mirror of
https://github.com/amd/blis.git
synced 2026-05-11 01:30:00 +00:00
Replaced banded/packed BLAS2 stubs with f2c code.
Details: - Retired the blas2blis wrappers that simply called abort with a "not yet implemented" message. This includes all of the level-2 banded and packed routines. - Replaced the aforementioned with the corresponding netlib implementations having been run through f2c (with some customization). - Added directories named 'attic' to build/gen-make-frags/ignore_list.
This commit is contained in:
917
frame/compat/f2c/bla_hpr2.c
Normal file
917
frame/compat/f2c/bla_hpr2.c
Normal file
@@ -0,0 +1,917 @@
|
||||
/*
|
||||
|
||||
BLIS
|
||||
An object-based framework for developing high-performance BLAS-like
|
||||
libraries.
|
||||
|
||||
Copyright (C) 2013, The University of Texas
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
- Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
- Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in the
|
||||
documentation and/or other materials provided with the distribution.
|
||||
- Neither the name of The University of Texas nor the names of its
|
||||
contributors may be used to endorse or promote products derived
|
||||
from this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
*/
|
||||
|
||||
#include "blis2.h"
|
||||
|
||||
#ifdef BLIS_ENABLE_BLAS2BLIS
|
||||
|
||||
#include "bl2_f2c.h"
|
||||
|
||||
/* chpr2.f -- translated by f2c (version 19991025).
|
||||
You must link the resulting object file with the libraries:
|
||||
-lf2c -lm (in that order)
|
||||
*/
|
||||
|
||||
/* Subroutine */ int PASTEF77(c,hpr2)(char *uplo, integer *n, complex *alpha, complex *
|
||||
x, integer *incx, complex *y, integer *incy, complex *ap)
|
||||
{
|
||||
/* System generated locals */
|
||||
integer i__1, i__2, i__3, i__4, i__5, i__6;
|
||||
real r__1;
|
||||
complex q__1, q__2, q__3, q__4;
|
||||
|
||||
/* Builtin functions */
|
||||
void r_cnjg(complex *, complex *);
|
||||
|
||||
/* Local variables */
|
||||
integer info;
|
||||
complex temp1, temp2;
|
||||
integer i__, j, k;
|
||||
extern logical lsame_(char *, char *, ftnlen, ftnlen);
|
||||
integer kk, ix, iy, jx = 0, jy = 0, kx = 0, ky = 0;
|
||||
extern /* Subroutine */ int xerbla_(char *, integer *, ftnlen);
|
||||
|
||||
/* .. Scalar Arguments .. */
|
||||
/* .. Array Arguments .. */
|
||||
/* .. */
|
||||
|
||||
/* Purpose */
|
||||
/* ======= */
|
||||
|
||||
/* CHPR2 performs the hermitian rank 2 operation */
|
||||
|
||||
/* A := alpha*x*conjg( y' ) + conjg( alpha )*y*conjg( x' ) + A, */
|
||||
|
||||
/* where alpha is a scalar, x and y are n element vectors and A is an */
|
||||
/* n by n hermitian matrix, supplied in packed form. */
|
||||
|
||||
/* Parameters */
|
||||
/* ========== */
|
||||
|
||||
/* UPLO - CHARACTER*1. */
|
||||
/* On entry, UPLO specifies whether the upper or lower */
|
||||
/* triangular part of the matrix A is supplied in the packed */
|
||||
/* array AP as follows: */
|
||||
|
||||
/* UPLO = 'U' or 'u' The upper triangular part of A is */
|
||||
/* supplied in AP. */
|
||||
|
||||
/* UPLO = 'L' or 'l' The lower triangular part of A is */
|
||||
/* supplied in AP. */
|
||||
|
||||
/* Unchanged on exit. */
|
||||
|
||||
/* N - INTEGER. */
|
||||
/* On entry, N specifies the order of the matrix A. */
|
||||
/* N must be at least zero. */
|
||||
/* Unchanged on exit. */
|
||||
|
||||
/* ALPHA - COMPLEX . */
|
||||
/* On entry, ALPHA specifies the scalar alpha. */
|
||||
/* Unchanged on exit. */
|
||||
|
||||
/* X - COMPLEX array of dimension at least */
|
||||
/* ( 1 + ( n - 1 )*abs( INCX ) ). */
|
||||
/* Before entry, the incremented array X must contain the n */
|
||||
/* element vector x. */
|
||||
/* Unchanged on exit. */
|
||||
|
||||
/* INCX - INTEGER. */
|
||||
/* On entry, INCX specifies the increment for the elements of */
|
||||
/* X. INCX must not be zero. */
|
||||
/* Unchanged on exit. */
|
||||
|
||||
/* Y - COMPLEX array of dimension at least */
|
||||
/* ( 1 + ( n - 1 )*abs( INCY ) ). */
|
||||
/* Before entry, the incremented array Y must contain the n */
|
||||
/* element vector y. */
|
||||
/* Unchanged on exit. */
|
||||
|
||||
/* INCY - INTEGER. */
|
||||
/* On entry, INCY specifies the increment for the elements of */
|
||||
/* Y. INCY must not be zero. */
|
||||
/* Unchanged on exit. */
|
||||
|
||||
/* AP - COMPLEX array of DIMENSION at least */
|
||||
/* ( ( n*( n + 1 ) )/2 ). */
|
||||
/* Before entry with UPLO = 'U' or 'u', the array AP must */
|
||||
/* contain the upper triangular part of the hermitian matrix */
|
||||
/* packed sequentially, column by column, so that AP( 1 ) */
|
||||
/* contains a( 1, 1 ), AP( 2 ) and AP( 3 ) contain a( 1, 2 ) */
|
||||
/* and a( 2, 2 ) respectively, and so on. On exit, the array */
|
||||
/* AP is overwritten by the upper triangular part of the */
|
||||
/* updated matrix. */
|
||||
/* Before entry with UPLO = 'L' or 'l', the array AP must */
|
||||
/* contain the lower triangular part of the hermitian matrix */
|
||||
/* packed sequentially, column by column, so that AP( 1 ) */
|
||||
/* contains a( 1, 1 ), AP( 2 ) and AP( 3 ) contain a( 2, 1 ) */
|
||||
/* and a( 3, 1 ) respectively, and so on. On exit, the array */
|
||||
/* AP is overwritten by the lower triangular part of the */
|
||||
/* updated matrix. */
|
||||
/* Note that the imaginary parts of the diagonal elements need */
|
||||
/* not be set, they are assumed to be zero, and on exit they */
|
||||
/* are set to zero. */
|
||||
|
||||
|
||||
/* Level 2 Blas routine. */
|
||||
|
||||
/* -- Written on 22-October-1986. */
|
||||
/* Jack Dongarra, Argonne National Lab. */
|
||||
/* Jeremy Du Croz, Nag Central Office. */
|
||||
/* Sven Hammarling, Nag Central Office. */
|
||||
/* Richard Hanson, Sandia National Labs. */
|
||||
|
||||
|
||||
/* .. Parameters .. */
|
||||
/* .. Local Scalars .. */
|
||||
/* .. External Functions .. */
|
||||
/* .. External Subroutines .. */
|
||||
/* .. Intrinsic Functions .. */
|
||||
/* .. */
|
||||
/* .. Executable Statements .. */
|
||||
|
||||
/* Test the input parameters. */
|
||||
|
||||
/* Parameter adjustments */
|
||||
--ap;
|
||||
--y;
|
||||
--x;
|
||||
|
||||
/* Function Body */
|
||||
info = 0;
|
||||
if (! lsame_(uplo, "U", (ftnlen)1, (ftnlen)1) && ! lsame_(uplo, "L", (
|
||||
ftnlen)1, (ftnlen)1)) {
|
||||
info = 1;
|
||||
} else if (*n < 0) {
|
||||
info = 2;
|
||||
} else if (*incx == 0) {
|
||||
info = 5;
|
||||
} else if (*incy == 0) {
|
||||
info = 7;
|
||||
}
|
||||
if (info != 0) {
|
||||
xerbla_("CHPR2 ", &info, (ftnlen)6);
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* Quick return if possible. */
|
||||
|
||||
if (*n == 0 || (alpha->r == 0.f && alpha->i == 0.f)) {
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* Set up the start points in X and Y if the increments are not both */
|
||||
/* unity. */
|
||||
|
||||
if (*incx != 1 || *incy != 1) {
|
||||
if (*incx > 0) {
|
||||
kx = 1;
|
||||
} else {
|
||||
kx = 1 - (*n - 1) * *incx;
|
||||
}
|
||||
if (*incy > 0) {
|
||||
ky = 1;
|
||||
} else {
|
||||
ky = 1 - (*n - 1) * *incy;
|
||||
}
|
||||
jx = kx;
|
||||
jy = ky;
|
||||
}
|
||||
|
||||
/* Start the operations. In this version the elements of the array AP */
|
||||
/* are accessed sequentially with one pass through AP. */
|
||||
|
||||
kk = 1;
|
||||
if (lsame_(uplo, "U", (ftnlen)1, (ftnlen)1)) {
|
||||
|
||||
/* Form A when upper triangle is stored in AP. */
|
||||
|
||||
if (*incx == 1 && *incy == 1) {
|
||||
i__1 = *n;
|
||||
for (j = 1; j <= i__1; ++j) {
|
||||
i__2 = j;
|
||||
i__3 = j;
|
||||
if (x[i__2].r != 0.f || x[i__2].i != 0.f || (y[i__3].r != 0.f
|
||||
|| y[i__3].i != 0.f)) {
|
||||
r_cnjg(&q__2, &y[j]);
|
||||
q__1.r = alpha->r * q__2.r - alpha->i * q__2.i, q__1.i =
|
||||
alpha->r * q__2.i + alpha->i * q__2.r;
|
||||
temp1.r = q__1.r, temp1.i = q__1.i;
|
||||
i__2 = j;
|
||||
q__2.r = alpha->r * x[i__2].r - alpha->i * x[i__2].i,
|
||||
q__2.i = alpha->r * x[i__2].i + alpha->i * x[i__2]
|
||||
.r;
|
||||
r_cnjg(&q__1, &q__2);
|
||||
temp2.r = q__1.r, temp2.i = q__1.i;
|
||||
k = kk;
|
||||
i__2 = j - 1;
|
||||
for (i__ = 1; i__ <= i__2; ++i__) {
|
||||
i__3 = k;
|
||||
i__4 = k;
|
||||
i__5 = i__;
|
||||
q__3.r = x[i__5].r * temp1.r - x[i__5].i * temp1.i,
|
||||
q__3.i = x[i__5].r * temp1.i + x[i__5].i *
|
||||
temp1.r;
|
||||
q__2.r = ap[i__4].r + q__3.r, q__2.i = ap[i__4].i +
|
||||
q__3.i;
|
||||
i__6 = i__;
|
||||
q__4.r = y[i__6].r * temp2.r - y[i__6].i * temp2.i,
|
||||
q__4.i = y[i__6].r * temp2.i + y[i__6].i *
|
||||
temp2.r;
|
||||
q__1.r = q__2.r + q__4.r, q__1.i = q__2.i + q__4.i;
|
||||
ap[i__3].r = q__1.r, ap[i__3].i = q__1.i;
|
||||
++k;
|
||||
/* L10: */
|
||||
}
|
||||
i__2 = kk + j - 1;
|
||||
i__3 = kk + j - 1;
|
||||
i__4 = j;
|
||||
q__2.r = x[i__4].r * temp1.r - x[i__4].i * temp1.i,
|
||||
q__2.i = x[i__4].r * temp1.i + x[i__4].i *
|
||||
temp1.r;
|
||||
i__5 = j;
|
||||
q__3.r = y[i__5].r * temp2.r - y[i__5].i * temp2.i,
|
||||
q__3.i = y[i__5].r * temp2.i + y[i__5].i *
|
||||
temp2.r;
|
||||
q__1.r = q__2.r + q__3.r, q__1.i = q__2.i + q__3.i;
|
||||
r__1 = ap[i__3].r + q__1.r;
|
||||
ap[i__2].r = r__1, ap[i__2].i = 0.f;
|
||||
} else {
|
||||
i__2 = kk + j - 1;
|
||||
i__3 = kk + j - 1;
|
||||
r__1 = ap[i__3].r;
|
||||
ap[i__2].r = r__1, ap[i__2].i = 0.f;
|
||||
}
|
||||
kk += j;
|
||||
/* L20: */
|
||||
}
|
||||
} else {
|
||||
i__1 = *n;
|
||||
for (j = 1; j <= i__1; ++j) {
|
||||
i__2 = jx;
|
||||
i__3 = jy;
|
||||
if (x[i__2].r != 0.f || x[i__2].i != 0.f || (y[i__3].r != 0.f
|
||||
|| y[i__3].i != 0.f)) {
|
||||
r_cnjg(&q__2, &y[jy]);
|
||||
q__1.r = alpha->r * q__2.r - alpha->i * q__2.i, q__1.i =
|
||||
alpha->r * q__2.i + alpha->i * q__2.r;
|
||||
temp1.r = q__1.r, temp1.i = q__1.i;
|
||||
i__2 = jx;
|
||||
q__2.r = alpha->r * x[i__2].r - alpha->i * x[i__2].i,
|
||||
q__2.i = alpha->r * x[i__2].i + alpha->i * x[i__2]
|
||||
.r;
|
||||
r_cnjg(&q__1, &q__2);
|
||||
temp2.r = q__1.r, temp2.i = q__1.i;
|
||||
ix = kx;
|
||||
iy = ky;
|
||||
i__2 = kk + j - 2;
|
||||
for (k = kk; k <= i__2; ++k) {
|
||||
i__3 = k;
|
||||
i__4 = k;
|
||||
i__5 = ix;
|
||||
q__3.r = x[i__5].r * temp1.r - x[i__5].i * temp1.i,
|
||||
q__3.i = x[i__5].r * temp1.i + x[i__5].i *
|
||||
temp1.r;
|
||||
q__2.r = ap[i__4].r + q__3.r, q__2.i = ap[i__4].i +
|
||||
q__3.i;
|
||||
i__6 = iy;
|
||||
q__4.r = y[i__6].r * temp2.r - y[i__6].i * temp2.i,
|
||||
q__4.i = y[i__6].r * temp2.i + y[i__6].i *
|
||||
temp2.r;
|
||||
q__1.r = q__2.r + q__4.r, q__1.i = q__2.i + q__4.i;
|
||||
ap[i__3].r = q__1.r, ap[i__3].i = q__1.i;
|
||||
ix += *incx;
|
||||
iy += *incy;
|
||||
/* L30: */
|
||||
}
|
||||
i__2 = kk + j - 1;
|
||||
i__3 = kk + j - 1;
|
||||
i__4 = jx;
|
||||
q__2.r = x[i__4].r * temp1.r - x[i__4].i * temp1.i,
|
||||
q__2.i = x[i__4].r * temp1.i + x[i__4].i *
|
||||
temp1.r;
|
||||
i__5 = jy;
|
||||
q__3.r = y[i__5].r * temp2.r - y[i__5].i * temp2.i,
|
||||
q__3.i = y[i__5].r * temp2.i + y[i__5].i *
|
||||
temp2.r;
|
||||
q__1.r = q__2.r + q__3.r, q__1.i = q__2.i + q__3.i;
|
||||
r__1 = ap[i__3].r + q__1.r;
|
||||
ap[i__2].r = r__1, ap[i__2].i = 0.f;
|
||||
} else {
|
||||
i__2 = kk + j - 1;
|
||||
i__3 = kk + j - 1;
|
||||
r__1 = ap[i__3].r;
|
||||
ap[i__2].r = r__1, ap[i__2].i = 0.f;
|
||||
}
|
||||
jx += *incx;
|
||||
jy += *incy;
|
||||
kk += j;
|
||||
/* L40: */
|
||||
}
|
||||
}
|
||||
} else {
|
||||
|
||||
/* Form A when lower triangle is stored in AP. */
|
||||
|
||||
if (*incx == 1 && *incy == 1) {
|
||||
i__1 = *n;
|
||||
for (j = 1; j <= i__1; ++j) {
|
||||
i__2 = j;
|
||||
i__3 = j;
|
||||
if (x[i__2].r != 0.f || x[i__2].i != 0.f || (y[i__3].r != 0.f
|
||||
|| y[i__3].i != 0.f)) {
|
||||
r_cnjg(&q__2, &y[j]);
|
||||
q__1.r = alpha->r * q__2.r - alpha->i * q__2.i, q__1.i =
|
||||
alpha->r * q__2.i + alpha->i * q__2.r;
|
||||
temp1.r = q__1.r, temp1.i = q__1.i;
|
||||
i__2 = j;
|
||||
q__2.r = alpha->r * x[i__2].r - alpha->i * x[i__2].i,
|
||||
q__2.i = alpha->r * x[i__2].i + alpha->i * x[i__2]
|
||||
.r;
|
||||
r_cnjg(&q__1, &q__2);
|
||||
temp2.r = q__1.r, temp2.i = q__1.i;
|
||||
i__2 = kk;
|
||||
i__3 = kk;
|
||||
i__4 = j;
|
||||
q__2.r = x[i__4].r * temp1.r - x[i__4].i * temp1.i,
|
||||
q__2.i = x[i__4].r * temp1.i + x[i__4].i *
|
||||
temp1.r;
|
||||
i__5 = j;
|
||||
q__3.r = y[i__5].r * temp2.r - y[i__5].i * temp2.i,
|
||||
q__3.i = y[i__5].r * temp2.i + y[i__5].i *
|
||||
temp2.r;
|
||||
q__1.r = q__2.r + q__3.r, q__1.i = q__2.i + q__3.i;
|
||||
r__1 = ap[i__3].r + q__1.r;
|
||||
ap[i__2].r = r__1, ap[i__2].i = 0.f;
|
||||
k = kk + 1;
|
||||
i__2 = *n;
|
||||
for (i__ = j + 1; i__ <= i__2; ++i__) {
|
||||
i__3 = k;
|
||||
i__4 = k;
|
||||
i__5 = i__;
|
||||
q__3.r = x[i__5].r * temp1.r - x[i__5].i * temp1.i,
|
||||
q__3.i = x[i__5].r * temp1.i + x[i__5].i *
|
||||
temp1.r;
|
||||
q__2.r = ap[i__4].r + q__3.r, q__2.i = ap[i__4].i +
|
||||
q__3.i;
|
||||
i__6 = i__;
|
||||
q__4.r = y[i__6].r * temp2.r - y[i__6].i * temp2.i,
|
||||
q__4.i = y[i__6].r * temp2.i + y[i__6].i *
|
||||
temp2.r;
|
||||
q__1.r = q__2.r + q__4.r, q__1.i = q__2.i + q__4.i;
|
||||
ap[i__3].r = q__1.r, ap[i__3].i = q__1.i;
|
||||
++k;
|
||||
/* L50: */
|
||||
}
|
||||
} else {
|
||||
i__2 = kk;
|
||||
i__3 = kk;
|
||||
r__1 = ap[i__3].r;
|
||||
ap[i__2].r = r__1, ap[i__2].i = 0.f;
|
||||
}
|
||||
kk = kk + *n - j + 1;
|
||||
/* L60: */
|
||||
}
|
||||
} else {
|
||||
i__1 = *n;
|
||||
for (j = 1; j <= i__1; ++j) {
|
||||
i__2 = jx;
|
||||
i__3 = jy;
|
||||
if (x[i__2].r != 0.f || x[i__2].i != 0.f || (y[i__3].r != 0.f
|
||||
|| y[i__3].i != 0.f)) {
|
||||
r_cnjg(&q__2, &y[jy]);
|
||||
q__1.r = alpha->r * q__2.r - alpha->i * q__2.i, q__1.i =
|
||||
alpha->r * q__2.i + alpha->i * q__2.r;
|
||||
temp1.r = q__1.r, temp1.i = q__1.i;
|
||||
i__2 = jx;
|
||||
q__2.r = alpha->r * x[i__2].r - alpha->i * x[i__2].i,
|
||||
q__2.i = alpha->r * x[i__2].i + alpha->i * x[i__2]
|
||||
.r;
|
||||
r_cnjg(&q__1, &q__2);
|
||||
temp2.r = q__1.r, temp2.i = q__1.i;
|
||||
i__2 = kk;
|
||||
i__3 = kk;
|
||||
i__4 = jx;
|
||||
q__2.r = x[i__4].r * temp1.r - x[i__4].i * temp1.i,
|
||||
q__2.i = x[i__4].r * temp1.i + x[i__4].i *
|
||||
temp1.r;
|
||||
i__5 = jy;
|
||||
q__3.r = y[i__5].r * temp2.r - y[i__5].i * temp2.i,
|
||||
q__3.i = y[i__5].r * temp2.i + y[i__5].i *
|
||||
temp2.r;
|
||||
q__1.r = q__2.r + q__3.r, q__1.i = q__2.i + q__3.i;
|
||||
r__1 = ap[i__3].r + q__1.r;
|
||||
ap[i__2].r = r__1, ap[i__2].i = 0.f;
|
||||
ix = jx;
|
||||
iy = jy;
|
||||
i__2 = kk + *n - j;
|
||||
for (k = kk + 1; k <= i__2; ++k) {
|
||||
ix += *incx;
|
||||
iy += *incy;
|
||||
i__3 = k;
|
||||
i__4 = k;
|
||||
i__5 = ix;
|
||||
q__3.r = x[i__5].r * temp1.r - x[i__5].i * temp1.i,
|
||||
q__3.i = x[i__5].r * temp1.i + x[i__5].i *
|
||||
temp1.r;
|
||||
q__2.r = ap[i__4].r + q__3.r, q__2.i = ap[i__4].i +
|
||||
q__3.i;
|
||||
i__6 = iy;
|
||||
q__4.r = y[i__6].r * temp2.r - y[i__6].i * temp2.i,
|
||||
q__4.i = y[i__6].r * temp2.i + y[i__6].i *
|
||||
temp2.r;
|
||||
q__1.r = q__2.r + q__4.r, q__1.i = q__2.i + q__4.i;
|
||||
ap[i__3].r = q__1.r, ap[i__3].i = q__1.i;
|
||||
/* L70: */
|
||||
}
|
||||
} else {
|
||||
i__2 = kk;
|
||||
i__3 = kk;
|
||||
r__1 = ap[i__3].r;
|
||||
ap[i__2].r = r__1, ap[i__2].i = 0.f;
|
||||
}
|
||||
jx += *incx;
|
||||
jy += *incy;
|
||||
kk = kk + *n - j + 1;
|
||||
/* L80: */
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return 0;
|
||||
|
||||
/* End of CHPR2 . */
|
||||
|
||||
} /* chpr2_ */
|
||||
|
||||
/* zhpr2.f -- translated by f2c (version 19991025).
|
||||
You must link the resulting object file with the libraries:
|
||||
-lf2c -lm (in that order)
|
||||
*/
|
||||
|
||||
/* Subroutine */ int PASTEF77(z,hpr2)(char *uplo, integer *n, doublecomplex *alpha,
|
||||
doublecomplex *x, integer *incx, doublecomplex *y, integer *incy,
|
||||
doublecomplex *ap)
|
||||
{
|
||||
/* System generated locals */
|
||||
integer i__1, i__2, i__3, i__4, i__5, i__6;
|
||||
doublereal d__1;
|
||||
doublecomplex z__1, z__2, z__3, z__4;
|
||||
|
||||
/* Builtin functions */
|
||||
void d_cnjg(doublecomplex *, doublecomplex *);
|
||||
|
||||
/* Local variables */
|
||||
integer info;
|
||||
doublecomplex temp1, temp2;
|
||||
integer i__, j, k;
|
||||
extern logical lsame_(char *, char *, ftnlen, ftnlen);
|
||||
integer kk, ix, iy, jx = 0, jy = 0, kx = 0, ky = 0;
|
||||
extern /* Subroutine */ int xerbla_(char *, integer *, ftnlen);
|
||||
|
||||
/* .. Scalar Arguments .. */
|
||||
/* .. Array Arguments .. */
|
||||
/* .. */
|
||||
|
||||
/* Purpose */
|
||||
/* ======= */
|
||||
|
||||
/* ZHPR2 performs the hermitian rank 2 operation */
|
||||
|
||||
/* A := alpha*x*conjg( y' ) + conjg( alpha )*y*conjg( x' ) + A, */
|
||||
|
||||
/* where alpha is a scalar, x and y are n element vectors and A is an */
|
||||
/* n by n hermitian matrix, supplied in packed form. */
|
||||
|
||||
/* Parameters */
|
||||
/* ========== */
|
||||
|
||||
/* UPLO - CHARACTER*1. */
|
||||
/* On entry, UPLO specifies whether the upper or lower */
|
||||
/* triangular part of the matrix A is supplied in the packed */
|
||||
/* array AP as follows: */
|
||||
|
||||
/* UPLO = 'U' or 'u' The upper triangular part of A is */
|
||||
/* supplied in AP. */
|
||||
|
||||
/* UPLO = 'L' or 'l' The lower triangular part of A is */
|
||||
/* supplied in AP. */
|
||||
|
||||
/* Unchanged on exit. */
|
||||
|
||||
/* N - INTEGER. */
|
||||
/* On entry, N specifies the order of the matrix A. */
|
||||
/* N must be at least zero. */
|
||||
/* Unchanged on exit. */
|
||||
|
||||
/* ALPHA - COMPLEX*16 . */
|
||||
/* On entry, ALPHA specifies the scalar alpha. */
|
||||
/* Unchanged on exit. */
|
||||
|
||||
/* X - COMPLEX*16 array of dimension at least */
|
||||
/* ( 1 + ( n - 1 )*abs( INCX ) ). */
|
||||
/* Before entry, the incremented array X must contain the n */
|
||||
/* element vector x. */
|
||||
/* Unchanged on exit. */
|
||||
|
||||
/* INCX - INTEGER. */
|
||||
/* On entry, INCX specifies the increment for the elements of */
|
||||
/* X. INCX must not be zero. */
|
||||
/* Unchanged on exit. */
|
||||
|
||||
/* Y - COMPLEX*16 array of dimension at least */
|
||||
/* ( 1 + ( n - 1 )*abs( INCY ) ). */
|
||||
/* Before entry, the incremented array Y must contain the n */
|
||||
/* element vector y. */
|
||||
/* Unchanged on exit. */
|
||||
|
||||
/* INCY - INTEGER. */
|
||||
/* On entry, INCY specifies the increment for the elements of */
|
||||
/* Y. INCY must not be zero. */
|
||||
/* Unchanged on exit. */
|
||||
|
||||
/* AP - COMPLEX*16 array of DIMENSION at least */
|
||||
/* ( ( n*( n + 1 ) )/2 ). */
|
||||
/* Before entry with UPLO = 'U' or 'u', the array AP must */
|
||||
/* contain the upper triangular part of the hermitian matrix */
|
||||
/* packed sequentially, column by column, so that AP( 1 ) */
|
||||
/* contains a( 1, 1 ), AP( 2 ) and AP( 3 ) contain a( 1, 2 ) */
|
||||
/* and a( 2, 2 ) respectively, and so on. On exit, the array */
|
||||
/* AP is overwritten by the upper triangular part of the */
|
||||
/* updated matrix. */
|
||||
/* Before entry with UPLO = 'L' or 'l', the array AP must */
|
||||
/* contain the lower triangular part of the hermitian matrix */
|
||||
/* packed sequentially, column by column, so that AP( 1 ) */
|
||||
/* contains a( 1, 1 ), AP( 2 ) and AP( 3 ) contain a( 2, 1 ) */
|
||||
/* and a( 3, 1 ) respectively, and so on. On exit, the array */
|
||||
/* AP is overwritten by the lower triangular part of the */
|
||||
/* updated matrix. */
|
||||
/* Note that the imaginary parts of the diagonal elements need */
|
||||
/* not be set, they are assumed to be zero, and on exit they */
|
||||
/* are set to zero. */
|
||||
|
||||
|
||||
/* Level 2 Blas routine. */
|
||||
|
||||
/* -- Written on 22-October-1986. */
|
||||
/* Jack Dongarra, Argonne National Lab. */
|
||||
/* Jeremy Du Croz, Nag Central Office. */
|
||||
/* Sven Hammarling, Nag Central Office. */
|
||||
/* Richard Hanson, Sandia National Labs. */
|
||||
|
||||
|
||||
/* .. Parameters .. */
|
||||
/* .. Local Scalars .. */
|
||||
/* .. External Functions .. */
|
||||
/* .. External Subroutines .. */
|
||||
/* .. Intrinsic Functions .. */
|
||||
/* .. */
|
||||
/* .. Executable Statements .. */
|
||||
|
||||
/* Test the input parameters. */
|
||||
|
||||
/* Parameter adjustments */
|
||||
--ap;
|
||||
--y;
|
||||
--x;
|
||||
|
||||
/* Function Body */
|
||||
info = 0;
|
||||
if (! lsame_(uplo, "U", (ftnlen)1, (ftnlen)1) && ! lsame_(uplo, "L", (
|
||||
ftnlen)1, (ftnlen)1)) {
|
||||
info = 1;
|
||||
} else if (*n < 0) {
|
||||
info = 2;
|
||||
} else if (*incx == 0) {
|
||||
info = 5;
|
||||
} else if (*incy == 0) {
|
||||
info = 7;
|
||||
}
|
||||
if (info != 0) {
|
||||
xerbla_("ZHPR2 ", &info, (ftnlen)6);
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* Quick return if possible. */
|
||||
|
||||
if (*n == 0 || (alpha->r == 0. && alpha->i == 0.)) {
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* Set up the start points in X and Y if the increments are not both */
|
||||
/* unity. */
|
||||
|
||||
if (*incx != 1 || *incy != 1) {
|
||||
if (*incx > 0) {
|
||||
kx = 1;
|
||||
} else {
|
||||
kx = 1 - (*n - 1) * *incx;
|
||||
}
|
||||
if (*incy > 0) {
|
||||
ky = 1;
|
||||
} else {
|
||||
ky = 1 - (*n - 1) * *incy;
|
||||
}
|
||||
jx = kx;
|
||||
jy = ky;
|
||||
}
|
||||
|
||||
/* Start the operations. In this version the elements of the array AP */
|
||||
/* are accessed sequentially with one pass through AP. */
|
||||
|
||||
kk = 1;
|
||||
if (lsame_(uplo, "U", (ftnlen)1, (ftnlen)1)) {
|
||||
|
||||
/* Form A when upper triangle is stored in AP. */
|
||||
|
||||
if (*incx == 1 && *incy == 1) {
|
||||
i__1 = *n;
|
||||
for (j = 1; j <= i__1; ++j) {
|
||||
i__2 = j;
|
||||
i__3 = j;
|
||||
if (x[i__2].r != 0. || x[i__2].i != 0. || (y[i__3].r != 0. ||
|
||||
y[i__3].i != 0.)) {
|
||||
d_cnjg(&z__2, &y[j]);
|
||||
z__1.r = alpha->r * z__2.r - alpha->i * z__2.i, z__1.i =
|
||||
alpha->r * z__2.i + alpha->i * z__2.r;
|
||||
temp1.r = z__1.r, temp1.i = z__1.i;
|
||||
i__2 = j;
|
||||
z__2.r = alpha->r * x[i__2].r - alpha->i * x[i__2].i,
|
||||
z__2.i = alpha->r * x[i__2].i + alpha->i * x[i__2]
|
||||
.r;
|
||||
d_cnjg(&z__1, &z__2);
|
||||
temp2.r = z__1.r, temp2.i = z__1.i;
|
||||
k = kk;
|
||||
i__2 = j - 1;
|
||||
for (i__ = 1; i__ <= i__2; ++i__) {
|
||||
i__3 = k;
|
||||
i__4 = k;
|
||||
i__5 = i__;
|
||||
z__3.r = x[i__5].r * temp1.r - x[i__5].i * temp1.i,
|
||||
z__3.i = x[i__5].r * temp1.i + x[i__5].i *
|
||||
temp1.r;
|
||||
z__2.r = ap[i__4].r + z__3.r, z__2.i = ap[i__4].i +
|
||||
z__3.i;
|
||||
i__6 = i__;
|
||||
z__4.r = y[i__6].r * temp2.r - y[i__6].i * temp2.i,
|
||||
z__4.i = y[i__6].r * temp2.i + y[i__6].i *
|
||||
temp2.r;
|
||||
z__1.r = z__2.r + z__4.r, z__1.i = z__2.i + z__4.i;
|
||||
ap[i__3].r = z__1.r, ap[i__3].i = z__1.i;
|
||||
++k;
|
||||
/* L10: */
|
||||
}
|
||||
i__2 = kk + j - 1;
|
||||
i__3 = kk + j - 1;
|
||||
i__4 = j;
|
||||
z__2.r = x[i__4].r * temp1.r - x[i__4].i * temp1.i,
|
||||
z__2.i = x[i__4].r * temp1.i + x[i__4].i *
|
||||
temp1.r;
|
||||
i__5 = j;
|
||||
z__3.r = y[i__5].r * temp2.r - y[i__5].i * temp2.i,
|
||||
z__3.i = y[i__5].r * temp2.i + y[i__5].i *
|
||||
temp2.r;
|
||||
z__1.r = z__2.r + z__3.r, z__1.i = z__2.i + z__3.i;
|
||||
d__1 = ap[i__3].r + z__1.r;
|
||||
ap[i__2].r = d__1, ap[i__2].i = 0.;
|
||||
} else {
|
||||
i__2 = kk + j - 1;
|
||||
i__3 = kk + j - 1;
|
||||
d__1 = ap[i__3].r;
|
||||
ap[i__2].r = d__1, ap[i__2].i = 0.;
|
||||
}
|
||||
kk += j;
|
||||
/* L20: */
|
||||
}
|
||||
} else {
|
||||
i__1 = *n;
|
||||
for (j = 1; j <= i__1; ++j) {
|
||||
i__2 = jx;
|
||||
i__3 = jy;
|
||||
if (x[i__2].r != 0. || x[i__2].i != 0. || (y[i__3].r != 0. ||
|
||||
y[i__3].i != 0.)) {
|
||||
d_cnjg(&z__2, &y[jy]);
|
||||
z__1.r = alpha->r * z__2.r - alpha->i * z__2.i, z__1.i =
|
||||
alpha->r * z__2.i + alpha->i * z__2.r;
|
||||
temp1.r = z__1.r, temp1.i = z__1.i;
|
||||
i__2 = jx;
|
||||
z__2.r = alpha->r * x[i__2].r - alpha->i * x[i__2].i,
|
||||
z__2.i = alpha->r * x[i__2].i + alpha->i * x[i__2]
|
||||
.r;
|
||||
d_cnjg(&z__1, &z__2);
|
||||
temp2.r = z__1.r, temp2.i = z__1.i;
|
||||
ix = kx;
|
||||
iy = ky;
|
||||
i__2 = kk + j - 2;
|
||||
for (k = kk; k <= i__2; ++k) {
|
||||
i__3 = k;
|
||||
i__4 = k;
|
||||
i__5 = ix;
|
||||
z__3.r = x[i__5].r * temp1.r - x[i__5].i * temp1.i,
|
||||
z__3.i = x[i__5].r * temp1.i + x[i__5].i *
|
||||
temp1.r;
|
||||
z__2.r = ap[i__4].r + z__3.r, z__2.i = ap[i__4].i +
|
||||
z__3.i;
|
||||
i__6 = iy;
|
||||
z__4.r = y[i__6].r * temp2.r - y[i__6].i * temp2.i,
|
||||
z__4.i = y[i__6].r * temp2.i + y[i__6].i *
|
||||
temp2.r;
|
||||
z__1.r = z__2.r + z__4.r, z__1.i = z__2.i + z__4.i;
|
||||
ap[i__3].r = z__1.r, ap[i__3].i = z__1.i;
|
||||
ix += *incx;
|
||||
iy += *incy;
|
||||
/* L30: */
|
||||
}
|
||||
i__2 = kk + j - 1;
|
||||
i__3 = kk + j - 1;
|
||||
i__4 = jx;
|
||||
z__2.r = x[i__4].r * temp1.r - x[i__4].i * temp1.i,
|
||||
z__2.i = x[i__4].r * temp1.i + x[i__4].i *
|
||||
temp1.r;
|
||||
i__5 = jy;
|
||||
z__3.r = y[i__5].r * temp2.r - y[i__5].i * temp2.i,
|
||||
z__3.i = y[i__5].r * temp2.i + y[i__5].i *
|
||||
temp2.r;
|
||||
z__1.r = z__2.r + z__3.r, z__1.i = z__2.i + z__3.i;
|
||||
d__1 = ap[i__3].r + z__1.r;
|
||||
ap[i__2].r = d__1, ap[i__2].i = 0.;
|
||||
} else {
|
||||
i__2 = kk + j - 1;
|
||||
i__3 = kk + j - 1;
|
||||
d__1 = ap[i__3].r;
|
||||
ap[i__2].r = d__1, ap[i__2].i = 0.;
|
||||
}
|
||||
jx += *incx;
|
||||
jy += *incy;
|
||||
kk += j;
|
||||
/* L40: */
|
||||
}
|
||||
}
|
||||
} else {
|
||||
|
||||
/* Form A when lower triangle is stored in AP. */
|
||||
|
||||
if (*incx == 1 && *incy == 1) {
|
||||
i__1 = *n;
|
||||
for (j = 1; j <= i__1; ++j) {
|
||||
i__2 = j;
|
||||
i__3 = j;
|
||||
if (x[i__2].r != 0. || x[i__2].i != 0. || (y[i__3].r != 0. ||
|
||||
y[i__3].i != 0.)) {
|
||||
d_cnjg(&z__2, &y[j]);
|
||||
z__1.r = alpha->r * z__2.r - alpha->i * z__2.i, z__1.i =
|
||||
alpha->r * z__2.i + alpha->i * z__2.r;
|
||||
temp1.r = z__1.r, temp1.i = z__1.i;
|
||||
i__2 = j;
|
||||
z__2.r = alpha->r * x[i__2].r - alpha->i * x[i__2].i,
|
||||
z__2.i = alpha->r * x[i__2].i + alpha->i * x[i__2]
|
||||
.r;
|
||||
d_cnjg(&z__1, &z__2);
|
||||
temp2.r = z__1.r, temp2.i = z__1.i;
|
||||
i__2 = kk;
|
||||
i__3 = kk;
|
||||
i__4 = j;
|
||||
z__2.r = x[i__4].r * temp1.r - x[i__4].i * temp1.i,
|
||||
z__2.i = x[i__4].r * temp1.i + x[i__4].i *
|
||||
temp1.r;
|
||||
i__5 = j;
|
||||
z__3.r = y[i__5].r * temp2.r - y[i__5].i * temp2.i,
|
||||
z__3.i = y[i__5].r * temp2.i + y[i__5].i *
|
||||
temp2.r;
|
||||
z__1.r = z__2.r + z__3.r, z__1.i = z__2.i + z__3.i;
|
||||
d__1 = ap[i__3].r + z__1.r;
|
||||
ap[i__2].r = d__1, ap[i__2].i = 0.;
|
||||
k = kk + 1;
|
||||
i__2 = *n;
|
||||
for (i__ = j + 1; i__ <= i__2; ++i__) {
|
||||
i__3 = k;
|
||||
i__4 = k;
|
||||
i__5 = i__;
|
||||
z__3.r = x[i__5].r * temp1.r - x[i__5].i * temp1.i,
|
||||
z__3.i = x[i__5].r * temp1.i + x[i__5].i *
|
||||
temp1.r;
|
||||
z__2.r = ap[i__4].r + z__3.r, z__2.i = ap[i__4].i +
|
||||
z__3.i;
|
||||
i__6 = i__;
|
||||
z__4.r = y[i__6].r * temp2.r - y[i__6].i * temp2.i,
|
||||
z__4.i = y[i__6].r * temp2.i + y[i__6].i *
|
||||
temp2.r;
|
||||
z__1.r = z__2.r + z__4.r, z__1.i = z__2.i + z__4.i;
|
||||
ap[i__3].r = z__1.r, ap[i__3].i = z__1.i;
|
||||
++k;
|
||||
/* L50: */
|
||||
}
|
||||
} else {
|
||||
i__2 = kk;
|
||||
i__3 = kk;
|
||||
d__1 = ap[i__3].r;
|
||||
ap[i__2].r = d__1, ap[i__2].i = 0.;
|
||||
}
|
||||
kk = kk + *n - j + 1;
|
||||
/* L60: */
|
||||
}
|
||||
} else {
|
||||
i__1 = *n;
|
||||
for (j = 1; j <= i__1; ++j) {
|
||||
i__2 = jx;
|
||||
i__3 = jy;
|
||||
if (x[i__2].r != 0. || x[i__2].i != 0. || (y[i__3].r != 0. ||
|
||||
y[i__3].i != 0.)) {
|
||||
d_cnjg(&z__2, &y[jy]);
|
||||
z__1.r = alpha->r * z__2.r - alpha->i * z__2.i, z__1.i =
|
||||
alpha->r * z__2.i + alpha->i * z__2.r;
|
||||
temp1.r = z__1.r, temp1.i = z__1.i;
|
||||
i__2 = jx;
|
||||
z__2.r = alpha->r * x[i__2].r - alpha->i * x[i__2].i,
|
||||
z__2.i = alpha->r * x[i__2].i + alpha->i * x[i__2]
|
||||
.r;
|
||||
d_cnjg(&z__1, &z__2);
|
||||
temp2.r = z__1.r, temp2.i = z__1.i;
|
||||
i__2 = kk;
|
||||
i__3 = kk;
|
||||
i__4 = jx;
|
||||
z__2.r = x[i__4].r * temp1.r - x[i__4].i * temp1.i,
|
||||
z__2.i = x[i__4].r * temp1.i + x[i__4].i *
|
||||
temp1.r;
|
||||
i__5 = jy;
|
||||
z__3.r = y[i__5].r * temp2.r - y[i__5].i * temp2.i,
|
||||
z__3.i = y[i__5].r * temp2.i + y[i__5].i *
|
||||
temp2.r;
|
||||
z__1.r = z__2.r + z__3.r, z__1.i = z__2.i + z__3.i;
|
||||
d__1 = ap[i__3].r + z__1.r;
|
||||
ap[i__2].r = d__1, ap[i__2].i = 0.;
|
||||
ix = jx;
|
||||
iy = jy;
|
||||
i__2 = kk + *n - j;
|
||||
for (k = kk + 1; k <= i__2; ++k) {
|
||||
ix += *incx;
|
||||
iy += *incy;
|
||||
i__3 = k;
|
||||
i__4 = k;
|
||||
i__5 = ix;
|
||||
z__3.r = x[i__5].r * temp1.r - x[i__5].i * temp1.i,
|
||||
z__3.i = x[i__5].r * temp1.i + x[i__5].i *
|
||||
temp1.r;
|
||||
z__2.r = ap[i__4].r + z__3.r, z__2.i = ap[i__4].i +
|
||||
z__3.i;
|
||||
i__6 = iy;
|
||||
z__4.r = y[i__6].r * temp2.r - y[i__6].i * temp2.i,
|
||||
z__4.i = y[i__6].r * temp2.i + y[i__6].i *
|
||||
temp2.r;
|
||||
z__1.r = z__2.r + z__4.r, z__1.i = z__2.i + z__4.i;
|
||||
ap[i__3].r = z__1.r, ap[i__3].i = z__1.i;
|
||||
/* L70: */
|
||||
}
|
||||
} else {
|
||||
i__2 = kk;
|
||||
i__3 = kk;
|
||||
d__1 = ap[i__3].r;
|
||||
ap[i__2].r = d__1, ap[i__2].i = 0.;
|
||||
}
|
||||
jx += *incx;
|
||||
jy += *incy;
|
||||
kk = kk + *n - j + 1;
|
||||
/* L80: */
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return 0;
|
||||
|
||||
/* End of ZHPR2 . */
|
||||
|
||||
} /* zhpr2_ */
|
||||
|
||||
#endif
|
||||
|
||||
Reference in New Issue
Block a user