floraachy
/
OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
OpenBLAS/lapack-netlib/SRC/sgttrf.c

505 lines
13 KiB
C
Raw Permalink Blame History

#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 blasint logical;
typedef char logical1;
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 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)}
/* -- translated by f2c (version 20000121).
You must link the resulting object file with the libraries:
-lf2c -lm (in that order)
*/
/* > \brief \b SGTTRF */
/* =========== DOCUMENTATION =========== */
/* Online html documentation available at */
/* http://www.netlib.org/lapack/explore-html/ */
/* > \htmlonly */
/* > Download SGTTRF + dependencies */
/* > <a href="http://www.netlib.org/cgi-bin/netlibfiles.tgz?format=tgz&filename=/lapack/lapack_routine/sgttrf.
f"> */
/* > [TGZ]</a> */
/* > <a href="http://www.netlib.org/cgi-bin/netlibfiles.zip?format=zip&filename=/lapack/lapack_routine/sgttrf.
f"> */
/* > [ZIP]</a> */
/* > <a href="http://www.netlib.org/cgi-bin/netlibfiles.txt?format=txt&filename=/lapack/lapack_routine/sgttrf.
f"> */
/* > [TXT]</a> */
/* > \endhtmlonly */
/* Definition: */
/* =========== */
/* SUBROUTINE SGTTRF( N, DL, D, DU, DU2, IPIV, INFO ) */
/* INTEGER INFO, N */
/* INTEGER IPIV( * ) */
/* REAL D( * ), DL( * ), DU( * ), DU2( * ) */
/* > \par Purpose: */
/* ============= */
/* > */
/* > \verbatim */
/* > */
/* > SGTTRF computes an LU factorization of a real tridiagonal matrix A */
/* > using elimination with partial pivoting and row interchanges. */
/* > */
/* > The factorization has the form */
/* > A = L * U */
/* > where L is a product of permutation and unit lower bidiagonal */
/* > matrices and U is upper triangular with nonzeros in only the main */
/* > diagonal and first two superdiagonals. */
/* > \endverbatim */
/* Arguments: */
/* ========== */
/* > \param[in] N */
/* > \verbatim */
/* > N is INTEGER */
/* > The order of the matrix A. */
/* > \endverbatim */
/* > */
/* > \param[in,out] DL */
/* > \verbatim */
/* > DL is REAL array, dimension (N-1) */
/* > On entry, DL must contain the (n-1) sub-diagonal elements of */
/* > A. */
/* > */
/* > On exit, DL is overwritten by the (n-1) multipliers that */
/* > define the matrix L from the LU factorization of A. */
/* > \endverbatim */
/* > */
/* > \param[in,out] D */
/* > \verbatim */
/* > D is REAL array, dimension (N) */
/* > On entry, D must contain the diagonal elements of A. */
/* > */
/* > On exit, D is overwritten by the n diagonal elements of the */
/* > upper triangular matrix U from the LU factorization of A. */
/* > \endverbatim */
/* > */
/* > \param[in,out] DU */
/* > \verbatim */
/* > DU is REAL array, dimension (N-1) */
/* > On entry, DU must contain the (n-1) super-diagonal elements */
/* > of A. */
/* > */
/* > On exit, DU is overwritten by the (n-1) elements of the first */
/* > super-diagonal of U. */
/* > \endverbatim */
/* > */
/* > \param[out] DU2 */
/* > \verbatim */
/* > DU2 is REAL array, dimension (N-2) */
/* > On exit, DU2 is overwritten by the (n-2) elements of the */
/* > second super-diagonal of U. */
/* > \endverbatim */
/* > */
/* > \param[out] IPIV */
/* > \verbatim */
/* > IPIV is INTEGER array, dimension (N) */
/* > The pivot indices; for 1 <= i <= n, row i of the matrix was */
/* > interchanged with row IPIV(i). IPIV(i) will always be either */
/* > i or i+1; IPIV(i) = i indicates a row interchange was not */
/* > required. */
/* > \endverbatim */
/* > */
/* > \param[out] INFO */
/* > \verbatim */
/* > INFO is INTEGER */
/* > = 0: successful exit */
/* > < 0: if INFO = -k, the k-th argument had an illegal value */
/* > > 0: if INFO = k, U(k,k) 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. */
/* > \endverbatim */
/* Authors: */
/* ======== */
/* > \author Univ. of Tennessee */
/* > \author Univ. of California Berkeley */
/* > \author Univ. of Colorado Denver */
/* > \author NAG Ltd. */
/* > \date December 2016 */
/* > \ingroup realGTcomputational */
/* ===================================================================== */
/* Subroutine */ void sgttrf_(integer *n, real *dl, real *d__, real *du, real *
du2, integer *ipiv, integer *info)
{
/* System generated locals */
integer i__1;
real r__1, r__2;
/* Local variables */
real fact, temp;
integer i__;
extern /* Subroutine */ int xerbla_(char *, integer *, ftnlen);
/* -- LAPACK computational 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 */
/* ===================================================================== */
/* Parameter adjustments */
--ipiv;
--du2;
--du;
--d__;
--dl;
/* Function Body */
*info = 0;
if (*n < 0) {
*info = -1;
i__1 = -(*info);
xerbla_("SGTTRF", &i__1, (ftnlen)6);
return;
}
/* Quick return if possible */
if (*n == 0) {
return;
}
/* Initialize IPIV(i) = i and DU2(I) = 0 */
i__1 = *n;
for (i__ = 1; i__ <= i__1; ++i__) {
ipiv[i__] = i__;
/* L10: */
}
i__1 = *n - 2;
for (i__ = 1; i__ <= i__1; ++i__) {
du2[i__] = 0.f;
/* L20: */
}
i__1 = *n - 2;
for (i__ = 1; i__ <= i__1; ++i__) {
if ((r__1 = d__[i__], abs(r__1)) >= (r__2 = dl[i__], abs(r__2))) {
/* No row interchange required, eliminate DL(I) */
if (d__[i__] != 0.f) {
fact = dl[i__] / d__[i__];
dl[i__] = fact;
d__[i__ + 1] -= fact * du[i__];
}
} else {
/* Interchange rows I and I+1, eliminate DL(I) */
fact = d__[i__] / dl[i__];
d__[i__] = dl[i__];
dl[i__] = fact;
temp = du[i__];
du[i__] = d__[i__ + 1];
d__[i__ + 1] = temp - fact * d__[i__ + 1];
du2[i__] = du[i__ + 1];
du[i__ + 1] = -fact * du[i__ + 1];
ipiv[i__] = i__ + 1;
}
/* L30: */
}
if (*n > 1) {
i__ = *n - 1;
if ((r__1 = d__[i__], abs(r__1)) >= (r__2 = dl[i__], abs(r__2))) {
if (d__[i__] != 0.f) {
fact = dl[i__] / d__[i__];
dl[i__] = fact;
d__[i__ + 1] -= fact * du[i__];
}
} else {
fact = d__[i__] / dl[i__];
d__[i__] = dl[i__];
dl[i__] = fact;
temp = du[i__];
du[i__] = d__[i__ + 1];
d__[i__ + 1] = temp - fact * d__[i__ + 1];
ipiv[i__] = i__ + 1;
}
}
/* Check for a zero on the diagonal of U. */
i__1 = *n;
for (i__ = 1; i__ <= i__1; ++i__) {
if (d__[i__] == 0.f) {
*info = i__;
goto L50;
}
/* L40: */
}
L50:
return;
/* End of SGTTRF */
} /* sgttrf_ */
Reference in New Issue View Git Blame Copy Permalink