1 /*********************************************************************/
2 /* Copyright 2009, 2010 The University of Texas at Austin. */
3 /* All rights reserved. */
5 /* Redistribution and use in source and binary forms, with or */
6 /* without modification, are permitted provided that the following */
7 /* conditions are met: */
9 /* 1. Redistributions of source code must retain the above */
10 /* copyright notice, this list of conditions and the following */
13 /* 2. Redistributions in binary form must reproduce the above */
14 /* copyright notice, this list of conditions and the following */
15 /* disclaimer in the documentation and/or other materials */
16 /* provided with the distribution. */
18 /* THIS SOFTWARE IS PROVIDED BY THE UNIVERSITY OF TEXAS AT */
19 /* AUSTIN ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, */
20 /* INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF */
21 /* MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE */
22 /* DISCLAIMED. IN NO EVENT SHALL THE UNIVERSITY OF TEXAS AT */
23 /* AUSTIN OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, */
24 /* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES */
25 /* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE */
26 /* GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR */
27 /* BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF */
28 /* LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT */
29 /* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT */
30 /* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE */
31 /* POSSIBILITY OF SUCH DAMAGE. */
33 /* The views and conclusions contained in the software and */
34 /* documentation are those of the authors and should not be */
35 /* interpreted as representing official policies, either expressed */
36 /* or implied, of The University of Texas at Austin. */
37 /*********************************************************************/
42 #ifdef FUNCTION_PROFILE
43 #include "functable.h"
47 #define ERROR_NAME "XHPMV "
49 #define ERROR_NAME "ZHPMV "
51 #define ERROR_NAME "CHPMV "
54 static int (*hpmv[])(BLASLONG, FLOAT, FLOAT, FLOAT *, FLOAT *, BLASLONG, FLOAT *, BLASLONG, void *) = {
56 xhpmv_U, xhpmv_L, xhpmv_V, xhpmv_M,
58 zhpmv_U, zhpmv_L, zhpmv_V, zhpmv_M,
60 chpmv_U, chpmv_L, chpmv_V, chpmv_M,
65 static int (*hpmv_thread[])(BLASLONG, FLOAT *, FLOAT *, FLOAT *, BLASLONG, FLOAT *, BLASLONG, FLOAT *, int) = {
67 xhpmv_thread_U, xhpmv_thread_L, xhpmv_thread_V, xhpmv_thread_M,
69 zhpmv_thread_U, zhpmv_thread_L, zhpmv_thread_V, zhpmv_thread_M,
71 chpmv_thread_U, chpmv_thread_L, chpmv_thread_V, chpmv_thread_M,
78 void NAME(char *UPLO, blasint *N, FLOAT *ALPHA, FLOAT *a,
79 FLOAT *x, blasint *INCX, FLOAT *BETA, FLOAT *y, blasint *INCY){
81 char uplo_arg = *UPLO;
83 FLOAT alpha_r = ALPHA[0];
84 FLOAT alpha_i = ALPHA[1];
86 FLOAT beta_r = BETA[0];
87 FLOAT beta_i = BETA[1];
102 if (uplo_arg == 'U') uplo = 0;
103 if (uplo_arg == 'L') uplo = 1;
107 if (incy == 0) info = 9;
108 if (incx == 0) info = 6;
110 if (uplo < 0) info = 1;
113 BLASFUNC(xerbla)(ERROR_NAME, &info, sizeof(ERROR_NAME));
119 void CNAME(enum CBLAS_ORDER order,
120 enum CBLAS_UPLO Uplo,
124 void *vx, blasint incx,
126 void *vy, blasint incy){
128 FLOAT* ALPHA = (FLOAT*) VALPHA;
129 FLOAT* BETA = (FLOAT*) VBETA;
130 FLOAT* a = (FLOAT*) va;
131 FLOAT* x = (FLOAT*) vx;
132 FLOAT* y = (FLOAT*) vy;
134 FLOAT alpha_r = ALPHA[0];
135 FLOAT alpha_i = ALPHA[1];
136 FLOAT beta_r = BETA[0];
137 FLOAT beta_i = BETA[1];
150 if (order == CblasColMajor) {
151 if (Uplo == CblasUpper) uplo = 0;
152 if (Uplo == CblasLower) uplo = 1;
156 if (incy == 0) info = 9;
157 if (incx == 0) info = 6;
159 if (uplo < 0) info = 1;
162 if (order == CblasRowMajor) {
163 if (Uplo == CblasUpper) uplo = 3;
164 if (Uplo == CblasLower) uplo = 2;
168 if (incy == 0) info = 9;
169 if (incx == 0) info = 6;
171 if (uplo < 0) info = 1;
175 BLASFUNC(xerbla)(ERROR_NAME, &info, sizeof(ERROR_NAME));
183 if ((beta_r != ONE) || (beta_i != ZERO)) SCAL_K(n, 0, 0, beta_r, beta_i, y, blasabs(incy), NULL, 0, NULL, 0);
185 if ((alpha_r == ZERO) && (alpha_i == ZERO)) return;
189 FUNCTION_PROFILE_START();
191 if (incx < 0 ) x -= (n - 1) * incx * 2;
192 if (incy < 0 ) y -= (n - 1) * incy * 2;
194 buffer = (FLOAT *)blas_memory_alloc(1);
197 nthreads = num_cpu_avail(2);
202 (hpmv[uplo])(n, alpha_r, alpha_i, a, x, incx, y, incy, buffer);
207 (hpmv_thread[uplo])(n, ALPHA, a, x, incx, y, incy, buffer, nthreads);
212 blas_memory_free(buffer);
214 FUNCTION_PROFILE_END(4, n * n / 2 + n, n * n);