OpenBLAS/lapack-netlib/SRC/DEPRECATED/slahrd.c

#include <math.h>
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include <complex.h>
#ifdef complex
#undef complex
#endif
#ifdef I
#undef I
#endif

#if defined(_WIN64)
typedef long long BLASLONG;
typedef unsigned long long BLASULONG;
#else
typedef long BLASLONG;
typedef unsigned long BLASULONG;
#endif

#ifdef LAPACK_ILP64
typedef BLASLONG blasint;
#if defined(_WIN64)
#define blasabs(x) llabs(x)
#else
#define blasabs(x) labs(x)
#endif
#else
typedef int blasint;
#define blasabs(x) abs(x)
#endif

typedef blasint integer;

typedef unsigned int uinteger;
typedef char *address;
typedef short int shortint;
typedef float real;
typedef double doublereal;
typedef struct { real r, i; } complex;
typedef struct { doublereal r, i; } doublecomplex;
#ifdef _MSC_VER
static inline _Fcomplex Cf(complex *z) {_Fcomplex zz={z->r , z->i}; return zz;}
static inline _Dcomplex Cd(doublecomplex *z) {_Dcomplex zz={z->r , z->i};return zz;}
static inline _Fcomplex * _pCf(complex *z) {return (_Fcomplex*)z;}
static inline _Dcomplex * _pCd(doublecomplex *z) {return (_Dcomplex*)z;}
#else
static inline _Complex float Cf(complex *z) {return z->r + z->i*_Complex_I;}
static inline _Complex double Cd(doublecomplex *z) {return z->r + z->i*_Complex_I;}
static inline _Complex float * _pCf(complex *z) {return (_Complex float*)z;}
static inline _Complex double * _pCd(doublecomplex *z) {return (_Complex double*)z;}
#endif
#define pCf(z) (*_pCf(z))
#define pCd(z) (*_pCd(z))
typedef char integer1;

#define TRUE_ (1)
#define FALSE_ (0)

/* Extern is for use with -E */
#ifndef Extern
#define Extern extern
#endif

/* I/O stuff */

typedef int flag;
typedef int ftnlen;
typedef int ftnint;

/*external read, write*/
typedef struct
{	flag cierr;
	ftnint ciunit;
	flag ciend;
	char *cifmt;
	ftnint cirec;
} cilist;

/*internal read, write*/
typedef struct
{	flag icierr;
	char *iciunit;
	flag iciend;
	char *icifmt;
	ftnint icirlen;
	ftnint icirnum;
} icilist;

/*open*/
typedef struct
{	flag oerr;
	ftnint ounit;
	char *ofnm;
	ftnlen ofnmlen;
	char *osta;
	char *oacc;
	char *ofm;
	ftnint orl;
	char *oblnk;
} olist;

/*close*/
typedef struct
{	flag cerr;
	ftnint cunit;
	char *csta;
} cllist;

/*rewind, backspace, endfile*/
typedef struct
{	flag aerr;
	ftnint aunit;
} alist;

/* inquire */
typedef struct
{	flag inerr;
	ftnint inunit;
	char *infile;
	ftnlen infilen;
	ftnint	*inex;	/*parameters in standard's order*/
	ftnint	*inopen;
	ftnint	*innum;
	ftnint	*innamed;
	char	*inname;
	ftnlen	innamlen;
	char	*inacc;
	ftnlen	inacclen;
	char	*inseq;
	ftnlen	inseqlen;
	char 	*indir;
	ftnlen	indirlen;
	char	*infmt;
	ftnlen	infmtlen;
	char	*inform;
	ftnint	informlen;
	char	*inunf;
	ftnlen	inunflen;
	ftnint	*inrecl;
	ftnint	*innrec;
	char	*inblank;
	ftnlen	inblanklen;
} inlist;

#define VOID void

union Multitype {	/* for multiple entry points */
	integer1 g;
	shortint h;
	integer i;
	/* longint j; */
	real r;
	doublereal d;
	complex c;
	doublecomplex z;
	};

typedef union Multitype Multitype;

struct Vardesc {	/* for Namelist */
	char *name;
	char *addr;
	ftnlen *dims;
	int  type;
	};
typedef struct Vardesc Vardesc;

struct Namelist {
	char *name;
	Vardesc **vars;
	int nvars;
	};
typedef struct Namelist Namelist;

#define abs(x) ((x) >= 0 ? (x) : -(x))
#define dabs(x) (fabs(x))
#define f2cmin(a,b) ((a) <= (b) ? (a) : (b))
#define f2cmax(a,b) ((a) >= (b) ? (a) : (b))
#define dmin(a,b) (f2cmin(a,b))
#define dmax(a,b) (f2cmax(a,b))
#define bit_test(a,b)	((a) >> (b) & 1)
#define bit_clear(a,b)	((a) & ~((uinteger)1 << (b)))
#define bit_set(a,b)	((a) |  ((uinteger)1 << (b)))

#define abort_() { sig_die("Fortran abort routine called", 1); }
#define c_abs(z) (cabsf(Cf(z)))
#define c_cos(R,Z) { pCf(R)=ccos(Cf(Z)); }
#ifdef _MSC_VER
#define c_div(c, a, b) {Cf(c)._Val[0] = (Cf(a)._Val[0]/Cf(b)._Val[0]); Cf(c)._Val[1]=(Cf(a)._Val[1]/Cf(b)._Val[1]);}
#define z_div(c, a, b) {Cd(c)._Val[0] = (Cd(a)._Val[0]/Cd(b)._Val[0]); Cd(c)._Val[1]=(Cd(a)._Val[1]/df(b)._Val[1]);}
#else
#define c_div(c, a, b) {pCf(c) = Cf(a)/Cf(b);}
#define z_div(c, a, b) {pCd(c) = Cd(a)/Cd(b);}
#endif
#define c_exp(R, Z) {pCf(R) = cexpf(Cf(Z));}
#define c_log(R, Z) {pCf(R) = clogf(Cf(Z));}
#define c_sin(R, Z) {pCf(R) = csinf(Cf(Z));}
//#define c_sqrt(R, Z) {*(R) = csqrtf(Cf(Z));}
#define c_sqrt(R, Z) {pCf(R) = csqrtf(Cf(Z));}
#define d_abs(x) (fabs(*(x)))
#define d_acos(x) (acos(*(x)))
#define d_asin(x) (asin(*(x)))
#define d_atan(x) (atan(*(x)))
#define d_atn2(x, y) (atan2(*(x),*(y)))
#define d_cnjg(R, Z) { pCd(R) = conj(Cd(Z)); }
#define r_cnjg(R, Z) { pCf(R) = conjf(Cf(Z)); }
#define d_cos(x) (cos(*(x)))
#define d_cosh(x) (cosh(*(x)))
#define d_dim(__a, __b) ( *(__a) > *(__b) ? *(__a) - *(__b) : 0.0 )
#define d_exp(x) (exp(*(x)))
#define d_imag(z) (cimag(Cd(z)))
#define r_imag(z) (cimagf(Cf(z)))
#define d_int(__x) (*(__x)>0 ? floor(*(__x)) : -floor(- *(__x)))
#define r_int(__x) (*(__x)>0 ? floor(*(__x)) : -floor(- *(__x)))
#define d_lg10(x) ( 0.43429448190325182765 * log(*(x)) )
#define r_lg10(x) ( 0.43429448190325182765 * log(*(x)) )
#define d_log(x) (log(*(x)))
#define d_mod(x, y) (fmod(*(x), *(y)))
#define u_nint(__x) ((__x)>=0 ? floor((__x) + .5) : -floor(.5 - (__x)))
#define d_nint(x) u_nint(*(x))
#define u_sign(__a,__b) ((__b) >= 0 ? ((__a) >= 0 ? (__a) : -(__a)) : -((__a) >= 0 ? (__a) : -(__a)))
#define d_sign(a,b) u_sign(*(a),*(b))
#define r_sign(a,b) u_sign(*(a),*(b))
#define d_sin(x) (sin(*(x)))
#define d_sinh(x) (sinh(*(x)))
#define d_sqrt(x) (sqrt(*(x)))
#define d_tan(x) (tan(*(x)))
#define d_tanh(x) (tanh(*(x)))
#define i_abs(x) abs(*(x))
#define i_dnnt(x) ((integer)u_nint(*(x)))
#define i_len(s, n) (n)
#define i_nint(x) ((integer)u_nint(*(x)))
#define i_sign(a,b) ((integer)u_sign((integer)*(a),(integer)*(b)))
#define pow_dd(ap, bp) ( pow(*(ap), *(bp)))
#define pow_si(B,E) spow_ui(*(B),*(E))
#define pow_ri(B,E) spow_ui(*(B),*(E))
#define pow_di(B,E) dpow_ui(*(B),*(E))
#define pow_zi(p, a, b) {pCd(p) = zpow_ui(Cd(a), *(b));}
#define pow_ci(p, a, b) {pCf(p) = cpow_ui(Cf(a), *(b));}
#define pow_zz(R,A,B) {pCd(R) = cpow(Cd(A),*(B));}
#define s_cat(lpp, rpp, rnp, np, llp) { 	ftnlen i, nc, ll; char *f__rp, *lp; 	ll = (llp); lp = (lpp); 	for(i=0; i < (int)*(np); ++i) {         	nc = ll; 	        if((rnp)[i] < nc) nc = (rnp)[i]; 	        ll -= nc;         	f__rp = (rpp)[i]; 	        while(--nc >= 0) *lp++ = *(f__rp)++;         } 	while(--ll >= 0) *lp++ = ' '; }
#define s_cmp(a,b,c,d) ((integer)strncmp((a),(b),f2cmin((c),(d))))
#define s_copy(A,B,C,D) { int __i,__m; for (__i=0, __m=f2cmin((C),(D)); __i<__m && (B)[__i] != 0; ++__i) (A)[__i] = (B)[__i]; }
#define sig_die(s, kill) { exit(1); }
#define s_stop(s, n) {exit(0);}
#define z_abs(z) (cabs(Cd(z)))
#define z_exp(R, Z) {pCd(R) = cexp(Cd(Z));}
#define z_sqrt(R, Z) {pCd(R) = csqrt(Cd(Z));}
#define myexit_() break;
#define mycycle() continue;
#define myceiling(w) {ceil(w)}
#define myhuge(w) {HUGE_VAL}
//#define mymaxloc_(w,s,e,n) {if (sizeof(*(w)) == sizeof(double)) dmaxloc_((w),*(s),*(e),n); else dmaxloc_((w),*(s),*(e),n);}
#define mymaxloc(w,s,e,n) {dmaxloc_(w,*(s),*(e),n)}

/* procedure parameter types for -A and -C++ */


/*  -- translated by f2c (version 20000121).
   You must link the resulting object file with the libraries:
	-lf2c -lm   (in that order)
*/




/* Table of constant values */

static real c_b4 = -1.f;
static real c_b5 = 1.f;
static integer c__1 = 1;
static real c_b38 = 0.f;

/* > \brief \b SLAHRD reduces the first nb columns of a general rectangular matrix A so that elements below th
e k-th subdiagonal are zero, and returns auxiliary matrices which are needed to apply the transformati
on to the unreduced part of A. */

/*  =========== DOCUMENTATION =========== */

/* Online html documentation available at */
/*            http://www.netlib.org/lapack/explore-html/ */

/* > \htmlonly */
/* > Download SLAHRD + dependencies */
/* > <a href="http://www.netlib.org/cgi-bin/netlibfiles.tgz?format=tgz&filename=/lapack/lapack_routine/slahrd.
f"> */
/* > [TGZ]</a> */
/* > <a href="http://www.netlib.org/cgi-bin/netlibfiles.zip?format=zip&filename=/lapack/lapack_routine/slahrd.
f"> */
/* > [ZIP]</a> */
/* > <a href="http://www.netlib.org/cgi-bin/netlibfiles.txt?format=txt&filename=/lapack/lapack_routine/slahrd.
f"> */
/* > [TXT]</a> */
/* > \endhtmlonly */

/*  Definition: */
/*  =========== */

/*       SUBROUTINE SLAHRD( N, K, NB, A, LDA, TAU, T, LDT, Y, LDY ) */

/*       INTEGER            K, LDA, LDT, LDY, N, NB */
/*       REAL               A( LDA, * ), T( LDT, NB ), TAU( NB ), */
/*      $                   Y( LDY, NB ) */


/* > \par Purpose: */
/*  ============= */
/* > */
/* > \verbatim */
/* > */
/* > This routine is deprecated and has been replaced by routine SLAHR2. */
/* > */
/* > SLAHRD reduces the first NB columns of a real general n-by-(n-k+1) */
/* > matrix A so that elements below the k-th subdiagonal are zero. The */
/* > reduction is performed by an orthogonal similarity transformation */
/* > Q**T * A * Q. The routine returns the matrices V and T which determine */
/* > Q as a block reflector I - V*T*V**T, and also the matrix Y = A * V * T. */
/* > \endverbatim */

/*  Arguments: */
/*  ========== */

/* > \param[in] N */
/* > \verbatim */
/* >          N is INTEGER */
/* >          The order of the matrix A. */
/* > \endverbatim */
/* > */
/* > \param[in] K */
/* > \verbatim */
/* >          K is INTEGER */
/* >          The offset for the reduction. Elements below the k-th */
/* >          subdiagonal in the first NB columns are reduced to zero. */
/* > \endverbatim */
/* > */
/* > \param[in] NB */
/* > \verbatim */
/* >          NB is INTEGER */
/* >          The number of columns to be reduced. */
/* > \endverbatim */
/* > */
/* > \param[in,out] A */
/* > \verbatim */
/* >          A is REAL array, dimension (LDA,N-K+1) */
/* >          On entry, the n-by-(n-k+1) general matrix A. */
/* >          On exit, the elements on and above the k-th subdiagonal in */
/* >          the first NB columns are overwritten with the corresponding */
/* >          elements of the reduced matrix; the elements below the k-th */
/* >          subdiagonal, with the array TAU, represent the matrix Q as a */
/* >          product of elementary reflectors. The other columns of A are */
/* >          unchanged. See Further Details. */
/* > \endverbatim */
/* > */
/* > \param[in] LDA */
/* > \verbatim */
/* >          LDA is INTEGER */
/* >          The leading dimension of the array A.  LDA >= f2cmax(1,N). */
/* > \endverbatim */
/* > */
/* > \param[out] TAU */
/* > \verbatim */
/* >          TAU is REAL array, dimension (NB) */
/* >          The scalar factors of the elementary reflectors. See Further */
/* >          Details. */
/* > \endverbatim */
/* > */
/* > \param[out] T */
/* > \verbatim */
/* >          T is REAL array, dimension (LDT,NB) */
/* >          The upper triangular matrix T. */
/* > \endverbatim */
/* > */
/* > \param[in] LDT */
/* > \verbatim */
/* >          LDT is INTEGER */
/* >          The leading dimension of the array T.  LDT >= NB. */
/* > \endverbatim */
/* > */
/* > \param[out] Y */
/* > \verbatim */
/* >          Y is REAL array, dimension (LDY,NB) */
/* >          The n-by-nb matrix Y. */
/* > \endverbatim */
/* > */
/* > \param[in] LDY */
/* > \verbatim */
/* >          LDY is INTEGER */
/* >          The leading dimension of the array Y. LDY >= N. */
/* > \endverbatim */

/*  Authors: */
/*  ======== */

/* > \author Univ. of Tennessee */
/* > \author Univ. of California Berkeley */
/* > \author Univ. of Colorado Denver */
/* > \author NAG Ltd. */

/* > \date December 2016 */

/* > \ingroup realOTHERauxiliary */

/* > \par Further Details: */
/*  ===================== */
/* > */
/* > \verbatim */
/* > */
/* >  The matrix Q is represented as a product of nb elementary reflectors */
/* > */
/* >     Q = H(1) H(2) . . . H(nb). */
/* > */
/* >  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+k-1) = 0, v(i+k) = 1; v(i+k+1:n) is stored on exit in */
/* >  A(i+k+1:n,i), and tau in TAU(i). */
/* > */
/* >  The elements of the vectors v together form the (n-k+1)-by-nb matrix */
/* >  V which is needed, with T and Y, to apply the transformation to the */
/* >  unreduced part of the matrix, using an update of the form: */
/* >  A := (I - V*T*V**T) * (A - Y*V**T). */
/* > */
/* >  The contents of A on exit are illustrated by the following example */
/* >  with n = 7, k = 3 and nb = 2: */
/* > */
/* >     ( a   h   a   a   a ) */
/* >     ( a   h   a   a   a ) */
/* >     ( a   h   a   a   a ) */
/* >     ( h   h   a   a   a ) */
/* >     ( v1  h   a   a   a ) */
/* >     ( v1  v2  a   a   a ) */
/* >     ( v1  v2  a   a   a ) */
/* > */
/* >  where a denotes an element of the original matrix A, h denotes a */
/* >  modified element of the upper Hessenberg matrix H, and vi denotes an */
/* >  element of the vector defining H(i). */
/* > \endverbatim */
/* > */
/*  ===================================================================== */
/* Subroutine */ void slahrd_(integer *n, integer *k, integer *nb, real *a, 
	integer *lda, real *tau, real *t, integer *ldt, real *y, integer *ldy)
{
    /* System generated locals */
    integer a_dim1, a_offset, t_dim1, t_offset, y_dim1, y_offset, i__1, i__2, 
	    i__3;
    real r__1;

    /* Local variables */
    integer i__;
    extern /* Subroutine */ void sscal_(integer *, real *, real *, integer *), 
	    sgemv_(char *, integer *, integer *, real *, real *, integer *, 
	    real *, integer *, real *, real *, integer *), scopy_(
	    integer *, real *, integer *, real *, integer *), saxpy_(integer *
	    , real *, real *, integer *, real *, integer *), strmv_(char *, 
	    char *, char *, integer *, real *, integer *, real *, integer *);
    real ei;
    extern /* Subroutine */ void slarfg_(integer *, real *, real *, integer *, 
	    real *);


/*  -- LAPACK auxiliary routine (version 3.7.0) -- */
/*  -- LAPACK is a software package provided by Univ. of Tennessee,    -- */
/*  -- Univ. of California Berkeley, Univ. of Colorado Denver and NAG Ltd..-- */
/*     December 2016 */


/*  ===================================================================== */


/*     Quick return if possible */

    /* Parameter adjustments */
    --tau;
    a_dim1 = *lda;
    a_offset = 1 + a_dim1 * 1;
    a -= a_offset;
    t_dim1 = *ldt;
    t_offset = 1 + t_dim1 * 1;
    t -= t_offset;
    y_dim1 = *ldy;
    y_offset = 1 + y_dim1 * 1;
    y -= y_offset;

    /* Function Body */
    if (*n <= 1) {
	return;
    }

    i__1 = *nb;
    for (i__ = 1; i__ <= i__1; ++i__) {
	if (i__ > 1) {

/*           Update A(1:n,i) */

/*           Compute i-th column of A - Y * V**T */

	    i__2 = i__ - 1;
	    sgemv_("No transpose", n, &i__2, &c_b4, &y[y_offset], ldy, &a[*k 
		    + i__ - 1 + a_dim1], lda, &c_b5, &a[i__ * a_dim1 + 1], &
		    c__1);

/*           Apply I - V * T**T * V**T to this column (call it b) from the */
/*           left, using the last column of T as workspace */

/*           Let  V = ( V1 )   and   b = ( b1 )   (first I-1 rows) */
/*                    ( V2 )             ( b2 ) */

/*           where V1 is unit lower triangular */

/*           w := V1**T * b1 */

	    i__2 = i__ - 1;
	    scopy_(&i__2, &a[*k + 1 + i__ * a_dim1], &c__1, &t[*nb * t_dim1 + 
		    1], &c__1);
	    i__2 = i__ - 1;
	    strmv_("Lower", "Transpose", "Unit", &i__2, &a[*k + 1 + a_dim1], 
		    lda, &t[*nb * t_dim1 + 1], &c__1);

/*           w := w + V2**T *b2 */

	    i__2 = *n - *k - i__ + 1;
	    i__3 = i__ - 1;
	    sgemv_("Transpose", &i__2, &i__3, &c_b5, &a[*k + i__ + a_dim1], 
		    lda, &a[*k + i__ + i__ * a_dim1], &c__1, &c_b5, &t[*nb * 
		    t_dim1 + 1], &c__1);

/*           w := T**T *w */

	    i__2 = i__ - 1;
	    strmv_("Upper", "Transpose", "Non-unit", &i__2, &t[t_offset], ldt,
		     &t[*nb * t_dim1 + 1], &c__1);

/*           b2 := b2 - V2*w */

	    i__2 = *n - *k - i__ + 1;
	    i__3 = i__ - 1;
	    sgemv_("No transpose", &i__2, &i__3, &c_b4, &a[*k + i__ + a_dim1],
		     lda, &t[*nb * t_dim1 + 1], &c__1, &c_b5, &a[*k + i__ + 
		    i__ * a_dim1], &c__1);

/*           b1 := b1 - V1*w */

	    i__2 = i__ - 1;
	    strmv_("Lower", "No transpose", "Unit", &i__2, &a[*k + 1 + a_dim1]
		    , lda, &t[*nb * t_dim1 + 1], &c__1);
	    i__2 = i__ - 1;
	    saxpy_(&i__2, &c_b4, &t[*nb * t_dim1 + 1], &c__1, &a[*k + 1 + i__ 
		    * a_dim1], &c__1);

	    a[*k + i__ - 1 + (i__ - 1) * a_dim1] = ei;
	}

/*        Generate the elementary reflector H(i) to annihilate */
/*        A(k+i+1:n,i) */

	i__2 = *n - *k - i__ + 1;
/* Computing MIN */
	i__3 = *k + i__ + 1;
	slarfg_(&i__2, &a[*k + i__ + i__ * a_dim1], &a[f2cmin(i__3,*n) + i__ * 
		a_dim1], &c__1, &tau[i__]);
	ei = a[*k + i__ + i__ * a_dim1];
	a[*k + i__ + i__ * a_dim1] = 1.f;

/*        Compute  Y(1:n,i) */

	i__2 = *n - *k - i__ + 1;
	sgemv_("No transpose", n, &i__2, &c_b5, &a[(i__ + 1) * a_dim1 + 1], 
		lda, &a[*k + i__ + i__ * a_dim1], &c__1, &c_b38, &y[i__ * 
		y_dim1 + 1], &c__1);
	i__2 = *n - *k - i__ + 1;
	i__3 = i__ - 1;
	sgemv_("Transpose", &i__2, &i__3, &c_b5, &a[*k + i__ + a_dim1], lda, &
		a[*k + i__ + i__ * a_dim1], &c__1, &c_b38, &t[i__ * t_dim1 + 
		1], &c__1);
	i__2 = i__ - 1;
	sgemv_("No transpose", n, &i__2, &c_b4, &y[y_offset], ldy, &t[i__ * 
		t_dim1 + 1], &c__1, &c_b5, &y[i__ * y_dim1 + 1], &c__1);
	sscal_(n, &tau[i__], &y[i__ * y_dim1 + 1], &c__1);

/*        Compute T(1:i,i) */

	i__2 = i__ - 1;
	r__1 = -tau[i__];
	sscal_(&i__2, &r__1, &t[i__ * t_dim1 + 1], &c__1);
	i__2 = i__ - 1;
	strmv_("Upper", "No transpose", "Non-unit", &i__2, &t[t_offset], ldt, 
		&t[i__ * t_dim1 + 1], &c__1)
		;
	t[i__ + i__ * t_dim1] = tau[i__];

/* L10: */
    }
    a[*k + *nb + *nb * a_dim1] = ei;

    return;

/*     End of SLAHRD */

} /* slahrd_ */