|
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 |
SUBROUTINE CGEQRFP( M, N, A, LDA, TAU, WORK, LWORK, INFO )
* * -- LAPACK routine (version 3.3.1) -- * -- LAPACK is a software package provided by Univ. of Tennessee, -- * -- Univ. of California Berkeley, Univ. of Colorado Denver and NAG Ltd..-- * -- April 2011 -- * * .. Scalar Arguments .. INTEGER INFO, LDA, LWORK, M, N * .. * .. Array Arguments .. COMPLEX A( LDA, * ), TAU( * ), WORK( * ) * .. * * Purpose * ======= * * CGEQRFP computes a QR factorization of a complex M-by-N matrix A: * A = Q * R. * * 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. * * A (input/output) COMPLEX array, dimension (LDA,N) * On entry, the M-by-N matrix A. * On exit, the elements on and above the diagonal of the array * contain the min(M,N)-by-N upper trapezoidal matrix R (R is * upper triangular if m >= n); the elements below the diagonal, * with the array TAU, represent the unitary matrix Q as a * product of min(m,n) elementary reflectors (see Further * Details). * * LDA (input) INTEGER * The leading dimension of the array A. LDA >= max(1,M). * * TAU (output) COMPLEX array, dimension (min(M,N)) * The scalar factors of the elementary reflectors (see Further * Details). * * WORK (workspace/output) COMPLEX array, dimension (MAX(1,LWORK)) * On exit, if INFO = 0, WORK(1) returns the optimal LWORK. * * LWORK (input) INTEGER * The dimension of the array WORK. LWORK >= max(1,N). * For optimum performance LWORK >= N*NB, where NB is * the optimal blocksize. * * If LWORK = -1, then a workspace query is assumed; the routine * only calculates the optimal size of the WORK array, returns * this value as the first entry of the WORK array, and no error * message related to LWORK is issued by XERBLA. * * INFO (output) INTEGER * = 0: successful exit * < 0: if INFO = -i, the i-th argument had an illegal value * * Further Details * =============== * * The matrix Q is represented as a product of elementary reflectors * * Q = H(1) H(2) . . . H(k), where k = min(m,n). * * Each H(i) has the form * * H(i) = I - tau * v * v**H * * where tau is a complex scalar, and v is a complex vector with * v(1:i-1) = 0 and v(i) = 1; v(i+1:m) is stored on exit in A(i+1:m,i), * and tau in TAU(i). * * ===================================================================== * * .. Local Scalars .. LOGICAL LQUERY INTEGER I, IB, IINFO, IWS, K, LDWORK, LWKOPT, NB, $ NBMIN, NX * .. * .. External Subroutines .. EXTERNAL CGEQR2P, CLARFB, CLARFT, XERBLA * .. * .. Intrinsic Functions .. INTRINSIC MAX, MIN * .. * .. External Functions .. INTEGER ILAENV EXTERNAL ILAENV * .. * .. Executable Statements .. * * Test the input arguments * INFO = 0 NB = ILAENV( 1, 'CGEQRF', ' ', M, N, -1, -1 ) LWKOPT = N*NB WORK( 1 ) = LWKOPT LQUERY = ( LWORK.EQ.-1 ) IF( M.LT.0 ) THEN INFO = -1 ELSE IF( N.LT.0 ) THEN INFO = -2 ELSE IF( LDA.LT.MAX( 1, M ) ) THEN INFO = -4 ELSE IF( LWORK.LT.MAX( 1, N ) .AND. .NOT.LQUERY ) THEN INFO = -7 END IF IF( INFO.NE.0 ) THEN CALL XERBLA( 'CGEQRFP', -INFO ) RETURN ELSE IF( LQUERY ) THEN RETURN END IF * * Quick return if possible * K = MIN( M, N ) IF( K.EQ.0 ) THEN WORK( 1 ) = 1 RETURN END IF * NBMIN = 2 NX = 0 IWS = N IF( NB.GT.1 .AND. NB.LT.K ) THEN * * Determine when to cross over from blocked to unblocked code. * NX = MAX( 0, ILAENV( 3, 'CGEQRF', ' ', M, N, -1, -1 ) ) IF( NX.LT.K ) THEN * * Determine if workspace is large enough for blocked code. * LDWORK = N IWS = LDWORK*NB IF( LWORK.LT.IWS ) THEN * * Not enough workspace to use optimal NB: reduce NB and * determine the minimum value of NB. * NB = LWORK / LDWORK NBMIN = MAX( 2, ILAENV( 2, 'CGEQRF', ' ', M, N, -1, $ -1 ) ) END IF END IF END IF * IF( NB.GE.NBMIN .AND. NB.LT.K .AND. NX.LT.K ) THEN * * Use blocked code initially * DO 10 I = 1, K - NX, NB IB = MIN( K-I+1, NB ) * * Compute the QR factorization of the current block * A(i:m,i:i+ib-1) * CALL CGEQR2P( M-I+1, IB, A( I, I ), LDA, TAU( I ), WORK, $ IINFO ) IF( I+IB.LE.N ) THEN * * Form the triangular factor of the block reflector * H = H(i) H(i+1) . . . H(i+ib-1) * CALL CLARFT( 'Forward', 'Columnwise', M-I+1, IB, $ A( I, I ), LDA, TAU( I ), WORK, LDWORK ) * * Apply H**H to A(i:m,i+ib:n) from the left * CALL CLARFB( 'Left', 'Conjugate transpose', 'Forward', $ 'Columnwise', M-I+1, N-I-IB+1, IB, $ A( I, I ), LDA, WORK, LDWORK, A( I, I+IB ), $ LDA, WORK( IB+1 ), LDWORK ) END IF 10 CONTINUE ELSE I = 1 END IF * * Use unblocked code to factor the last or only block. * IF( I.LE.K ) $ CALL CGEQR2P( M-I+1, N-I+1, A( I, I ), LDA, TAU( I ), WORK, $ IINFO ) * WORK( 1 ) = IWS RETURN * * End of CGEQRFP * END |