2 * LIBOIL - Library of Optimized Inner Loops
3 * Copyright (c) 2003,2004 David A. Schleef <ds@schleef.org>
6 * Redistribution and use in source and binary forms, with or without
7 * modification, are permitted provided that the following conditions
9 * 1. Redistributions of source code must retain the above copyright
10 * notice, this list of conditions and the following disclaimer.
11 * 2. Redistributions in binary form must reproduce the above copyright
12 * notice, this list of conditions and the following disclaimer in the
13 * documentation and/or other materials provided with the distribution.
15 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
16 * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
17 * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
18 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT,
19 * INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
20 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
21 * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
22 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
23 * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
24 * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
25 * POSSIBILITY OF SUCH DAMAGE.
32 #include <liboil/liboilfunction.h>
33 #include <liboil/simdpack/simdpack.h>
37 squaresum_f64_i10_simple(double *dest, double *src, int n)
43 sum2 += src[i]*src[i];
48 OIL_DEFINE_IMPL (squaresum_f64_i10_simple, squaresum_f64);
51 #include <multsum_f64.h>
53 squaresum_f64_i10_multsum(double *dest, double *src, int n)
55 multsum_f64(dest,src,src,n);
60 squaresum_f64_i10_unroll4a(double *dest, double *src, int n)
84 *dest = sum1 + sum2 + sum3 + sum4;
86 OIL_DEFINE_IMPL (squaresum_f64_i10_unroll4a, squaresum_f64);
89 squaresum_f64_i10_unroll4(double *dest, double *src, int n)
98 sum1 += src[0]*src[0];
103 sum1 += src[i]*src[i];
104 sum2 += src[i+1]*src[i+1];
105 sum3 += src[i+2]*src[i+2];
106 sum4 += src[i+3]*src[i+3];
109 *dest = sum1 + sum2 + sum3 + sum4;
111 OIL_DEFINE_IMPL (squaresum_f64_i10_unroll4, squaresum_f64);
114 squaresum_f64_i10_unroll8(double *dest, double *src, int n)
127 sum1 += src[0]*src[0];
132 sum1 += src[i]*src[i];
133 sum2 += src[i+1]*src[i+1];
134 sum3 += src[i+2]*src[i+2];
135 sum4 += src[i+3]*src[i+3];
136 sum5 += src[i+4]*src[i+4];
137 sum6 += src[i+5]*src[i+5];
138 sum7 += src[i+6]*src[i+6];
139 sum8 += src[i+7]*src[i+7];
142 *dest = sum1 + sum2 + sum3 + sum4 + sum5 + sum6 + sum7 + sum8;
144 OIL_DEFINE_IMPL (squaresum_f64_i10_unroll8, squaresum_f64);