Commit | Line | Data |
---|---|---|
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 | #ifndef __MACH__ | |
25 | .arm | |
26 | #endif | |
27 | ||
28 | .align 4 | |
29 | .globl convert_float_s16_asm | |
30 | #ifndef __MACH__ | |
31 | .type convert_float_s16_asm, %function | |
32 | #endif | |
33 | .globl _convert_float_s16_asm | |
34 | #ifndef __MACH__ | |
35 | .type _convert_float_s16_asm, %function | |
36 | #endif | |
37 | # convert_float_s16_asm(int16_t *out, const float *in, size_t samples) | |
38 | convert_float_s16_asm: | |
39 | _convert_float_s16_asm: | |
40 | # Hacky way to get a constant of 2^15. | |
41 | # ((2^4)^2)^2 * 0.5 = 2^15 | |
42 | vmov.f32 q8, #16.0 | |
43 | vmov.f32 q9, #0.5 | |
44 | vmul.f32 q8, q8, q8 | |
45 | vmul.f32 q8, q8, q8 | |
46 | vmul.f32 q8, q8, q9 | |
47 | ||
48 | 1: | |
49 | # Preload here? | |
50 | vld1.f32 {q0-q1}, [r1]! | |
51 | ||
52 | vmul.f32 q0, q0, q8 | |
53 | vmul.f32 q1, q1, q8 | |
54 | ||
55 | vcvt.s32.f32 q0, q0 | |
56 | vcvt.s32.f32 q1, q1 | |
57 | ||
58 | vqmovn.s32 d4, q0 | |
59 | vqmovn.s32 d5, q1 | |
60 | ||
61 | vst1.f32 {d4-d5}, [r0]! | |
62 | ||
63 | # Guaranteed to get samples in multiples of 8. | |
64 | subs r2, r2, #8 | |
65 | bne 1b | |
66 | ||
67 | bx lr | |
68 | ||
69 | #endif |