/*  -- translated by f2c (version 20100827).
   You must link the resulting object file with libf2c:
	on Microsoft Windows system, link with libf2c.lib;
	on Linux or Unix systems, link with .../path/to/libf2c.a -lm
	or, if you install libf2c.a in a standard place, with -lf2c -lm
	-- in that order, at the end of the command line, as in
		cc *.o -lf2c -lm
	Source for libf2c is in /netlib/f2c/libf2c.zip, e.g.,

		http://www.netlib.org/f2c/libf2c.zip
*/

#include "f2c.h"

/* Table of constant values */

static integer c__1 = 1;
static integer c_n1 = -1;
static integer c__3 = 3;
static integer c__2 = 2;

/* Subroutine */ int splicingdgelqf_(integer *m, integer *n, doublereal *a, integer *
	lda, doublereal *tau, doublereal *work, integer *lwork, integer *info)
{
    /* System generated locals */
    integer a_dim1, a_offset, i__1, i__2, i__3, i__4;

    /* Local variables */
    static integer i__, k, ib, nb, nx, iws, nbmin, iinfo;
    extern /* Subroutine */ int splicingdgelq2_(integer *, integer *, doublereal *, 
	    integer *, doublereal *, doublereal *, integer *), splicingdlarfb_(char *,
	     char *, char *, char *, integer *, integer *, integer *, 
	    doublereal *, integer *, doublereal *, integer *, doublereal *, 
	    integer *, doublereal *, integer *), splicingdlarft_(char *, char *, integer *, integer *, doublereal 
	    *, integer *, doublereal *, doublereal *, integer *), splicingxerbla_(char *, integer *, ftnlen);
    extern integer splicingilaenv_(integer *, char *, char *, integer *, integer *, 
	    integer *, integer *, ftnlen, ftnlen);
    static integer ldwork, lwkopt;
    static logical lquery;


/*  -- 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                                                      --   


    Purpose   
    =======   

    DGELQF computes an LQ factorization of a real M-by-N matrix A:   
    A = L * Q.   

    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) DOUBLE PRECISION array, dimension (LDA,N)   
            On entry, the M-by-N matrix A.   
            On exit, the elements on and below the diagonal of the array   
            contain the m-by-min(m,n) lower trapezoidal matrix L (L is   
            lower triangular if m <= n); the elements above the diagonal,   
            with the array TAU, represent the orthogonal matrix Q as a   
            product of elementary reflectors (see Further Details).   

    LDA     (input) INTEGER   
            The leading dimension of the array A.  LDA >= max(1,M).   

    TAU     (output) DOUBLE PRECISION array, dimension (min(M,N))   
            The scalar factors of the elementary reflectors (see Further   
            Details).   

    WORK    (workspace/output) DOUBLE PRECISION 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,M).   
            For optimum performance LWORK >= M*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(k) . . . H(2) H(1), where k = min(m,n).   

    Each H(i) has the form   

       H(i) = I - tau * v * v**T   

    where tau is a real scalar, and v is a real vector with   
    v(1:i-1) = 0 and v(i) = 1; v(i+1:n) is stored on exit in A(i,i+1:n),   
    and tau in TAU(i).   

    =====================================================================   


       Test the input arguments   

       Parameter adjustments */
    a_dim1 = *lda;
    a_offset = 1 + a_dim1;
    a -= a_offset;
    --tau;
    --work;

    /* Function Body */
    *info = 0;
    nb = splicingilaenv_(&c__1, "DGELQF", " ", m, n, &c_n1, &c_n1, (ftnlen)6, (ftnlen)
	    1);
    lwkopt = *m * nb;
    work[1] = (doublereal) lwkopt;
    lquery = *lwork == -1;
    if (*m < 0) {
	*info = -1;
    } else if (*n < 0) {
	*info = -2;
    } else if (*lda < max(1,*m)) {
	*info = -4;
    } else if (*lwork < max(1,*m) && ! lquery) {
	*info = -7;
    }
    if (*info != 0) {
	i__1 = -(*info);
	splicingxerbla_("DGELQF", &i__1, (ftnlen)6);
	return 0;
    } else if (lquery) {
	return 0;
    }

/*     Quick return if possible */

    k = min(*m,*n);
    if (k == 0) {
	work[1] = 1.;
	return 0;
    }

    nbmin = 2;
    nx = 0;
    iws = *m;
    if (nb > 1 && nb < k) {

/*        Determine when to cross over from blocked to unblocked code.   

   Computing MAX */
	i__1 = 0, i__2 = splicingilaenv_(&c__3, "DGELQF", " ", m, n, &c_n1, &c_n1, (
		ftnlen)6, (ftnlen)1);
	nx = max(i__1,i__2);
	if (nx < k) {

/*           Determine if workspace is large enough for blocked code. */

	    ldwork = *m;
	    iws = ldwork * nb;
	    if (*lwork < iws) {

/*              Not enough workspace to use optimal NB:  reduce NB and   
                determine the minimum value of NB. */

		nb = *lwork / ldwork;
/* Computing MAX */
		i__1 = 2, i__2 = splicingilaenv_(&c__2, "DGELQF", " ", m, n, &c_n1, &
			c_n1, (ftnlen)6, (ftnlen)1);
		nbmin = max(i__1,i__2);
	    }
	}
    }

    if (nb >= nbmin && nb < k && nx < k) {

/*        Use blocked code initially */

	i__1 = k - nx;
	i__2 = nb;
	for (i__ = 1; i__2 < 0 ? i__ >= i__1 : i__ <= i__1; i__ += i__2) {
/* Computing MIN */
	    i__3 = k - i__ + 1;
	    ib = min(i__3,nb);

/*           Compute the LQ factorization of the current block   
             A(i:i+ib-1,i:n) */

	    i__3 = *n - i__ + 1;
	    splicingdgelq2_(&ib, &i__3, &a[i__ + i__ * a_dim1], lda, &tau[i__], &work[
		    1], &iinfo);
	    if (i__ + ib <= *m) {

/*              Form the triangular factor of the block reflector   
                H = H(i) H(i+1) . . . H(i+ib-1) */

		i__3 = *n - i__ + 1;
		splicingdlarft_("Forward", "Rowwise", &i__3, &ib, &a[i__ + i__ * 
			a_dim1], lda, &tau[i__], &work[1], &ldwork);

/*              Apply H to A(i+ib:m,i:n) from the right */

		i__3 = *m - i__ - ib + 1;
		i__4 = *n - i__ + 1;
		splicingdlarfb_("Right", "No transpose", "Forward", "Rowwise", &i__3, 
			&i__4, &ib, &a[i__ + i__ * a_dim1], lda, &work[1], &
			ldwork, &a[i__ + ib + i__ * a_dim1], lda, &work[ib + 
			1], &ldwork);
	    }
/* L10: */
	}
    } else {
	i__ = 1;
    }

/*     Use unblocked code to factor the last or only block. */

    if (i__ <= k) {
	i__2 = *m - i__ + 1;
	i__1 = *n - i__ + 1;
	splicingdgelq2_(&i__2, &i__1, &a[i__ + i__ * a_dim1], lda, &tau[i__], &work[1]
		, &iinfo);
    }

    work[1] = (doublereal) iws;
    return 0;

/*     End of DGELQF */

} /* splicingdgelqf_ */

