git subrepo clone https://github.com/libretro/libretro-common.git deps/libretro-common
[pcsx_rearmed.git] / deps / libretro-common / audio / conversion / float_to_s16_neon.c
CommitLineData
3719602c
PC
1/* Copyright (C) 2010-2020 The RetroArch team
2 *
3 * ---------------------------------------------------------------------------------------
4 * The following license statement only applies to this file (float_to_s16_neon.S).
5 * ---------------------------------------------------------------------------------------
6 *
7 * Permission is hereby granted, free of charge,
8 * to any person obtaining a copy of this software and associated documentation files (the "Software"),
9 * to deal in the Software without restriction, including without limitation the rights to
10 * use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software,
11 * and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
12 *
13 * The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
14 *
15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
16 * INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
18 * IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
19 * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
21 */
22#if defined(__ARM_NEON__) && defined(HAVE_ARM_NEON_ASM_OPTIMIZATIONS)
23
24#if defined(__thumb__)
25#define DECL_ARMMODE(x) " .align 2\n" " .global " x "\n" " .thumb\n" " .thumb_func\n" " .type " x ", %function\n" x ":\n"
26#else
27#define DECL_ARMMODE(x) " .align 4\n" " .global " x "\n" " .arm\n" x ":\n"
28#endif
29
30asm(
31 DECL_ARMMODE("convert_float_s16_asm")
32 DECL_ARMMODE("_convert_float_s16_asm")
33 "# convert_float_s16_asm(int16_t *out, const float *in, size_t samples)\n"
34 " # Hacky way to get a constant of 2^15.\n"
35 " # ((2^4)^2)^2 * 0.5 = 2^15\n"
36 " vmov.f32 q8, #16.0\n"
37 " vmov.f32 q9, #0.5\n"
38 " vmul.f32 q8, q8, q8\n"
39 " vmul.f32 q8, q8, q8\n"
40 " vmul.f32 q8, q8, q9\n"
41 "\n"
42 "1:\n"
43 " # Preload here?\n"
44 " vld1.f32 {q0-q1}, [r1]!\n"
45 "\n"
46 " vmul.f32 q0, q0, q8\n"
47 " vmul.f32 q1, q1, q8\n"
48 "\n"
49 " vcvt.s32.f32 q0, q0\n"
50 " vcvt.s32.f32 q1, q1\n"
51 "\n"
52 " vqmovn.s32 d4, q0\n"
53 " vqmovn.s32 d5, q1\n"
54 "\n"
55 " vst1.f32 {d4-d5}, [r0]!\n"
56 "\n"
57 " # Guaranteed to get samples in multiples of 8.\n"
58 " subs r2, r2, #8\n"
59 " bne 1b\n"
60 "\n"
61 " bx lr\n"
62 "\n"
63 );
64#endif