Some small performance improvements on 32-bit architectures.
[BearSSL] / src / int / i32_mulacc.c
1 /*
2 * Copyright (c) 2016 Thomas Pornin <pornin@bolet.org>
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining
5 * a copy of this software and associated documentation files (the
6 * "Software"), to deal in the Software without restriction, including
7 * without limitation the rights to use, copy, modify, merge, publish,
8 * distribute, sublicense, and/or sell copies of the Software, and to
9 * permit persons to whom the Software is furnished to do so, subject to
10 * the following conditions:
11 *
12 * The above copyright notice and this permission notice shall be
13 * included in all copies or substantial portions of the Software.
14 *
15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
16 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
17 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
18 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
19 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
20 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
21 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
22 * SOFTWARE.
23 */
24
25 #include "inner.h"
26
27 /* see inner.h */
28 void
29 br_i32_mulacc(uint32_t *d, const uint32_t *a, const uint32_t *b)
30 {
31 size_t alen, blen, u;
32
33 alen = (a[0] + 31) >> 5;
34 blen = (b[0] + 31) >> 5;
35 d[0] = a[0] + b[0];
36 for (u = 0; u < blen; u ++) {
37 uint32_t f;
38 size_t v;
39 #if BR_64
40 uint64_t cc;
41 #else
42 uint32_t cc;
43 #endif
44
45 f = b[1 + u];
46 cc = 0;
47 for (v = 0; v < alen; v ++) {
48 uint64_t z;
49
50 z = (uint64_t)d[1 + u + v] + MUL(f, a[1 + v]) + cc;
51 cc = z >> 32;
52 d[1 + u + v] = (uint32_t)z;
53 }
54 d[1 + u + alen] = (uint32_t)cc;
55 }
56 }