| 1 | /* |
| 2 | * ARM NEON optimised integer operations |
| 3 | * Copyright (c) 2009 Konstantin Shishkov |
| 4 | * |
| 5 | * This file is part of FFmpeg. |
| 6 | * |
| 7 | * FFmpeg is free software; you can redistribute it and/or |
| 8 | * modify it under the terms of the GNU Lesser General Public |
| 9 | * License as published by the Free Software Foundation; either |
| 10 | * version 2.1 of the License, or (at your option) any later version. |
| 11 | * |
| 12 | * FFmpeg is distributed in the hope that it will be useful, |
| 13 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 14 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 15 | * Lesser General Public License for more details. |
| 16 | * |
| 17 | * You should have received a copy of the GNU Lesser General Public |
| 18 | * License along with FFmpeg; if not, write to the Free Software |
| 19 | * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA |
| 20 | */ |
| 21 | |
| 22 | #include "libavutil/arm/asm.S" |
| 23 | |
| 24 | function ff_scalarproduct_int16_neon, export=1 |
| 25 | vmov.i16 q0, #0 |
| 26 | vmov.i16 q1, #0 |
| 27 | vmov.i16 q2, #0 |
| 28 | vmov.i16 q3, #0 |
| 29 | 1: vld1.16 {d16-d17}, [r0]! |
| 30 | vld1.16 {d20-d21}, [r1,:128]! |
| 31 | vmlal.s16 q0, d16, d20 |
| 32 | vld1.16 {d18-d19}, [r0]! |
| 33 | vmlal.s16 q1, d17, d21 |
| 34 | vld1.16 {d22-d23}, [r1,:128]! |
| 35 | vmlal.s16 q2, d18, d22 |
| 36 | vmlal.s16 q3, d19, d23 |
| 37 | subs r2, r2, #16 |
| 38 | bgt 1b |
| 39 | |
| 40 | vpadd.s32 d16, d0, d1 |
| 41 | vpadd.s32 d17, d2, d3 |
| 42 | vpadd.s32 d18, d4, d5 |
| 43 | vpadd.s32 d19, d6, d7 |
| 44 | vpadd.s32 d0, d16, d17 |
| 45 | vpadd.s32 d1, d18, d19 |
| 46 | vpadd.s32 d2, d0, d1 |
| 47 | vpaddl.s32 d3, d2 |
| 48 | vmov.32 r0, d3[0] |
| 49 | bx lr |
| 50 | endfunc |
| 51 | |