SUBROUTINE CDBTRF( M, N, KL, KU, AB, LDAB, INFO )
*
* Written by Andrew J. Cleary, University of Tennessee.
* August, 1996.
* Modified from CGBTRF:
* -- LAPACK routine (preliminary version) --
* Univ. of Tennessee, Univ. of California Berkeley, NAG Ltd.,
* Courant Institute, Argonne National Lab, and Rice University
* August 6, 1991
*
* .. Scalar Arguments ..
INTEGER INFO, KL, KU, LDAB, M, N
* ..
* .. Array Arguments ..
COMPLEX AB( LDAB, * )
* ..
*
* Purpose
* =======
*
* Cdbtrf computes an LU factorization of a real m-by-n band matrix A
* without using partial pivoting or row interchanges.
*
* This is the blocked version of the algorithm, calling Level 3 BLAS.
*
* Arguments
* =========
*
* M (input) INTEGER
* The number of rows of the matrix A. M >= 0.
*
* N (input) INTEGER
* The number of columns of the matrix A. N >= 0.
*
* KL (input) INTEGER
* The number of subdiagonals within the band of A. KL >= 0.
*
* KU (input) INTEGER
* The number of superdiagonals within the band of A. KU >= 0.
*
* AB (input/output) REAL array, dimension (LDAB,N)
* On entry, the matrix A in band storage, in rows KL+1 to
* 2*KL+KU+1; rows 1 to KL of the array need not be set.
* The j-th column of A is stored in the j-th column of the
* array AB as follows:
* AB(kl+ku+1+i-j,j) = A(i,j) for max(1,j-ku)<=i<=min(m,j+kl)
*
* On exit, details of the factorization: U is stored as an
* upper triangular band matrix with KL+KU superdiagonals in
* rows 1 to KL+KU+1, and the multipliers used during the
* factorization are stored in rows KL+KU+2 to 2*KL+KU+1.
* See below for further details.
*
* LDAB (input) INTEGER
* The leading dimension of the array AB. LDAB >= 2*KL+KU+1.
*
* INFO (output) INTEGER
* = 0: successful exit
* < 0: if INFO = -i, the i-th argument had an illegal value
* > 0: if INFO = +i, U(i,i) is exactly zero. The factorization
* has been completed, but the factor U is exactly
* singular, and division by zero will occur if it is used
* to solve a system of equations.
*
* Further Details
* ===============
*
* The band storage scheme is illustrated by the following example, when
* M = N = 6, KL = 2, KU = 1:
*
* On entry: On exit:
*
* * a12 a23 a34 a45 a56 * u12 u23 u34 u45 u56
* a11 a22 a33 a44 a55 a66 u11 u22 u33 u44 u55 u66
* a21 a32 a43 a54 a65 * m21 m32 m43 m54 m65 *
* a31 a42 a53 a64 * * m31 m42 m53 m64 * *
*
* Array elements marked * are not used by the routine.
*
* =====================================================================
*
* .. Parameters ..
REAL ONE, ZERO
PARAMETER ( ONE = 1.0E+0 )
PARAMETER ( ZERO = 0.0E+0 )
COMPLEX CONE, CZERO
PARAMETER ( CONE = ( 1.0E+0, 0.0E+0 ) )
PARAMETER ( CZERO = ( 0.0E+0, 0.0E+0 ) )
INTEGER NBMAX, LDWORK
PARAMETER ( NBMAX = 64, LDWORK = NBMAX+1 )
* ..
* .. Local Scalars ..
INTEGER I, I2, I3, II, J, J2, J3, JB, JJ, JM, JP,
$ JU, KM, KV, NB, NW
* ..
* .. Local Arrays ..
COMPLEX WORK13( LDWORK, NBMAX ),
$ WORK31( LDWORK, NBMAX )
* ..
* .. External Functions ..
INTEGER ILAENV, ISAMAX
EXTERNAL ILAENV, ISAMAX
* ..
* .. External Subroutines ..
EXTERNAL CCOPY, CDBTF2, CGEMM, CGERU, CSCAL,
$ CSWAP, CTRSM, XERBLA
* ..
* .. Intrinsic Functions ..
INTRINSIC MAX, MIN
* ..
* .. Executable Statements ..
*
* KV is the number of superdiagonals in the factor U
*
KV = KU
*
* Test the input parameters.
*
INFO = 0
IF( M.LT.0 ) THEN
INFO = -1
ELSE IF( N.LT.0 ) THEN
INFO = -2
ELSE IF( KL.LT.0 ) THEN
INFO = -3
ELSE IF( KU.LT.0 ) THEN
INFO = -4
ELSE IF( LDAB.LT.MIN( MIN( KL+KV+1,M ),N ) ) THEN
INFO = -6
END IF
IF( INFO.NE.0 ) THEN
CALL XERBLA( 'CDBTRF', -INFO )
RETURN
END IF
*
* Quick return if possible
*
IF( M.EQ.0 .OR. N.EQ.0 )
$ RETURN
*
* Determine the block size for this environment
*
NB = ILAENV( 1, 'CDBTRF', ' ', M, N, KL, KU )
*
* The block size must not exceed the limit set by the size of the
* local arrays WORK13 and WORK31.
*
NB = MIN( NB, NBMAX )
*
IF( NB.LE.1 .OR. NB.GT.KL ) THEN
*
* Use unblocked code
*
CALL CDBTF2( M, N, KL, KU, AB, LDAB, INFO )
ELSE
*
* Use blocked code
*
* Zero the superdiagonal elements of the work array WORK13
*
DO 20 J = 1, NB
DO 10 I = 1, J - 1
WORK13( I, J ) = ZERO
10 CONTINUE
20 CONTINUE
*
* Zero the subdiagonal elements of the work array WORK31
*
DO 40 J = 1, NB
DO 30 I = J + 1, NB
WORK31( I, J ) = ZERO
30 CONTINUE
40 CONTINUE
*
* JU is the index of the last column affected by the current
* stage of the factorization
*
JU = 1
*
DO 180 J = 1, MIN( M, N ), NB
JB = MIN( NB, MIN( M, N )-J+1 )
*
* The active part of the matrix is partitioned
*
* A11 A12 A13
* A21 A22 A23
* A31 A32 A33
*
* Here A11, A21 and A31 denote the current block of JB columns
* which is about to be factorized. The number of rows in the
* partitioning are JB, I2, I3 respectively, and the numbers
* of columns are JB, J2, J3. The superdiagonal elements of A13
* and the subdiagonal elements of A31 lie outside the band.
*
I2 = MIN( KL-JB, M-J-JB+1 )
I3 = MIN( JB, M-J-KL+1 )
*
* J2 and J3 are computed after JU has been updated.
*
* Factorize the current block of JB columns
*
DO 80 JJ = J, J + JB - 1
*
* Find pivot and test for singularity. KM is the number of
* subdiagonal elements in the current column.
*
KM = MIN( KL, M-JJ )
JP = 1
IF( AB( KV+JP, JJ ).NE.ZERO ) THEN
JU = MAX( JU, MIN( JJ+KU+JP-1, N ) )
*
* Compute multipliers
*
CALL CSCAL( KM, ONE / AB( KV+1, JJ ), AB( KV+2, JJ ),
$ 1 )
*
* Update trailing submatrix within the band and within
* the current block. JM is the index of the last column
* which needs to be updated.
*
JM = MIN( JU, J+JB-1 )
IF( JM.GT.JJ ) THEN
CALL CGERU( KM, JM-JJ, -CONE, AB( KV+2, JJ ), 1,
$ AB( KV, JJ+1 ), LDAB-1,
$ AB( KV+1, JJ+1 ), LDAB-1 )
END IF
END IF
*
* Copy current column of A31 into the work array WORK31
*
NW = MIN( JJ-J+1, I3 )
IF( NW.GT.0 )
$ CALL CCOPY( NW, AB( KV+KL+1-JJ+J, JJ ), 1,
$ WORK31( 1, JJ-J+1 ), 1 )
80 CONTINUE
IF( J+JB.LE.N ) THEN
*
* Apply the row interchanges to the other blocks.
*
J2 = MIN( JU-J+1, KV ) - JB
J3 = MAX( 0, JU-J-KV+1 )
*
* Update the relevant part of the trailing submatrix
*
IF( J2.GT.0 ) THEN
*
* Update A12
*
CALL CTRSM( 'Left', 'Lower', 'No transpose', 'Unit',
$ JB, J2, CONE, AB( KV+1, J ), LDAB-1,
$ AB( KV+1-JB, J+JB ), LDAB-1 )
*
IF( I2.GT.0 ) THEN
*
* Update A22
*
CALL CGEMM( 'No transpose', 'No transpose', I2, J2,
$ JB, -CONE, AB( KV+1+JB, J ), LDAB-1,
$ AB( KV+1-JB, J+JB ), LDAB-1, CONE,
$ AB( KV+1, J+JB ), LDAB-1 )
END IF
*
IF( I3.GT.0 ) THEN
*
* Update A32
*
CALL CGEMM( 'No transpose', 'No transpose', I3, J2,
$ JB, -CONE, WORK31, LDWORK,
$ AB( KV+1-JB, J+JB ), LDAB-1, CONE,
$ AB( KV+KL+1-JB, J+JB ), LDAB-1 )
END IF
END IF
*
IF( J3.GT.0 ) THEN
*
* Copy the lower triangle of A13 into the work array
* WORK13
*
DO 130 JJ = 1, J3
DO 120 II = JJ, JB
WORK13( II, JJ ) = AB( II-JJ+1, JJ+J+KV-1 )
120 CONTINUE
130 CONTINUE
*
* Update A13 in the work array
*
CALL CTRSM( 'Left', 'Lower', 'No transpose', 'Unit',
$ JB, J3, CONE, AB( KV+1, J ), LDAB-1,
$ WORK13, LDWORK )
*
IF( I2.GT.0 ) THEN
*
* Update A23
*
CALL CGEMM( 'No transpose', 'No transpose', I2, J3,
$ JB, -CONE, AB( KV+1+JB, J ), LDAB-1,
$ WORK13, LDWORK, CONE, AB( 1+JB, J+KV ),
$ LDAB-1 )
END IF
*
IF( I3.GT.0 ) THEN
*
* Update A33
*
CALL CGEMM( 'No transpose', 'No transpose', I3, J3,
$ JB, -CONE, WORK31, LDWORK, WORK13,
$ LDWORK, CONE, AB( 1+KL, J+KV ), LDAB-1 )
END IF
*
* Copy the lower triangle of A13 back into place
*
DO 150 JJ = 1, J3
DO 140 II = JJ, JB
AB( II-JJ+1, JJ+J+KV-1 ) = WORK13( II, JJ )
140 CONTINUE
150 CONTINUE
END IF
ELSE
END IF
*
* copy the upper triangle of A31 back into place
*
DO 170 JJ = J + JB - 1, J, -1
*
* Copy the current column of A31 back into place
*
NW = MIN( I3, JJ-J+1 )
IF( NW.GT.0 )
$ CALL CCOPY( NW, WORK31( 1, JJ-J+1 ), 1,
$ AB( KV+KL+1-JJ+J, JJ ), 1 )
170 CONTINUE
180 CONTINUE
END IF
*
RETURN
*
* End of CDBTRF
*
END