1/* Copyright (C) 2013 Xiph.Org Foundation and contributors */
2/*
3   Redistribution and use in source and binary forms, with or without
4   modification, are permitted provided that the following conditions
5   are met:
6
7   - Redistributions of source code must retain the above copyright
8   notice, this list of conditions and the following disclaimer.
9
10   - Redistributions in binary form must reproduce the above copyright
11   notice, this list of conditions and the following disclaimer in the
12   documentation and/or other materials provided with the distribution.
13
14   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
15   ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
16   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
17   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER
18   OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
19   EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
20   PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
21   PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
22   LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
23   NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
24   SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
25*/
26
27#ifndef FIXED_ARMv4_H
28#define FIXED_ARMv4_H
29
30/** 16x32 multiplication, followed by a 16-bit shift right. Results fits in 32 bits */
31#undef MULT16_32_Q16
32static OPUS_INLINE opus_val32 MULT16_32_Q16_armv4(opus_val16 a, opus_val32 b)
33{
34  unsigned rd_lo;
35  int rd_hi;
36  __asm__(
37      "#MULT16_32_Q16\n\t"
38      "smull %0, %1, %2, %3\n\t"
39      : "=&r"(rd_lo), "=&r"(rd_hi)
40      : "%r"(b),"r"(a<<16)
41  );
42  return rd_hi;
43}
44#define MULT16_32_Q16(a, b) (MULT16_32_Q16_armv4(a, b))
45
46
47/** 16x32 multiplication, followed by a 15-bit shift right. Results fits in 32 bits */
48#undef MULT16_32_Q15
49static OPUS_INLINE opus_val32 MULT16_32_Q15_armv4(opus_val16 a, opus_val32 b)
50{
51  unsigned rd_lo;
52  int rd_hi;
53  __asm__(
54      "#MULT16_32_Q15\n\t"
55      "smull %0, %1, %2, %3\n\t"
56      : "=&r"(rd_lo), "=&r"(rd_hi)
57      : "%r"(b), "r"(a<<16)
58  );
59  /*We intentionally don't OR in the high bit of rd_lo for speed.*/
60  return rd_hi<<1;
61}
62#define MULT16_32_Q15(a, b) (MULT16_32_Q15_armv4(a, b))
63
64
65/** 16x32 multiply, followed by a 15-bit shift right and 32-bit add.
66    b must fit in 31 bits.
67    Result fits in 32 bits. */
68#undef MAC16_32_Q15
69#define MAC16_32_Q15(c, a, b) ADD32(c, MULT16_32_Q15(a, b))
70
71
72/** 32x32 multiplication, followed by a 31-bit shift right. Results fits in 32 bits */
73#undef MULT32_32_Q31
74#define MULT32_32_Q31(a,b) (opus_val32)((((opus_int64)(a)) * ((opus_int64)(b)))>>31)
75
76#endif
77