Project Ne10
An Open Optimized Software Library Project for the ARM Architecture
Loading...
Searching...
No Matches
NE10_mla.c
1/*
2 * Copyright 2011-15 ARM Limited and Contributors.
3 * All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions are met:
7 * * Redistributions of source code must retain the above copyright
8 * notice, this list of conditions and the following disclaimer.
9 * * Redistributions in binary form must reproduce the above copyright
10 * notice, this list of conditions and the following disclaimer in the
11 * documentation and/or other materials provided with the distribution.
12 * * Neither the name of ARM Limited nor the
13 * names of its contributors may be used to endorse or promote products
14 * derived from this software without specific prior written permission.
15 *
16 * THIS SOFTWARE IS PROVIDED BY ARM LIMITED AND CONTRIBUTORS "AS IS" AND
17 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
18 * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
19 * DISCLAIMED. IN NO EVENT SHALL ARM LIMITED AND CONTRIBUTORS BE LIABLE FOR ANY
20 * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26 */
27
28/*
29 * NE10 Library : math/NE10_mla.c
30 */
31
32#include "NE10_types.h"
33#include "macros.h"
34
35#include <assert.h>
36
37ne10_result_t ne10_mla_float_c (ne10_float32_t * dst, ne10_float32_t * acc, ne10_float32_t * src1, ne10_float32_t * src2, ne10_uint32_t count)
38{
39 NE10_X_OPERATION_FLOAT_C
40 (
41 dst[ itr ] = acc[ itr ] + (src1[ itr ] * src2[ itr ]);
42 );
43}
44
45ne10_result_t ne10_vmla_vec2f_c (ne10_vec2f_t * dst, ne10_vec2f_t * acc, ne10_vec2f_t * src1, ne10_vec2f_t * src2, ne10_uint32_t count)
46{
47 NE10_X_OPERATION_FLOAT_C
48 (
49 dst[ itr ].x = acc[ itr ].x + (src1[ itr ].x * src2[ itr ].x);
50 dst[ itr ].y = acc[ itr ].y + (src1[ itr ].y * src2[ itr ].y);
51 );
52}
53
54ne10_result_t ne10_vmla_vec3f_c (ne10_vec3f_t * dst, ne10_vec3f_t * acc, ne10_vec3f_t * src1, ne10_vec3f_t * src2, ne10_uint32_t count)
55{
56 NE10_X_OPERATION_FLOAT_C
57 (
58 dst[ itr ].x = acc[ itr ].x + (src1[ itr ].x * src2[ itr ].x);
59 dst[ itr ].y = acc[ itr ].y + (src1[ itr ].y * src2[ itr ].y);
60 dst[ itr ].z = acc[ itr ].z + (src1[ itr ].z * src2[ itr ].z);
61 );
62}
63
64ne10_result_t ne10_vmla_vec4f_c (ne10_vec4f_t * dst, ne10_vec4f_t * acc, ne10_vec4f_t * src1, ne10_vec4f_t * src2, ne10_uint32_t count)
65{
66 NE10_X_OPERATION_FLOAT_C
67 (
68 dst[ itr ].x = acc[ itr ].x + (src1[ itr ].x * src2[ itr ].x);
69 dst[ itr ].y = acc[ itr ].y + (src1[ itr ].y * src2[ itr ].y);
70 dst[ itr ].z = acc[ itr ].z + (src1[ itr ].z * src2[ itr ].z);
71 dst[ itr ].w = acc[ itr ].w + (src1[ itr ].w * src2[ itr ].w);
72 );
73}
a 2-tuple of ne10_float32_t values.
Definition NE10_types.h:88
a 3-tuple of ne10_float32_t values.
Definition NE10_types.h:97
a 4-tuple of ne10_float32_t values.
Definition NE10_types.h:107