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 /*********************************************************************/
41 #ifdef FUNCTION_PROFILE
42 #include "functable.h"
45 #define MULTI_THREAD_MINIMAL 200000
47 #define MULTI_THREAD_MINIMAL 10000
51 void NAME(blasint *N, FLOAT *ALPHA, FLOAT *x, blasint *INCX, FLOAT *y, blasint *INCY){
59 void CNAME(blasint n, void *VALPHA, void *vx, blasint incx, void *vy, blasint incy){
60 FLOAT *ALPHA = (FLOAT*) VALPHA;
61 FLOAT *x = (FLOAT*) vx;
62 FLOAT *y = (FLOAT*) vy;
64 void CNAME(blasint n, FLOAT *ALPHA, FLOAT *x, blasint incx, FLOAT *y, blasint incy){
68 FLOAT alpha_r = *(ALPHA + 0);
69 FLOAT alpha_i = *(ALPHA + 1);
83 if ((alpha_r == ZERO) && (alpha_i == ZERO)) return;
87 FUNCTION_PROFILE_START();
89 if (incx < 0) x -= (n - 1) * incx * 2;
90 if (incy < 0) y -= (n - 1) * incy * 2;
93 //disable multi-thread when incx==0 or incy==0
94 //In that case, the threads would be dependent.
96 //Temporarily work-around the low performance issue with small imput size &
98 if (incx == 0 || incy == 0 || n <= MULTI_THREAD_MINIMAL)
101 nthreads = num_cpu_avail(1);
107 AXPYU_K (n, 0, 0, alpha_r, alpha_i, x, incx, y, incy, NULL, 0);
109 AXPYC_K(n, 0, 0, alpha_r, alpha_i, x, incx, y, incy, NULL, 0);
116 mode = BLAS_XDOUBLE | BLAS_COMPLEX;
117 #elif defined(DOUBLE)
118 mode = BLAS_DOUBLE | BLAS_COMPLEX;
120 mode = BLAS_SINGLE | BLAS_COMPLEX;
123 blas_level1_thread(mode, n, 0, 0, ALPHA, x, incx, y, incy, NULL, 0,
133 FUNCTION_PROFILE_END(4, 2 * n, 2 * n);