1 /*
2 * Copyright (c) 2009, Michael Lehn
3 *
4 * All rights reserved.
5 *
6 * Redistribution and use in source and binary forms, with or without
7 * modification, are permitted provided that the following conditions
8 * are met:
9 *
10 * 1) Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * 2) Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in
14 * the documentation and/or other materials provided with the
15 * distribution.
16 * 3) Neither the name of the FLENS development group nor the names of
17 * its contributors may be used to endorse or promote products derived
18 * from this software without specific prior written permission.
19 *
20 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
21 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
22 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
23 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
24 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
25 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
26 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
27 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
28 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
29 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
30 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
31 */
32
33 #ifndef CXXBLAS_LEVEL2_HPR2_TCC
34 #define CXXBLAS_LEVEL2_HPR2_TCC 1
35
36 #include <complex>
37 #include <cxxblas/level1/level1.h>
38
39 namespace cxxblas {
40
41 template <typename IndexType, typename ALPHA, typename VX, typename VY,
42 typename MA>
43 void
44 hpr2_generic(StorageOrder order, StorageUpLo upLo, Transpose conjugateA,
45 IndexType n,
46 const ALPHA &alpha,
47 const VX *x, IndexType incX,
48 const VY *y, IndexType incY,
49 MA *A)
50 {
51 if (alpha==ALPHA(0)) {
52 return;
53 }
54 if (order==ColMajor) {
55 upLo = (upLo==Upper) ? Lower : Upper;
56 conjugateA = Transpose(conjugateA^Conj);
57 hpr2_generic(RowMajor, upLo, conjugateA,
58 n, alpha, x, incX, y, incY, A);
59 return;
60 }
61 #ifdef CXXBLAS_USE_XERBLA
62 // insert error check here
63 #endif
64 if (upLo==Upper) {
65 if (conjugateA==Conj) {
66 for (IndexType i=0, iX=0, iY=0; i<n; ++i, iX+=incX, iY+=incY) {
67 axpy_generic(n-i, conjugate(alpha*x[iX]),
68 y+iY, incY,
69 A+i*(2*n-i+1)/2, IndexType(1));
70 axpy_generic(n-i, alpha*conjugate(y[iY]),
71 x+iX, incX,
72 A+i*(2*n-i+1)/2, IndexType(1));
73 }
74 } else {
75 for (IndexType i=0, iX=0, iY=0; i<n; ++i, iX+=incX, iY+=incY) {
76 acxpy_generic(n-i, alpha*x[iX],
77 y+iY, incY,
78 A+i*(2*n-i+1)/2, IndexType(1));
79 acxpy_generic(n-i, conjugate(alpha)*y[iY],
80 x+iX, incX,
81 A+i*(2*n-i+1)/2, IndexType(1));
82 }
83 }
84 for (IndexType i=0; i<n; ++i) {
85 A[i+i*(2*n-i-1)/2] = cxxblas::real(A[i+i*(2*n-i-1)/2]);
86 }
87 } else {
88 if (conjugateA==Conj) {
89 for (IndexType i=0, iX=0, iY=0; i<n; ++i, iX+=incX, iY+=incY) {
90 axpy_generic(i+1, conjugate(alpha*x[iX]),
91 y, incY,
92 A+i*(i+1)/2, IndexType(1));
93 axpy_generic(i+1, alpha*conjugate(y[iY]),
94 x, incX,
95 A+i*(i+1)/2, IndexType(1));
96 }
97 } else {
98 for (IndexType i=0, iX=0, iY=0; i<n; ++i, iX+=incX, iY+=incY) {
99 acxpy_generic(i+1, alpha*x[iX],
100 y, incY,
101 A+i*(i+1)/2, IndexType(1));
102 acxpy_generic(i+1, conjugate(alpha)*y[iY],
103 x, incX,
104 A+i*(i+1)/2, IndexType(1));
105 }
106 }
107 for (IndexType i=0; i<n; ++i) {
108 A[i+i*(i+1)/2] = cxxblas::real(A[i+i*(i+1)/2]);
109 }
110 }
111 }
112
113 template <typename IndexType, typename ALPHA, typename VX, typename VY,
114 typename MA>
115 void
116 hpr2(StorageOrder order, StorageUpLo upLo,
117 IndexType n,
118 const ALPHA &alpha,
119 const VX *x, IndexType incX,
120 const VY *y, IndexType incY,
121 MA *A)
122 {
123 CXXBLAS_DEBUG_OUT("hpr2_generic");
124
125 if (incX<0) {
126 x -= incX*(n-1);
127 }
128 if (incY<0) {
129 y -= incY*(n-1);
130 }
131 hpr2_generic(order, upLo, NoTrans, n, alpha, x, incX, y, incY, A);
132 }
133
134 } // namespace cxxblas
135
136 #endif // CXXBLAS_LEVEL2_HPR2_TCC
2 * Copyright (c) 2009, Michael Lehn
3 *
4 * All rights reserved.
5 *
6 * Redistribution and use in source and binary forms, with or without
7 * modification, are permitted provided that the following conditions
8 * are met:
9 *
10 * 1) Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * 2) Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in
14 * the documentation and/or other materials provided with the
15 * distribution.
16 * 3) Neither the name of the FLENS development group nor the names of
17 * its contributors may be used to endorse or promote products derived
18 * from this software without specific prior written permission.
19 *
20 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
21 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
22 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
23 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
24 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
25 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
26 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
27 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
28 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
29 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
30 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
31 */
32
33 #ifndef CXXBLAS_LEVEL2_HPR2_TCC
34 #define CXXBLAS_LEVEL2_HPR2_TCC 1
35
36 #include <complex>
37 #include <cxxblas/level1/level1.h>
38
39 namespace cxxblas {
40
41 template <typename IndexType, typename ALPHA, typename VX, typename VY,
42 typename MA>
43 void
44 hpr2_generic(StorageOrder order, StorageUpLo upLo, Transpose conjugateA,
45 IndexType n,
46 const ALPHA &alpha,
47 const VX *x, IndexType incX,
48 const VY *y, IndexType incY,
49 MA *A)
50 {
51 if (alpha==ALPHA(0)) {
52 return;
53 }
54 if (order==ColMajor) {
55 upLo = (upLo==Upper) ? Lower : Upper;
56 conjugateA = Transpose(conjugateA^Conj);
57 hpr2_generic(RowMajor, upLo, conjugateA,
58 n, alpha, x, incX, y, incY, A);
59 return;
60 }
61 #ifdef CXXBLAS_USE_XERBLA
62 // insert error check here
63 #endif
64 if (upLo==Upper) {
65 if (conjugateA==Conj) {
66 for (IndexType i=0, iX=0, iY=0; i<n; ++i, iX+=incX, iY+=incY) {
67 axpy_generic(n-i, conjugate(alpha*x[iX]),
68 y+iY, incY,
69 A+i*(2*n-i+1)/2, IndexType(1));
70 axpy_generic(n-i, alpha*conjugate(y[iY]),
71 x+iX, incX,
72 A+i*(2*n-i+1)/2, IndexType(1));
73 }
74 } else {
75 for (IndexType i=0, iX=0, iY=0; i<n; ++i, iX+=incX, iY+=incY) {
76 acxpy_generic(n-i, alpha*x[iX],
77 y+iY, incY,
78 A+i*(2*n-i+1)/2, IndexType(1));
79 acxpy_generic(n-i, conjugate(alpha)*y[iY],
80 x+iX, incX,
81 A+i*(2*n-i+1)/2, IndexType(1));
82 }
83 }
84 for (IndexType i=0; i<n; ++i) {
85 A[i+i*(2*n-i-1)/2] = cxxblas::real(A[i+i*(2*n-i-1)/2]);
86 }
87 } else {
88 if (conjugateA==Conj) {
89 for (IndexType i=0, iX=0, iY=0; i<n; ++i, iX+=incX, iY+=incY) {
90 axpy_generic(i+1, conjugate(alpha*x[iX]),
91 y, incY,
92 A+i*(i+1)/2, IndexType(1));
93 axpy_generic(i+1, alpha*conjugate(y[iY]),
94 x, incX,
95 A+i*(i+1)/2, IndexType(1));
96 }
97 } else {
98 for (IndexType i=0, iX=0, iY=0; i<n; ++i, iX+=incX, iY+=incY) {
99 acxpy_generic(i+1, alpha*x[iX],
100 y, incY,
101 A+i*(i+1)/2, IndexType(1));
102 acxpy_generic(i+1, conjugate(alpha)*y[iY],
103 x, incX,
104 A+i*(i+1)/2, IndexType(1));
105 }
106 }
107 for (IndexType i=0; i<n; ++i) {
108 A[i+i*(i+1)/2] = cxxblas::real(A[i+i*(i+1)/2]);
109 }
110 }
111 }
112
113 template <typename IndexType, typename ALPHA, typename VX, typename VY,
114 typename MA>
115 void
116 hpr2(StorageOrder order, StorageUpLo upLo,
117 IndexType n,
118 const ALPHA &alpha,
119 const VX *x, IndexType incX,
120 const VY *y, IndexType incY,
121 MA *A)
122 {
123 CXXBLAS_DEBUG_OUT("hpr2_generic");
124
125 if (incX<0) {
126 x -= incX*(n-1);
127 }
128 if (incY<0) {
129 y -= incY*(n-1);
130 }
131 hpr2_generic(order, upLo, NoTrans, n, alpha, x, incX, y, incY, A);
132 }
133
134 } // namespace cxxblas
135
136 #endif // CXXBLAS_LEVEL2_HPR2_TCC