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"
46 // this is smallest dimension N of square input a to permit threading
47 // see graph in issue #1820 for explanation
48 #define MULTI_THREAD_MINIMAL 362
51 #define ERROR_NAME "XHEMV "
53 #define ERROR_NAME "ZHEMV "
55 #define ERROR_NAME "CHEMV "
60 void NAME(char *UPLO, blasint *N, FLOAT *ALPHA, FLOAT *a, blasint *LDA,
61 FLOAT *x, blasint *INCX, FLOAT *BETA, FLOAT *y, blasint *INCY){
63 char uplo_arg = *UPLO;
65 FLOAT alpha_r = ALPHA[0];
66 FLOAT alpha_i = ALPHA[1];
69 FLOAT beta_r = BETA[0];
70 FLOAT beta_i = BETA[1];
76 int (*hemv[])(BLASLONG, BLASLONG, FLOAT, FLOAT, FLOAT *, BLASLONG, FLOAT *, BLASLONG, FLOAT *, BLASLONG, FLOAT *) = {
77 HEMV_U, HEMV_L, HEMV_V, HEMV_M,
81 int (*hemv_thread[])(BLASLONG, FLOAT *, FLOAT *, BLASLONG, FLOAT *, BLASLONG, FLOAT *, BLASLONG, FLOAT *, int) = {
82 HEMV_THREAD_U, HEMV_THREAD_L, HEMV_THREAD_V, HEMV_THREAD_M,
95 if (uplo_arg == 'U') uplo = 0;
96 if (uplo_arg == 'L') uplo = 1;
97 if (uplo_arg == 'V') uplo = 2;
98 if (uplo_arg == 'M') uplo = 3;
102 if (incy == 0) info = 10;
103 if (incx == 0) info = 7;
104 if (lda < MAX(1, n)) info = 5;
106 if (uplo < 0) info = 1;
109 BLASFUNC(xerbla)(ERROR_NAME, &info, sizeof(ERROR_NAME));
115 void CNAME(enum CBLAS_ORDER order, enum CBLAS_UPLO Uplo, blasint n, void *VALPHA,
116 void *va, blasint lda, void *vx, blasint incx, void *VBETA, void *vy, blasint incy) {
118 FLOAT* ALPHA = (FLOAT*) VALPHA;
119 FLOAT* BETA = (FLOAT*) VBETA;
120 FLOAT* a = (FLOAT*) va;
121 FLOAT* x = (FLOAT*) vx;
122 FLOAT* y = (FLOAT*) vy;
124 FLOAT alpha_r = ALPHA[0];
125 FLOAT alpha_i = ALPHA[1];
126 FLOAT beta_r = BETA[0];
127 FLOAT beta_i = BETA[1];
136 int (*hemv[])(BLASLONG, BLASLONG, FLOAT, FLOAT, FLOAT *, BLASLONG, FLOAT *, BLASLONG, FLOAT *, BLASLONG, FLOAT *) = {
137 HEMV_U, HEMV_L, HEMV_V, HEMV_M,
141 int (*hemv_thread[])(BLASLONG, FLOAT *, FLOAT *, BLASLONG, FLOAT *, BLASLONG, FLOAT *, BLASLONG, FLOAT *, int) = {
142 HEMV_THREAD_U, HEMV_THREAD_L, HEMV_THREAD_V, HEMV_THREAD_M,
151 if (order == CblasColMajor) {
153 if (Uplo == CblasUpper) uplo = 0;
154 if (Uplo == CblasLower) uplo = 1;
158 if (incy == 0) info = 10;
159 if (incx == 0) info = 7;
160 if (lda < MAX(1, n)) info = 5;
162 if (uplo < 0) info = 1;
165 if (order == CblasRowMajor) {
167 if (Uplo == CblasUpper) uplo = 3;
168 if (Uplo == CblasLower) uplo = 2;
172 if (incy == 0) info = 10;
173 if (incx == 0) info = 7;
174 if (lda < MAX(1, n)) info = 5;
176 if (uplo < 0) info = 1;
180 BLASFUNC(xerbla)(ERROR_NAME, &info, sizeof(ERROR_NAME));
188 if ((beta_r != ONE) || (beta_i != ZERO)) SCAL_K(n, 0, 0, beta_r, beta_i, y, blasabs(incy), NULL, 0, NULL, 0);
190 if ((alpha_r == ZERO) && (alpha_i == ZERO)) return;
194 FUNCTION_PROFILE_START();
196 if (incx < 0 ) x -= (n - 1) * incx * 2;
197 if (incy < 0 ) y -= (n - 1) * incy * 2;
199 buffer = (FLOAT *)blas_memory_alloc(1);
202 if (n<MULTI_THREAD_MINIMAL) {
205 nthreads = num_cpu_avail(2);
211 (hemv[uplo])(n, n, alpha_r, alpha_i, a, lda, x, incx, y, incy, buffer);
216 (hemv_thread[uplo])(n, ALPHA, a, lda, x, incx, y, incy, buffer, nthreads);
221 blas_memory_free(buffer);
223 FUNCTION_PROFILE_END(4, n * n / 2 + n, 2 * n * n);