
*
IF( LSAME( UPLO, 'U' ) ) THEN
*
* Upper triangular matrix
*
II = IIA
JJ = JJA
JN = MIN( ICEIL( JA, DESCA( NB_ ) ) * DESCA( NB_ ), JA+N-1 )
JB = JN-JA+1
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 590 LL = JJ, JJ + JB -1
DO 580 KK = IIA, MIN( II+LL-JJ, IIA+MP-1 )
WORK( KK-IIA+1 ) = WORK( KK-IIA+1 ) +
$ ABS( A( IOFFA+KK ) )
580 CONTINUE
IOFFA = IOFFA + LDA
590 CONTINUE
ELSE
DO 610 LL = JJ, JJ + JB -1
DO 600 KK = IIA, MIN(II+LL-JJ+1,IIA+MP-1)
WORK( KK-IIA+1 ) = WORK( KK-IIA+1 ) +
$ ABS( A( IOFFA+KK ) )
600 CONTINUE
IOFFA = IOFFA + LDA
610 CONTINUE
END IF
ELSE
DO 630 LL = JJ, JJ + JB -1
DO 620 KK = IIA, MIN( II-1, IIA+MP-1 )
WORK( KK-IIA+1 ) = WORK( KK-IIA+1 ) +
$ ABS( A( IOFFA+KK ) )
620 CONTINUE
IOFFA = IOFFA + LDA
630 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
* Loop over remaining block of columns
*
DO 700 J = JN+1, JA+N-1, DESCA( NB_ )
JB = MIN( JA+N-J, DESCA( NB_ ) )
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 650 LL = JJ, JJ + JB -1
DO 640 KK = IIA, MIN( II+LL-JJ+1, IIA+MP-1 )
WORK( KK-IIA+1 ) = WORK( KK-IIA+1 ) +
$ ABS( A( IOFFA+KK ) )
640 CONTINUE
IOFFA = IOFFA + LDA
650 CONTINUE
ELSE
DO 670 LL = JJ, JJ + JB -1
DO 660 KK = IIA, MIN( II+LL-JJ, IIA+MP-1 )
WORK( KK-IIA+1 ) = WORK( KK-IIA+1 ) +
$ ABS( A( IOFFA+KK ) )
660 CONTINUE
IOFFA = IOFFA + LDA
670 CONTINUE
END IF
ELSE
DO 690 LL = JJ, JJ + JB -1
DO 680 KK = IIA, MIN( II-1, IIA+MP-1 )
WORK( KK-IIA+1 ) = WORK( KK-IIA+1 ) +
$ ABS( A( IOFFA+KK ) )
680 CONTINUE
IOFFA = IOFFA + LDA
690 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
700 CONTINUE
*
ELSE
*
* Lower triangular matrix
*
II = IIA
JJ = JJA
JN = MIN( ICEIL( JA, DESCA( NB_ ) ) * DESCA( NB_ ), JA+N-1 )
JB = JN-JA+1
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 720 LL = JJ, JJ + JB -1
DO 710 KK = II+LL-JJ+1, IIA+MP-1
WORK( KK-IIA+1 ) = WORK( KK-IIA+1 ) +
$ ABS( A( IOFFA+KK ) )
710 CONTINUE
IOFFA = IOFFA + LDA
720 CONTINUE
ELSE
DO 740 LL = JJ, JJ + JB -1
DO 730 KK = II+LL-JJ, IIA+MP-1
WORK( KK-IIA+1 ) = WORK( KK-IIA+1 ) +
$ ABS( A( IOFFA+KK ) )
730 CONTINUE
IOFFA = IOFFA + LDA
740 CONTINUE
END IF
ELSE
DO 760 LL = JJ, JJ + JB -1
DO 750 KK = II, IIA+MP-1
WORK( KK-IIA+1 ) = WORK( KK-IIA+1 ) +
$ ABS( A( IOFFA+KK ) )
750 CONTINUE
IOFFA = IOFFA + LDA
760 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
* Loop over remaining block of columns
*
DO 830 J = JN+1, JA+N-1, DESCA( NB_ )
JB = MIN( JA+N-J, DESCA( NB_ ) )
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 780 LL = JJ, JJ + JB -1
DO 770 KK = II+LL-JJ+1, IIA+MP-1
WORK( KK-IIA+1 ) = WORK( KK-IIA+1 ) +
$ ABS( A( IOFFA+KK ) )
770 CONTINUE
IOFFA = IOFFA + LDA
780 CONTINUE
ELSE
DO 800 LL = JJ, JJ + JB -1
DO 790 KK = II+LL-JJ, IIA+MP-1
WORK( KK-IIA+1 ) = WORK( KK-IIA+1 ) +
$ ABS( A( IOFFA+KK ) )
790 CONTINUE
IOFFA = IOFFA + LDA
800 CONTINUE
END IF
ELSE
DO 820 LL = JJ, JJ + JB -1
DO 810 KK = II, IIA+MP-1
WORK( KK-IIA+1 ) = WORK( KK-IIA+1 ) +
$ ABS( A( IOFFA+KK ) )
810 CONTINUE
IOFFA = IOFFA + LDA
820 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
830 CONTINUE
*
END IF
*
* Find sum of global matrix rows and store on column 0 of
* process grid
*
CALL DGSUM2D( ICTXT, 'Rowwise', ' ', MP, 1, WORK, MAX( 1, MP ),
$ MYROW, 0 )
*
* Find maximum sum of rows for Infinity-norm
*
IF( MYCOL.EQ.0 ) THEN
IF( MP.GT.0 ) THEN
VALUE = WORK( IDAMAX( MP, WORK, 1 ) )
ELSE
VALUE = ZERO
END IF
CALL DGAMX2D( ICTXT, 'Columnwise', ' ', 1, 1, VALUE, 1, KK,
$ LL, -1, 0, 0 )
END IF
*
ELSE IF( LSAME( NORM, 'F' ) .OR. LSAME( NORM, 'E' ) ) THEN
*
IF( UDIAG ) THEN
SCALE = ONE
SUM = DBLE( MIN( M, N ) ) / DBLE( NPROW*NPCOL )
ELSE
SCALE = ZERO
SUM = ONE
END IF
*
IF( LSAME( UPLO, 'U' ) ) THEN
*
* Upper triangular matrix
*
II = IIA
JJ = JJA
JN = MIN( ICEIL( JA, DESCA( NB_ ) ) * DESCA( NB_ ), JA+N-1 )
JB = JN-JA+1
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 840 LL = JJ, JJ + JB -1
CALL DLASSQ( MIN( II+LL-JJ, IIA+MP-1 )-IIA+1,
$ A( IIA+IOFFA ), 1, SCALE, SUM )
IOFFA = IOFFA + LDA
840 CONTINUE
ELSE
DO 850 LL = JJ, JJ + JB -1
CALL DLASSQ( MIN( II+LL-JJ+1, IIA+MP-1 )-IIA+1,
$ A( IIA+IOFFA ), 1, SCALE, SUM )
IOFFA = IOFFA + LDA
850 CONTINUE
END IF
ELSE
DO 860 LL = JJ, JJ + JB -1
CALL DLASSQ( MIN( II-1, IIA+MP-1 )-IIA+1,
$ A( IIA+IOFFA ), 1, SCALE, SUM )
IOFFA = IOFFA + LDA
860 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
* Loop over remaining block of columns
*
DO 900 J = JN+1, JA+N-1, DESCA( NB_ )
JB = MIN( JA+N-J, DESCA( NB_ ) )
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 870 LL = JJ, JJ + JB -1
CALL DLASSQ( MIN( II+LL-JJ+1, IIA+MP-1 )-
$ IIA+1, A( IIA+IOFFA ), 1, SCALE,
$ SUM )
IOFFA = IOFFA + LDA
870 CONTINUE
ELSE
DO 880 LL = JJ, JJ + JB -1
CALL DLASSQ( MIN( II+LL-JJ, IIA+MP-1 )-
$ IIA+1, A( IIA+IOFFA ), 1, SCALE,
$ SUM )
IOFFA = IOFFA + LDA
880 CONTINUE
END IF
ELSE
DO 890 LL = JJ, JJ + JB -1
CALL DLASSQ( MIN( II-1, IIA+MP-1 )-IIA+1,
$ A( IIA+IOFFA ), 1, SCALE, SUM )
IOFFA = IOFFA + LDA
890 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
900 CONTINUE
*
ELSE
*
* Lower triangular matrix
*
II = IIA
JJ = JJA
JN = MIN( ICEIL( JA, DESCA( NB_ ) ) * DESCA( NB_ ), JA+N-1 )
JB = JN-JA+1
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 910 LL = JJ, JJ + JB -1
CALL DLASSQ( IIA+MP-(II+LL-JJ+1),
$ A( II+LL-JJ+IOFFA ), 1, SCALE,
$ SUM )
IOFFA = IOFFA + LDA
910 CONTINUE
ELSE
DO 920 LL = JJ, JJ + JB -1
CALL DLASSQ( IIA+MP-(II+LL-JJ),
$ A( II+LL-JJ+IOFFA ), 1, SCALE,
$ SUM )
IOFFA = IOFFA + LDA
920 CONTINUE
END IF
ELSE
DO 930 LL = JJ, JJ + JB -1
CALL DLASSQ( IIA+MP-II, A( II+IOFFA ), 1, SCALE,
$ SUM )
IOFFA = IOFFA + LDA
930 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
* Loop over remaining block of columns
*
DO 970 J = JN+1, JA+N-1, DESCA( NB_ )
JB = MIN( JA+N-J, DESCA( NB_ ) )
*
IF( MYCOL.EQ.IACOL ) THEN
IF( MYROW.EQ.IAROW ) THEN
IF( UDIAG ) THEN
DO 940 LL = JJ, JJ + JB -1
CALL DLASSQ( IIA+MP-(II+LL-JJ+1),
$ A( II+LL-JJ+IOFFA ), 1, SCALE,
$ SUM )
IOFFA = IOFFA + LDA
940 CONTINUE
ELSE
DO 950 LL = JJ, JJ + JB -1
CALL DLASSQ( IIA+MP-(II+LL-JJ),
$ A( II+LL-JJ+IOFFA ), 1, SCALE,
$ SUM )
IOFFA = IOFFA + LDA
950 CONTINUE
END IF
ELSE
DO 960 LL = JJ, JJ + JB -1
CALL DLASSQ( IIA+MP-II, A( II+IOFFA ), 1, SCALE,
$ SUM )
IOFFA = IOFFA + LDA
960 CONTINUE
END IF
JJ = JJ + JB
END IF
*
IF( MYROW.EQ.IAROW )
$ II = II + JB
IAROW = MOD( IAROW+1, NPROW )
IACOL = MOD( IACOL+1, NPCOL )
*
970 CONTINUE
*
END IF
*
* Perform the global scaled sum
*
RWORK( 1 ) = SCALE
RWORK( 2 ) = SUM
CALL PDTREECOMB( ICTXT, 'All', 2, RWORK, 0, 0, DCOMBSSQ )
VALUE = RWORK( 1 ) * SQRT( RWORK( 2 ) )
*
END IF
*
* Broadcast the result to every process in the grid.
*
IF( MYROW.EQ.0 .AND. MYCOL.EQ.0 ) THEN
CALL DGEBS2D( ICTXT, 'All', ' ', 1, 1, VALUE, 1 )
ELSE
CALL DGEBR2D( ICTXT, 'All', ' ', 1, 1, VALUE, 1, 0, 0 )
END IF
*
PDLANTR = VALUE
*
RETURN
*
* End of PDLANTR
*
END
|