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_LEVEL1_AXPY_TCC
34 #define CXXBLAS_LEVEL1_AXPY_TCC 1
35
36 #include <cstdio>
37 #include "xflens/cxxblas/cxxblas.h"
38
39 namespace cxxblas {
40
41 template <typename IndexType, typename ALPHA, typename X, typename Y>
42 void
axpy_generic(IndexType n,const ALPHA & alpha,const X * x,IndexType incX,Y * y,IndexType incY)43 axpy_generic(IndexType n, const ALPHA &alpha, const X *x,
44 IndexType incX, Y *y, IndexType incY)
45 {
46 CXXBLAS_DEBUG_OUT("axpy_generic");
47
48 for (IndexType i=0, iX=0, iY=0; i<n; ++i, iX+=incX, iY+=incY) {
49 y[iY] += alpha*x[iX];
50 }
51 }
52
53 template <typename IndexType, typename ALPHA, typename X, typename Y>
54 void
axpy(IndexType n,const ALPHA & alpha,const X * x,IndexType incX,Y * y,IndexType incY)55 axpy(IndexType n, const ALPHA &alpha, const X *x,
56 IndexType incX, Y *y, IndexType incY)
57 {
58 if (incX<0) {
59 x -= incX*(n-1);
60 }
61 if (incY<0) {
62 y -= incY*(n-1);
63 }
64 axpy_generic(n, alpha, x, incX, y, incY);
65 }
66
67 #ifdef HAVE_CBLAS
68 // saxpy
69 template <typename IndexType>
70 typename If<IndexType>::isBlasCompatibleInteger
axpy(IndexType n,const float & alpha,const float * x,IndexType incX,float * y,IndexType incY)71 axpy(IndexType n, const float &alpha, const float *x, IndexType incX,
72 float *y, IndexType incY)
73 {
74 CXXBLAS_DEBUG_OUT("[" BLAS_IMPL "] cblas_saxpy");
75
76 cblas_saxpy(n, alpha, x, incX, y, incY);
77 }
78
79 // daxpy
80 template <typename IndexType>
81 typename If<IndexType>::isBlasCompatibleInteger
axpy(IndexType n,const double & alpha,const double * x,IndexType incX,double * y,IndexType incY)82 axpy(IndexType n, const double &alpha, const double *x, IndexType incX,
83 double *y, IndexType incY)
84 {
85 CXXBLAS_DEBUG_OUT("[" BLAS_IMPL "] cblas_daxpy");
86
87 cblas_daxpy(n, alpha, x, incX, y, incY);
88 }
89
90 // caxpy
91 template <typename IndexType>
92 typename If<IndexType>::isBlasCompatibleInteger
axpy(IndexType n,const ComplexFloat & alpha,const ComplexFloat * x,IndexType incX,ComplexFloat * y,IndexType incY)93 axpy(IndexType n, const ComplexFloat &alpha,
94 const ComplexFloat *x, IndexType incX,
95 ComplexFloat *y, IndexType incY)
96 {
97 CXXBLAS_DEBUG_OUT("[" BLAS_IMPL "] cblas_caxpy");
98
99 cblas_caxpy(n, reinterpret_cast<const float *>(&alpha),
100 reinterpret_cast<const float *>(x), incX,
101 reinterpret_cast<float *>(y), incY);
102 }
103
104 // zaxpy
105 template <typename IndexType>
106 typename If<IndexType>::isBlasCompatibleInteger
axpy(IndexType n,const ComplexDouble & alpha,const ComplexDouble * x,IndexType incX,ComplexDouble * y,IndexType incY)107 axpy(IndexType n, const ComplexDouble &alpha,
108 const ComplexDouble *x, IndexType incX,
109 ComplexDouble *y, IndexType incY)
110 {
111 CXXBLAS_DEBUG_OUT("[" BLAS_IMPL "] cblas_zaxpy");
112
113 cblas_zaxpy(n, reinterpret_cast<const double *>(&alpha),
114 reinterpret_cast<const double *>(x), incX,
115 reinterpret_cast<double *>(y), incY);
116 }
117
118 #endif // HAVE_CBLAS
119
120 } // namespace cxxblas
121
122 #endif // CXXBLAS_LEVEL1_AXPY_TCC
123